Daniel Bourke
I didnt eat food for 4 days, heres what happened
updated
Other links:
Learn ML (beginner-friendly courses I teach) - mrdbourke.com/ml-courses
ML courses/books I recommend - mrdbourke.com/ml-resources
Read my novel Charlie Walks - charliewalks.com
Connect elsewhere:
Web - https://dbourke.link/web
Twitter - twitter.com/mrdbourke
Twitch - twitch.tv/mrdbourke
ArXiv channel (past streams) - https://dbourke.link/archive-channel
Get email updates on my work - https://dbourke.link/newsletter
All code on GitHub - https://dbourke.link/pt-github
Ask a question - https://dbourke.link/pt-github-discussions
Read the course materials online - learnpytorch.io
Sign up for the full course on Zero to Mastery (20+ hours more video) - https://dbourke.link/ZTMPyTorch
Below are the timestamps/outline of the video. The video you're watching is comprised of 162 smaller videos but YouTube limits timestamps at 100 so some have been left out.
00:00 Hello :)
🛠 Chapter 0: PyTorch Fundamentals
01:17 0. Welcome and "what is deep learning?"
07:13 1. Why use machine/deep learning?
10:47 2. The number one rule of ML
16:27 3. Machine learning vs deep learning
22:34 4. Anatomy of neural networks
31:56 5. Different learning paradigms
36:28 6. What can deep learning be used for?
42:50 7. What is/why PyTorch?
53:05 8. What are tensors?
57:24 9. Outline
1:03:28 10. How to (and how not to) approach this course
1:08:37 11. Important resources
1:14:00 12. Getting setup
1:21:40 13. Introduction to tensors
1:35:07 14. Creating tensors
1:53:33 17. Tensor datatypes
2:02:58 18. Tensor attributes (information about tensors)
2:11:22 19. Manipulating tensors
2:17:22 20. Matrix multiplication
2:47:50 23. Finding the min, max, mean and sum
2:57:20 25. Reshaping, viewing and stacking
3:11:03 26. Squeezing, unsqueezing and permuting
3:23:00 27. Selecting data (indexing)
3:32:33 28. PyTorch and NumPy
3:41:42 29. Reproducibility
3:52:30 30. Accessing a GPU
4:04:21 31. Setting up device agnostic code
🗺 Chapter 1: PyTorch Workflow
4:16:59 33. Introduction to PyTorch Workflow
4:19:46 34. Getting setup
4:27:02 35. Creating a dataset with linear regression
4:36:44 36. Creating training and test sets (the most important concept in ML)
4:52:50 38. Creating our first PyTorch model
5:13:13 40. Discussing important model building classes
5:19:41 41. Checking out the internals of our model
5:29:33 42. Making predictions with our model
5:40:47 43. Training a model with PyTorch (intuition building)
5:49:03 44. Setting up a loss function and optimizer
6:01:56 45. PyTorch training loop intuition
6:39:37 48. Running our training loop epoch by epoch
6:49:03 49. Writing testing loop code
7:15:25 51. Saving/loading a model
7:44:00 54. Putting everything together
🤨 Chapter 2: Neural Network Classification
8:31:32 60. Introduction to machine learning classification
8:41:14 61. Classification input and outputs
8:50:22 62. Architecture of a classification neural network
9:09:13 64. Turing our data into tensors
9:25:30 66. Coding a neural network for classification data
9:43:27 68. Using torch.nn.Sequential
9:56:45 69. Loss, optimizer and evaluation functions for classification
10:11:37 70. From model logits to prediction probabilities to prediction labels
10:27:45 71. Train and test loops
10:57:27 73. Discussing options to improve a model
11:27:24 76. Creating a straight line dataset
11:45:34 78. Evaluating our model's predictions
11:50:58 79. The missing piece: non-linearity
12:42:04 84. Putting it all together with a multiclass problem
13:23:41 88. Troubleshooting a mutli-class model
😎 Chapter 3: Computer Vision
14:00:20 92. Introduction to computer vision
14:12:08 93. Computer vision input and outputs
14:22:18 94. What is a convolutional neural network?
14:27:21 95. TorchVision
14:36:42 96. Getting a computer vision dataset
15:01:06 98. Mini-batches
15:08:24 99. Creating DataLoaders
15:51:33 103. Training and testing loops for batched data
16:25:59 105. Running experiments on the GPU
16:29:46 106. Creating a model with non-linear functions
16:41:55 108. Creating a train/test loop
17:13:04 112. Convolutional neural networks (overview)
17:21:29 113. Coding a CNN
17:41:18 114. Breaking down nn.Conv2d/nn.MaxPool2d
18:28:34 118. Training our first CNN
18:43:54 120. Making predictions on random test samples
18:55:33 121. Plotting our best model predictions
19:19:06 123. Evaluating model predictions with a confusion matrix
🗃 Chapter 4: Custom Datasets
19:43:37 126. Introduction to custom datasets
19:59:26 128. Downloading a custom dataset of pizza, steak and sushi images
20:13:31 129. Becoming one with the data
20:38:43 132. Turning images into tensors
21:15:48 136. Creating image DataLoaders
21:24:52 137. Creating a custom dataset class (overview)
21:42:01 139. Writing a custom dataset class from scratch
22:21:22 142. Turning custom datasets into DataLoaders
22:28:22 143. Data augmentation
22:42:46 144. Building a baseline model
23:10:39 147. Getting a summary of our model with torchinfo
23:17:18 148. Creating training and testing loop functions
23:50:31 151. Plotting model 0 loss curves
23:59:34 152. Overfitting and underfitting
24:32:03 155. Plotting model 1 loss curves
24:35:25 156. Plotting all the loss curves
24:46:22 157. Predicting on custom data
#pytorch #machinelearning #deeplearning
Get the code on GitHub - github.com/mrdbourke/pytorch-apple-silicon
PyTorch on Mac announcement blog post - pytorch.org/blog/introducing-accelerated-pytorch-training-on-mac
Learn PyTorch - learnpytorch.io
Setup Apple M1 for TensorFlow - youtu.be/_1CaUOHhI6U
Other links:
Learn ML (beginner-friendly courses I teach) - mrdbourke.com/ml-courses
ML courses/books I recommend - mrdbourke.com/ml-resources
Read my novel Charlie Walks - charliewalks.com
Connect elsewhere:
Web - https://dbourke.link/web
Twitter - twitter.com/mrdbourke
Twitch - twitch.tv/mrdbourke
ArXiv channel (past streams) - https://dbourke.link/archive-channel
Get email updates on my work - https://dbourke.link/newsletter
Timestamps:
0:00 - Intro and what we’re covering
1:00 - Open Terminal
1:30 - Requirements
2:22 - 1. Download and install Homebrew
3:51 - 2. Download Miniforge3
4:35 - 3. Install Miniforge3 to get access to Conda
6:10 - 4. Restart Terminal
6:25 - 5. Create a directory to hold the environment/test PyTorch
6:40 - 6. Create a Conda environment and activate it
7:32 - 7. Install PyTorch for Mac
9:01 - 8. Install common data science packages (Jupyter, NumPy, pandas etc)
9:35 - 9. Start a Jupyter Notebook server and create a new notebook
10:00 - 10. Running import code and testing whether PyTorch has access to GPU
11:05 - 11. Seeing if PyTorch can send a tensor to the MPS device
The jingle is not endorsed by PyTorch whatsoever.
Materials for this video come from the Learn PyTorch for Deep Learning book - learnpytorch.io
Learn PyTorch for Deep Learning course (coming soon) - github.com/mrdbourke/pytorch-deep-learning
Connect elsewhere:
Web - https://dbourke.link/web
Twitter - twitter.com/mrdbourke
Twitch - twitch.tv/mrdbourke
ArXiv channel (past streams) - https://dbourke.link/archive-channel
Get email updates on my work - https://dbourke.link/newsletter
#pytorch #deeplearning
I'd like to own a large piece of land in the future.
So I'm learning what goes into maintaining one.
There's a few goats on the farm.
And usually they stand out in the fields eating grass.
But a few of them got worms.
So they're being hand fed.
They love fresh plants, especially cucumbers.
The way things go at the farm is,
work a couple of hours in the morning.
Then when it gets too hot, go for a swim in the creek.
And have lunch together.
And relax for the afternoon until it cools down.
Farm website - loopgrowers.com
My first day on a farm blog post - mrdbourke.com/my-first-day-on-a-farm
#shorts
Get $100USD off Coursera Plus yearly (before Jan 31 2022) - https://dbourke.link/coursera-plus-2022-deal
Notion data science curriculum template - https://dbourke.link/coursera-notion-template-2022
Blog post version - mrdbourke.com/how-to-learn-data-science-on-coursera-in-2022
Note: Coursera links are affiliate links which means if you click one and buy something, I may get money from it. This doesn't change the price. I'll use the funds to create more materials like this one.
Others links:
Learn ML (beginner-friendly courses I teach) - mrdbourke.com/ml-courses
ML courses/books I recommend - mrdbourke.com/ml-resources
Read my novel Charlie Walks - charliewalks.com
Connect elsewhere:
Web - https://dbourke.link/web
Twitter - twitter.com/mrdbourke
Twitch - twitch.tv/mrdbourke
ArXiv channel (past streams) - https://dbourke.link/archive-channel
Get email updates on my work - https://dbourke.link/newsletter
Timestamps:
0:00 - Intro
0:42 - Overview of what we’re covering
1:05 - Coursera Plus
2:11 - Defining different data roles (data scientist vs. data analyst)
3:12 - What is machine learning?
3:38 - Curriculum outline (beginner, bonus, advanced)
4:16 - Curriculum outline (beginner courses for Python, data science and machine learning)
5:16 - Course 1: Learning How to Learn
6:01 - Course 2: Python for Everybody
6:52 - Course 3: Applied Data Science with Python
7:46 - Course 4: Machine Learning Specialization
8:30 - Special mention: Andrew Ng’s classic machine learning course
8:59 - Course 5: Mathematics for Machine Learning
9:39 - Bonus 1: Google’s Introduction to Git and GitHub
10:31 - Bonus 2: “How does a beginner data scientist like me get experience?”
11:05 - Notion curriculum creation walkthrough
#datascience #machinelearning #notion
Location - Loop Growers, Brisbane, Australia
Website - loopgrowers.com
My first day on a farm (blog post) - mrdbourke.com/my-first-day-on-a-farm
Links:
Learn ML (beginner-friendly courses I teach) - mrdbourke.com/ml-courses
ML courses/books I recommend - mrdbourke.com/ml-resources
Read my novel Charlie Walks - charliewalks.com
Connect elsewhere:
Web - https://dbourke.link/web
Twitter - twitter.com/mrdbourke
Twitch - twitch.tv/mrdbourke
ArXiv channel (past streams) - https://dbourke.link/archive-channel
Get email updates on my work - https://dbourke.link/newsletter
#shorts #farm
Teach yourself programming in 10 years - norvig.com/21-days.html
My first day on a farm - mrdbourke.com/my-first-day-on-a-farm
Links:
Learn ML (beginner-friendly courses I teach) - mrdbourke.com/ml-courses
ML courses/books I recommend - mrdbourke.com/ml-resources
Read my novel Charlie Walks - charliewalks.com
Connect elsewhere:
Web - https://dbourke.link/web
Twitter - twitter.com/mrdbourke
Twitch - twitch.tv/mrdbourke
ArXiv channel (past streams) - https://dbourke.link/archive-channel
Get email updates on my work - https://dbourke.link/newsletter
Blog post with results - mrdbourke.com/m1-pro-m1-max-machine-learning-speed-test-comparison
Code on GitHub - github.com/mrdbourke/m1-machine-learning-test
Setup your M1 Mac for machine learning video - youtu.be/_1CaUOHhI6U
Links:
Learn ML (beginner-friendly courses I teach) - mrdbourke.com/ml-courses
ML courses/books I recommend - mrdbourke.com/ml-resources
Read my novel Charlie Walks - charliewalks.com
Connect elsewhere:
Web - https://dbourke.link/web
Twitter - twitter.com/mrdbourke
Twitch - twitch.tv/mrdbourke
ArXiv channel (past streams) - https://dbourke.link/archive-channel
Get email updates on my work - https://dbourke.link/newsletter
Timestamps:
0:00 - Intro
0:47 - Different Mac models we're testing
2:02 - Different experiments run across machines
2:51 - Final Cut Pro Large video H264 encoding export results
3:53 - Final Cut Pro Large video ProRes encoding export results
5:34 - Final Cut Pro Small video H264 encoding export results
6:10 - Final Cut Pro Small video ProRes encoding export results
7:04 - CreateML Image Classification model training results
9:02 - TensorFlow CIFAR10 & TinyVGG model training results
10:47 - TensorFlow Food101 & EfficientNetB0 feature extractor model training results
12:30 - Summary and recommendations
#MachineLearning #MacBookPro
In this video, we install Homebrew and Miniforge3 to create a Conda environment containing pandas, NumPy, Scikit-Learn, Matplotlib, Jupyter and TensorFlow.
We'll also setup TensorFlow to leverage the GPU on the new M1 chips.
Step by step instructions - github.com/mrdbourke/m1-machine-learning-test
See M1 machine learning speed test benchmarks - youtu.be/JWYsWhR3Pxg
Setup Apple Silicon Mac with PyTorch - youtu.be/Zx2MHdRgAIc
Links:
Learn ML (beginner-friendly courses I teach) - mrdbourke.com/ml-courses
ML courses/books I recommend - mrdbourke.com/ml-resources
Read my novel Charlie Walks - charliewalks.com
Connect elsewhere:
Web - https://dbourke.link/web
Twitter - twitter.com/mrdbourke
Twitch - twitch.tv/mrdbourke
ArXiv channel (past streams) - https://dbourke.link/archive-channel
Get email updates on my work - https://dbourke.link/newsletter
Timestamps:
0:00 - Intro
0:30 - What we're covering
1:00 - All resources are on GitHub
1:25 - Downloading and installing Homebrew
2:45 - Downloading and installing Miniforge3
4:25 - Restart terminal for changes to take effect
4:57 - Creating a directory to test out TensorFlow
5:30 - Creating a Conda environment for machine learning experiments
7:12 - Installing TensorFlow dependencies for Mac from Apple's Conda channel
8:40 - Installing tensorflow-macos
9:15 - Installing tensorflow-metal so you can run TensorFlow on your Mac's GPU
10:30 - Installing tensorflow-datasets (optional)
10:50 - Installing standard data science packages (Jupyter, NumPy, pandas, Matplotlib, Sklearn)
11:15 - Starting a Jupyter Notebook
11:40 - Testing importing different libraries and seeing if TensorFlow has GPU access
#MachineLearning #MacBookPro
Tune in for 10 hours straight (give or take a bit for dancing breaks/food etc).
Get the code - github.com/mrdbourke/food-not-food
Try the app - https://www.foodnotfood.app
Get the free stuff/surprises here - mrdbourke.com/100k-subs
Links:
Learn ML (beginner-friendly courses I teach) - mrdbourke.com/ml-courses
ML courses/books I recommend - mrdbourke.com/ml-resources
Read my novel Charlie Walks - charliewalks.com
Connect elsewhere:
Web - https://dbourke.link/web
Twitter - twitter.com/mrdbourke
Twitch - twitch.tv/mrdbourke
ArXiv channel (past streams) - https://dbourke.link/archive-channel
Get email updates on my work - https://dbourke.link/newsletter
Timestamps:
0:00 - Intro & hello
3:53 - Stream rules (10 pushups, squats, kicks, punches every hour)
5:00 - What we're going to build (food not food app)
10:58 - First commit
21:52 - Collecting a dataset (food and not food images)
2:20:30 - Food break
2:33:59 - Back to coding
3:36:09 - Downloading images
3:55:25 - Small model building
4:47:59 - Making train and test datasets
4:56:18 - Building binary classification model
5:29:54 - First model training
5:54:34 - Filtering food and non-food images from ImageNet
7:52:39 - Machine learning model deployment with TensorFlow Lite and TensorFlow JS
9:16:44 - Testing predictions with TensorFlow Lite model
9:40:39 - First prediction working on deployed model!!!
10:04:50 - Model deployed and live to the internet!!!
Yes, neural networks are completely based on math, though it's not 100% required to know everything happening behind the scenes to code and use neural networks.
So if you're thinking about getting into machine learning but being held back by the math, try writing algorithms in code first and learning math as you go, just like learning another programming language (math is Nature's programming language).
Original video source - youtu.be/OtznK7I11s8
Meme source - marksaroufim.substack.com/p/working-class-deep-learner
Links:
Learn ML (beginner-friendly courses I teach) - mrdbourke.com/ml-courses
ML courses/books I recommend - mrdbourke.com/ml-resources
Read my novel Charlie Walks - charliewalks.com
Connect elsewhere:
Web - https://dbourke.link/web
Twitter - twitter.com/mrdbourke
Twitch - twitch.tv/mrdbourke
ArXiv channel (past streams) - https://dbourke.link/archive-channel
Get email updates on my work - https://dbourke.link/newsletter
Why 97,777?
I like the number 7.
Links:
Learn ML (beginner-friendly courses I teach) - mrdbourke.com/ml-courses
ML courses/books I recommend - mrdbourke.com/ml-resources
Read my novel Charlie Walks - charliewalks.com
Connect elsewhere:
Web - https://dbourke.link/web
Twitter - twitter.com/mrdbourke
Twitch - twitch.tv/mrdbourke
ArXiv channel (past streams) - https://dbourke.link/archive-channel
Get email updates on my work - https://dbourke.link/newsletter
Timestamps:
0:00 - Intro & hello
3:39 - Preface & warning (I don't know much)
5:07 - How to ask a good question
5:25 - Q&A start
6:31 - What was your former job before machine learning?
8:47 - Do I have a date of release for the hardcover of my book?
9:04 - How to adapt to a Lindy life?
11:56 - How to overcome laziness before a workout or exercise or even a walk?
14:03 - Tidbits on eating quality food?
15:11 - Why did you get into programming?
16:19 - Best way to learn time series prediction for the stock market?
20:30 - What needs to be considered for full-stack ML applications?
23:28 - Advice for a computer science student (poor question)
25:40 - How to start a job before you have it
28:49 - Will you do a state of AI video this year?
29:50 - Will ML and AI influence bureaucracy?
31:48 - I'm 13 years old, am I too young to learn machine learning?
33:35 - I'm an ex-Google machine learning engineer, how can I make ML videos on YouTube?
35:53 - Ken Jee stops by
36:15 - Have I worked on distributed apps? And blockchain singularity net (I don't know what this is)
40:05 - Can anyone take fastai courses?
41:12 - How should I improve my coding skills?
44:10 - How important is domain-specific knowledge and picking the right models?
46:57 - Discuss the full ML lifecycle, including data collection to deployment
48:28 - Is NLP a good start project?
50:15 - Do data scientists write less code than software developers?
52:33 - Will there be object detection or advanced ML courses in the future?
54:52 - Is math necessary for machine learning?
57:41 - What projects are you working on?
58:19 - Rant on career vs family
1:01:07 - What book do you recommend for CNN's?
1:01:36 - Should I interview for ML intern starting position?
1:02:34 - How to enter into bioinformatics for non-biology students?
1:03:02 - Do you plan on making more advanced TensorFlow courses?
1:03:30 - How do you balance social life and learning?
1:05:04 - Have you ever been in a low point? If yes, how did you come out of it?
1:08:49 - Can you advise me on my final year project?
1:09:12 - What are you plans in the mid/long run?
1:11:08 - Do you plan on staying on your current job for a while? Or taking other opportunities?
1:14:14 - Thank you thank you thank you
This video is based on an article I wrote with the same name - mrdbourke.com/6-techniques-which-help-me-study-machine-learning-five-days-per-week
Links:
Learn ML (beginner-friendly courses I teach) - mrdbourke.com/ml-courses
ML courses/books I recommend - mrdbourke.com/ml-resources
Read my novel Charlie Walks - charliewalks.com
Connect elsewhere:
Web - https://dbourke.link/web
Twitter - twitter.com/mrdbourke
Twitch - twitch.tv/mrdbourke
ArXiv channel (past streams) - https://dbourke.link/archive-channel
Get email updates on my work - https://dbourke.link/newsletter
Timestamps:
0:00 - Intro
1:17 - 1: Reduce your search space
2:30 - 2: Fix your environment
3:45 - 3: Set the system up so you always win
4:51 - 4: Sometimes do nothing
6:15 - 5: Embrace the suck
6:56 - 6: The 3-year-old principle
8:45 - 7: Sleep your way to better knowledge
Thank you to Sam Bourke for the shoot planning and video editing help.
ML Monthly August 2021 - zerotomastery.io/blog/machine-learning-monthly-august-2021
Links:
Learn ML (beginner-friendly course) - https://dbourke.link/mlcourse
Learn Deep Learning + TensorFlow (code-first) - https://dbourke.link/tfcourse
Read TensorFlow Book (free) - learntensorflow.io
Read my first novel (about a machine learning engineer who wants to be a writer) - charliewalks.com
Connect elsewhere:
Web - https://dbourke.link/web
Twitch - https://dbourke.link/twitch
ArXiv channel (past streams) - https://dbourke.link/archive-channel
Get email updates on my work - https://dbourke.link/newsletter
Timestamps:
0:00 - Intro/hello
0:29 - My work (I published a novel!)
0:56 - Community submissions
1:05 - Artificialis Medium Publication and Discord Server
1:39 - Writing online + submit your work
3:20 - Resources from the internet
3:38 - What's the right level of specialization? by Erik Bernhardsson
5:00 - Modern Data Engineer Roadmap by datastacktv
6:41 - Facebook AI's new CNN + Transformer architecture for vision
8:35 - Create your own AI-generated art
11:17 - Self-driving car updates
12:00 - Tesla's AI Day keynote highlights
14:54 - Waymo Driver updates
15:53 - COMMA_CON keynote
16:30 - Machine learning in the wild
16:55 - Applied ML by Eugene Yan
17:53 - Apple's on-device photo recognition
19:10 - Google AI's improved polyp detection
21:12 - Outro
In this video, Daniel Bourke reads the first 42 pages (16 chapters) of the book out loud.
Book homepage - charliewalks.com
Buy the book (digital version) - mrdbourke.gumroad.com/l/charlie-walks
Other things I've made:
Learn ML (beginner-friendly course) - https://dbourke.link/mlcourse
Learn Deep Learning + TensorFlow (code-first) - https://dbourke.link/tfcourse
Read TensorFlow Book (free) - learntensorflow.io
Connect elsewhere:
Web - https://dbourke.link/web
Twitch - twitch.tv/mrdbourke
ArXiv channel (past streams) - youtube.com/channel/UCKt-z-AVy7duq6-_N-michg
Get email updates on my work - https://dbourke.link/newsletter
Timestamps:
0:00 - Intro
1:15 - Chapter 1
3:17 - Chapter 2
7:37 - Chapter 3
13:19 - Chapter 4
16:39 - Chapter 5
28:56 - Chapter 6
29:37 - Chapter 7
30:57 - Chapter 8
32:44 - Chapter 9
33:54 - Chapter 10
37:11 - Chapter 11
41:03 - Chapter 12
52:39 - Chapter 13
56:51 - Chapter 14
1:01:28 - Chapter 15
1:04:30 - Chapter 16
1:18:36 - Outro
3 day fast article - mrdbourke.com/3-day-fast
Things mentioned in video:
Lindy newsletter - paulskallas.substack.com/p/on-diet-part-1
Why you might feel cold during fasting - youtu.be/mX377LF8UpU
Zero fasting app - zerofasting.com
Timestamps:
0:00 - Day 1 start
0:30 - 3 day water only fast rules
0:56 - Warning
2:12 - First blood ketone measurement
3:17 - Afternoon Day 1
4:35 - Feeling cold during an extended fast
6:12 - End of Day 1
7:28 - Start of Day 2
10:04 - What happens as you get deeper into a fast
12:05 - The Lindy Newsletter and fasting and the Lindy effect
15:40 - End of Day 2
17:12 - Start of Day 3
18:18 - Day 1 to Day 3 weight changes
19:21 - What happens during ketosis
21:46 - Afternoon writing and reading
24:35 - Benefits and side effects of fasting
26:39 - Why fast?
28:25 - End of Day 3 (after breaking the fast)
30:09 - Start of Day 4 (one day after fast)
30:30 - Weight changes from Day 1 to Day 4
32:25 - Progress pictures and outro
ML Monthly July 2021 - zerotomastery.io/blog/machine-learning-monthly-july-2021
Learn ML (beginner-friendly course) - https://dbourke.link/mlcourse
Learn Deep Learning + TensorFlow (code-first) - https://dbourke.link/tfcourse
Read TensorFlow Book (free) - learntensorflow.io
Connect elsewhere:
Web - https://dbourke.link/web
Twitch - https://dbourke.link/twitch
ArXiv channel (past streams) - https://dbourke.link/archive-channel
Get email updates on my work - https://dbourke.link/newsletter
Timestamps:
0:00 - Intro/dance
0:24 - Where to sign up for more
1:05 - The Zero to Mastery TensorFlow for Deep Learning Course has been completed
1:35 - Free online book at learntensorflow.io
2:00 - Time series with TensorFlow
2:14 - Preparing for the TensorFlow Developer Certification
2:56 - How to submit your work to Machine Learning Monthly
3:24 - Skytowner tutorials, docs and recipes
5:38 - Saed's Towards Data Science Articles
8:00 - Building a data team at a mid-stage startup by Erik Bernhardsson
12:36 - End-to-end ML School
14:10 - Using Machine Learning to Enhance Speech Recognition in Cochlear Implants
19:04 - Learn NLP from the best: The Hugging Face 🤗 NLP Course
21:46 - Dance break 🕺
21:56 - Demo your ML models with Gradio
26:11 - GitHub Copilot: Blessing or Curse by Jeremy Howard
29:20 - Hand labelling data considered harmful (the perils of hand labelling data)
33:07 - Summary
33:40 - Bonus: comma_con
34:53 - Outro & more dancing
#machinelearning #machinelearningmonthly
ML Monthly June 2021 - zerotomastery.io/blog/machine-learning-monthly-june-2021
Learn ML (beginner-friendly course) - https://dbourke.link/mlcourse
Learn Deep Learning + TensorFlow (code-first) - https://dbourke.link/tfcourse
ML courses/books I recommend - mrdbourke.com/ml-resources
Read TensorFlow Book (free) - learntensorflow.io
Connect elsewhere:
Web - https://dbourke.link/web
Twitch - twitch.tv/mrdbourke
ArXiv channel (past streams) - youtube.com/channel/UCKt-z-AVy7duq6-_N-michg
Get email updates on my work - https://dbourke.link/newsletter
Timestamps:
0:00 - Intro
0:32 - Sign up for future issues
1:04 - TensorFlow for Deep Learning Book (learntensorflow.io)
2:20 - Uber’s Data Culture from First Principles
5:01 - Text-based video editing
7:27 - GitHub Copilot (AI-powered partner programming)
9:54 - Microsoft + GitHub + OpenAI
11:03 - Machine Learning Interviews Book by Chip Huyen
17:32 - How Tesla are building full-self-driving (Andrei Karpathy CVPR 2021 talk)
19:48 - Facebook Kats and LinkedIn Greykite (Python time series libraries)
21:24 - All kinds of data augmentation with AugLy by Facebook
23:11 - Made with ML MLOps course complete
25:13 - MLOps toys (a website for MLOps tools)
25:58 - Training Transformers with Compact Transformers in 30-minutes
27:45 - How to think about applying NLP in production by Ines Montani
29:27 - Outro/dancing 🕺
#machinelearningmonthly #machinelearning
ML Monthly May 2021 - zerotomastery.io/blog/machine-learning-monthly-may-2021
Learn ML (beginner-friendly course) - https://dbourke.link/mlcourse
Learn Deep Learning + TensorFlow (code-first) - https://dbourke.link/tfcourse
Connect elsewhere:
Web - https://dbourke.link/web
Twitch - twitch.tv/mrdbourke
ArXiv channel (past streams) - youtube.com/channel/UCKt-z-AVy7duq6-_N-michg
Get email updates on my work - https://dbourke.link/newsletter
Timestamps:
0:00 - Intro
0:24 - Google IO 2021
1:03 - Google's On-device Machine Learning Page
1:43 - TensorFlow Lite Models are now compatible with TensorFlow.js
2:28 - Create your own TensorFlow Lite models with the new Model Maker library
3:13 - TensorFlow Hub Upgrades
4:00 - TensorFlow Cloud (run your small experiments at cloud scale)
4:48 - Vertex AI (Google Cloud's new one-stop-shop for everything machine learning)
5:31 - The Practitioner's Guide to MLOps White Paper
6:13 - The new TensorFlow Town Square (TensorFlow Forum)
6:37 - People and AI Guidebook 2.0
7:53 - Know Your Data tool (beta)
8:32 - Where to learn more about Google IO ML & TensorFlow updates
8:57 - Next generation pose detection with MoveNet and TensorFlow.js
9:57 - Datasets and code on arXiv (thanks to paperswithcode)
10:31 - wav2vec-U (high performance speech recognition with no supervision)
12:14 - What is active learning? blog post by Roboflow
13:17 - Reproducible Deep Learning course by Simone Scardapane
14:25 - The Rise of HuggingFace by Mark Saroufim
15:06 - Outro & 🕺
#machinelearning #mlmontly
Machine Learning Monthly April 2021 - zerotomastery.io/blog/machine-learning-monthly-april-2021
Links:
Learn ML (beginner-friendly courses I teach) - mrdbourke.com/ml-courses
ML courses/books I recommend - mrdbourke.com/ml-resources
Read my novel Charlie Walks - charliewalks.com
Connect elsewhere:
Web - https://dbourke.link/web
Twitch - twitch.tv/mrdbourke
ArXiv channel (past streams) - youtube.com/channel/UCKt-z-AVy7duq6-_N-michg
Get email updates on my work - https://dbourke.link/newsletter
Timestamps:
0:00 - Intro/hello
1:06 - My New TensorFlow for Deep Learning course has launched!
1:50 - Louis Francois’ What’s AI channel
3:17 - The best resources from the internet
3:40 - “What kind of machine learning project should I work on?”
4:10 - Machine Learning is an infrastructure problem
5:35 - Apple’s Human Interface Guidelines for Machine Learning
10:00 - Make it easy for people to correct frequent or predictable mistakes (move towards a data flywheel)
10:48 - Google’s People and AI Research (PAIR)
14:23 - Microsoft’s design guidelines for Human-AI interaction
18:03 - Facebook’s Field Guide to Machine Learning
19:55 - Spotify’s 3 Principles for Designing ML-powered products
22:09 - From Big Data to Good Data by Andrew Ng
23:48 - The Data Flywheel
25:45 - Where to learn how to design ML-powered systems
28:42 - Outro/goodbye 👋
#machinelearning #machinelearningmonthly
Sign up for the course: https://dbourke.link/udemyTFlaunch
See the questions/answers: https://www.notion.so/mrdbourke/2021-04-30-TensorFlow-for-Deep-Learning-course-Udemy-launch-Q-A-8efe33b92c434ae5bea05fcae8114179
Try out the course on YouTube: https://dbourke.link/tfpart1part2
Course materials on GitHub: github.com/mrdbourke/tensorflow-deep-learning
Timestamps:
0:00 - Intro/hello/dancing
1:30 - Celebratory fireworks
3:23 - Q&A start, can this course help even if I don’t know TensorFlow?
5:14 - How do you start your day?
5:40 - How to get started in machine learning from zero to advanced?
7:45 - Is this course TensorFlow 1.0 or 2.0?
8:58 - Will you teach ML pipelines on AWS?
11:00 - Does this course help you pass the TensorFlow Developer Certification?
13:15 - When are the full contents coming to Udemy?
16:15 - Any recommendations on standing desks?
17:25 - I found the TensorFlow Developer Certification easy, is it worth it?
20:48 - Have you done anything cool with ML recently?
22:13 - Do we need any experience in ML for the course?
25:05 - Does ML require experience in programming to start?
28:00 - Will the course cover using TensorFlow on Google Cloud?
29:57 - Will you ever teach ML with R?
30:51 - Is TensorFlow 2.0 and PyTorch similar?
32:56 - Do you plan to make a TensorFlow deployment course?
34:23 - What can I do after this course?
36:35 - What projects will be on the course?
39:00 - Any tips for becoming a freelancer in AI?
40:09 - Do we need a GPU to learn?
42:12 - Does the TensorFlow Certification have financial aid?
43:42 - How much time to go from beginner to advanced in ML?
46:22 - How to prepare for an internship in ML?
49:32 - Do you have experience with ML streaming data?
52:55 - How would you explain TensorFlow to a beginner?
56:23 - Will AI make web development obsolete?
58:00 - What is the difference between your ML/DS course and the TensorFlow course?
1:00:49 - Does your course cover mathematics?
1:03:00 - Outro/finish
Sign up here: https://dbourke.link/udemyTFlaunch (to celebrate the launch, there's a great deal going for the next 5 days)
Not a fan of Udemy?
You can sign up on the Zero to Mastery Academy:
TensorFlow course - https://dbourke.link/ZTMTFcourse
ML course (beginner-friendly) - https://dbourke.link/ZTMMLcourse
Connect elsewhere:
Web - https://dbourke.link/web
Twitch - twitch.tv/mrdbourke
ArXiv channel (past streams) - youtube.com/channel/UCKt-z-AVy7duq6-_N-michg
Get email updates on my work - https://dbourke.link/newsletter
Machine Learning Monthly March 2021 - zerotomastery.io/blog/machine-learning-monthly-march-2021
EfficientNetV2 - arxiv.org/abs/2104.00298
Learn:
Beginner-friendly Machine Learning - https://dbourke.link/mlcourse
TensorFlow for Deep Learning - https://dbourke.link/ZTMTFcourse
Connect elsewhere:
Web - https://dbourke.link/web
Twitch - twitch.tv/mrdbourke
ArXiv channel (past streams) - youtube.com/channel/UCKt-z-AVy7duq6-_N-michg
Get email updates on my work - https://dbourke.link/newsletter
Timestamps:
0:00 - Intro/hello/dancing
0:54 - My work from the past month
2:21 - Why is machine learning hard? By Zayd Enam
4:13 - Software 2.0 by Andrej Karpathy
4:32 - Start with less fancy networks by Victor Sanh
6:50 - Airbnb’s Multimodal model for images, text and structured data
10:16 - Learning from Videos by Facebook AI
13:10 - Self-supervised Learning: The dark matter of intelligence by Yann LeCun
15:48 - SEER: A new state of the art for self-supervised computer vision
18:39 - Paper of the month: ResNets are back baby!!!
21:55 - ...and they’re gone, welcome EfficientNetV2
24:03 - Super-powered Speech tools: Coqui & SpeechBrain
26:03 - The Deep Bootstrap Framework
30:27 - Summary/outro/more dancing
#machinelearningmonthly #machinelearning
This part continues right where part one left off so get that Google Colab window open and get ready to write plenty more TensorFlow code.
Sign up for the full course - https://dbourke.link/ZTMTFcourse
Get all of the code/materials on GitHub - github.com/mrdbourke/tensorflow-deep-learning
Ask a question - github.com/mrdbourke/tensorflow-deep-learning/discussions
See part 1 - youtu.be/tpCFfeUEGs8
TensorFlow Python documentation - tensorflow.org/api_docs/python/tf
Connect elsewhere:
Web - mrdbourke.com
Livestreams on Twitch - twitch.tv/mrdbourke
Get email updates on my work - mrdbourke.com/newsletter
Timestamps:
0:00 - Intro/hello/have you watched part 1? If not, you should
0:55 - 66. Non-linearity part 1 (straight lines and non-straight lines)
10:33 - 67. Non-linearity part 2 (building our first neural network with a non-linear activation function)
16:21 - 68. Non-linearity part 3 (upgrading our non-linear model with more layers)
26:40 - 69. Non-linearity part 4 (modelling our non-linear data)
35:18 - 70. Non-linearity part 5 (reproducing our non-linear functions from scratch)
49:45 - 71. Getting great results in less time by tweaking the learning rate
1:04:32 - 72. Using the history object to plot a model’s loss curves
1:10:43 - 73. Using callbacks to find a model’s ideal learning rate
1:28:16 - 74. Training and evaluating a model with an ideal learning rate
1:37:37 - [Keynote] 75. Introducing more classification methods
1:43:41 - 76. Finding the accuracy of our model
1:47:59 - 77. Creating our first confusion matrix
1:56:27 - 78. Making our confusion matrix prettier
2:10:28 - 79. Multi-class classification part 1 (preparing data)
2:21:04 - 80. Multi-class classification part 2 (becoming one with the data)
2:28:13 - 81. Multi-class classification part 3 (building a multi-class model)
2:43:52 - 82. Multi-class classification part 4 (improving our multi-class model)
2:56:35 - 83. Multi-class classification part 5 (normalised vs non-normalised)
3:00:48 - 84. Multi-class classification part 6 (finding the ideal learning rate)
3:11:27 - 85. Multi-class classification part 7 (evaluating our model)
3:25:34 - 86. Multi-class classification part 8 (creating a confusion matrix)
3:30:00 - 87. Multi-class classification part 9 (visualising random samples)
3:40:42 - 88. What patterns is our model learning?
#tensorflow #deeplearning #machinelearning
After this two-part code-first introduction, you’ll have written 100s of lines of TensorFlow code and have hands-on experience with two important problems in machine learning: regression (predicting a number) and classification (predicting if something is one thing or another).
Open a Google Colab (if you’re not sure what this is, you’ll find out soon) window and get ready to code along.
Sign up for the full course - https://dbourke.link/ZTMTFcourse
Get all of the code/materials on GitHub - github.com/mrdbourke/tensorflow-deep-learning
Ask a question - github.com/mrdbourke/tensorflow-deep-learning/discussions
See part 2 - youtu.be/ZUKz4125WNI
TensorFlow Python documentation - tensorflow.org/api_docs/python/tf
Connect elsewhere:
Web - mrdbourke.com
Livestreams on Twitch - twitch.tv/mrdbourke
Get email updates on my work - mrdbourke.com/newsletter
Timestamps:
0:00 - Intro/hello/how to approach this video
1:50 - MODULE 0 START (TensorFlow/deep learning fundamentals)
1:53 - [Keynote] 1. What is deep learning?
6:31 - [Keynote] 2. Why use deep learning?
16:10 - [Keynote] 3. What are neural networks?
26:33 - [Keynote] 4. What is deep learning actually used for?
35:10 - [Keynote] 5. What is and why use TensorFlow?
43:05 - [Keynote] 6. What is a tensor?
46:40 - [Keynote] 7. What we're going to cover
51:12 - [Keynote] 8. How to approach this course
56:45 - 9. Creating our first tensors with TensorFlow
1:15:32 - 10. Creating tensors with tf Variable
1:22:40 - 11. Creating random tensors
1:32:20 - 12. Shuffling the order of tensors
1:42:00 - 13. Creating tensors from NumPy arrays
1:53:57 - 14. Getting information from our tensors
2:05:52 - 15. Indexing and expanding tensors
2:18:27 - 16. Manipulating tensors with basic operations
2:24:00 - 17. Matrix multiplication part 1
2:35:55 - 18. Matrix multiplication part 2
2:49:25 - 19. Matrix multiplication part 3
2:59:27 - 20. Changing the datatype of tensors
3:06:24 - 21. Aggregating tensors
3:16:14 - 22. Tensor troubleshooting
3:22:27 - 23. Find the positional min and max of a tensor
3:31:56 - 24. Squeezing a tensor
3:34:57 - 25. One-hot encoding tensors
3:40:44 - 26. Trying out more tensor math operations
3:45:31 - 27. Using TensorFlow with NumPy
3:51:14 - MODULE 1 START (neural network regression)
3:51:25 - [Keynote] 28. Intro to neural network regression with TensorFlow
3:58:57 - [Keynote] 29. Inputs and outputs of a regression model
4:07:55 - [Keynote] 30. Architecture of a neural network regression model
4:15:51 - 31. Creating sample regression data
4:28:39 - 32. Steps in modelling with TensorFlow
4:48:53 - 33. Steps in improving a model part 1
4:54:56 - 34. Steps in improving a model part 2
5:04:22 - 35. Steps in improving a model part 3
5:16:55 - 36. Evaluating a model part 1 ("visualize, visualize, visualize")
5:24:20 - 37. Evaluating a model part 2 (the 3 datasets)
5:35:22 - 38. Evaluating a model part 3 (model summary)
5:52:39 - 39. Evaluating a model part 4 (visualizing layers)
5:59:56 - 40. Evaluating a model part 5 (visualizing predictions)
6:09:11 - 41. Evaluating a model part 6 (regression evaluation metrics)
6:17:19 - 42. Evaluating a regression model part 7 (MAE)
6:23:10 - 43. Evaluating a regression model part 8 (MSE)
6:26:29 - 44. Modelling experiments part 1 (start with a simple model)
6:40:19 - 45. Modelling experiments part 2 (increasing complexity)
6:51:49 - 46. Comparing and tracking experiments
7:02:08 - 47. Saving a model
7:11:32 - 48. Loading a saved model
7:21:49 - 49. Saving and downloading files from Google Colab
7:28:07 - 50. Putting together what we've learned 1 (preparing a dataset)
7:41:38 - 51. Putting together what we've learned 2 (building a regression model)
7:55:01 - 52. Putting together what we've learned 3 (improving our regression model)
8:10:45 - [Code] 53. Preprocessing data 1 (concepts)
8:20:21 - [Code] 54. Preprocessing data 2 (normalizing data)
8:31:17 - [Code] 55. Preprocessing data 3 (fitting a model on normalized data)
8:38:57 - MODULE 2 START (neural network classification)
8:39:07 - [Keynote] 56. Introduction to neural network classification with TensorFlow
8:47:31 - [Keynote] 57. Classification inputs and outputs
8:54:08 - [Keynote] 58. Classification input and output tensor shapes
9:00:31 - [Keynote] 59. Typical architecture of a classification model
9:10:08 - 60. Creating and viewing classification data to model
9:21:39 - 61. Checking the input and output shapes of our classification data
9:26:17 - 62. Building a not very good classification model
9:38:28 - 63. Trying to improve our not very good classification model
9:47:42 - 64. Creating a function to visualize our model's not so good predictions
10:02:50 - 65. Making our poor classification model work for a regression dataset
#tensorflow #deeplearning #machinelearning
Links:
Read the post - zerotomastery.io/blog/machine-learning-monthly-february-2021
My courses:
Learn Machine Learning (beginner) - https://dbourke.link/mlcourse
Learn TensorFlow and Deep Learning - https://dbourke.link/ZTMTFcourse
Connect elsewhere:
Web - mrdbourke.com
Live coding on Twitch - twitch.tv/mrdbourke
Get email updates on my work - mrdbourke.com/newsletter
Timestamps:
0:00 - Intro/dancing/hello
1:01 - Where to sign up for ML Monthly emails
1:30 - My new TensorFlow course
2:45 - See me code live on Twitch (twitch.tv/mrdbourke)
3:00 - My ML deployment tutorial for CS329s
4:11 - Using deep learning to read brainwaves
7:07 - Alvaro’s guide to TensorFlow Serving
9:05 - Chip Huyen’s MLOps Tooling Landscape v2 blog post
11:08 - ML is going real-time by Chip Huyen
14:04 - Using GitHub for MLOps
15:42 - Upgrade your software engineering skills as a machine learning practitioner
17:42 - freeCodeCamp’s upcoming DS + ML curriculum
19:22 - Transformers from scratch by Peter Bloem
21:44 - Estimating training data influence with TracIn
24:40 - Learn fundamental statistics with Python
26:25 - The most important statistical ideas of the past 50 years
28:56 - Outro/submit your work/more dancing
#machinelearning #datascience
Sign up for the TensorFlow Deep Learning course - https://dbourke.link/ZTMTFcourse
Use code "TF20" for 20% off for the next 3 days!
See all the materials on GitHub - github.com/mrdbourke/tensorflow-deep-learning
Ask questions - github.com/mrdbourke/tensorflow-deep-learning/discussions
Timestamps:
0:00 - Intro/hello/dancing 🕺
3:15 - Course materials on GitHub
4:09 - How I got TensorFlow Developer Certified (inspiration for course)
6:50 - Course prerequisites
7:55 - Should you do this course? (2 simple questions)
9:46 - Will the course be available on Udemy?
10:19 - Got a question about the course? Ask it on GitHub Discussions
16:29 - How hard is the TensorFlow Developer Certification Exam?
24:41 - Do you need the TensorFlow Developer Certification or are projects enough?
27:26 - Will the course be relevant in 3 years?
32:50 - Where can I learn the math for machine learning?
59:11 - Answering a GitHub Discussions question live (will you keep the course updated?)
#tensorflow #machinelearning #deeplearning
Get all the code on GitHub - github.com/mrdbourke/cs329s-ml-deployment-tutorial
Slides - github.com/mrdbourke/cs329s-ml-deployment-tutorial/blob/main/CS329s-deploying-ml-models-tutorial.pdf
Full CS329s syllabus - stanford-cs329s.github.io/index.html
Learn ML (my beginner-friendly ML course) - https://dbourke.link/mlcourse
Connect elsewhere:
Web - mrdbourke.com
Get email updates on my work - mrdbourke.com/newsletter
Timestamps:
0:00 - Intro/hello
1:42 - Presentation start (what we’re going to cover)
6:00 - Food Vision 🍔👁 (the app we’re building) recipe
11:16 - The end goal we’re working towards (data flywheel)
13:07 - The data flywheel: the holy grail of ML apps
14:57 - Tesla’s data flywheel
17:02 - Food Vision’s data flywheel
18:24 - Deploying a model on the cloud outline
21:14 - Steps we’re going to go through to deploy our app
27:06 - Question: “How do you identify hard samples in your data?”
37:53 - Creating a bucket on Google Storage
45:51 - Uploading to Google Storage from Google Colab
48:02 - Deploying a model to AI Platform
52:50 - Creating an AI Platform Prediction version
58:10 - Creating a Service Account to access our model on Google Cloud
1:02:32 - Authenticating our app with our private Service Account key
1:09:19 - What happens when we run make gcloud-deploy
1:11:27 - Problems you’ll run into when deploying your models
1:20:12 - Extensions you could perform on this tutorial
1:20:49 - Part 2 start (tutorial overtime)
1:28:43 - Dealing with different data shapes
1:32:35 - An error you might run into when using the example app (3 total models deployed)
1:33:20 - Dealing with data size restrictions
1:38:48 - Stepping through the make gcloud-deploy command
1:51:00 - Summary and wrap up
#machinelearning
Machine Learning Monthly January 2021 - zerotomastery.io/blog/machine-learning-monthly-january-2021
Support freeCodeCamp's Data Science Curriculum - freecodecamp.org/news/building-a-data-science-curriculum-with-advanced-math-and-machine-learning
Connect elsewhere:
Web - https://dbourke.link/web
Get email updates on my work - https://dbourke.link/newsletter
Timestamps:
0:00 - Intro/hello
1:15 - freeCodeCamp's data science fund (donate if you can!)
2:57 - my upcoming TensorFlow course
3:54 - detecting hateful memes by Niklas Muennighoff
7:09 - Aurélien’s deep thoughts blog
9:14 - OpenAI’s massive January
10:12 - DALLE (creating images from text)
14:32 - CLIP (using text to help fix major problems in computer vision)
20:34 - Amit’s Papers with Video Chrome extension
22:30 - Bottleneck Transformers take over vision
25:16 - Bonus #1: Full Stack Deep Learning’s guide to transformers
25:59 - Made with ML’s pivot
29:13 - Awesome production machine learning
30:12 - Josh Tobin’s the missing piece of full-stack ML talk
33:26 - Bonus #2: Full Stack Deep Learning’s 2021 curriculum
35:02 - Apple’s system for delivering ML to 1 billion+ devices
40:05 - Outro/summary
#machinelearning #datascience
Read the article/sign up for more - zerotomastery.io/blog/machine-learning-monthly-december-2020
Timestamps:
0:00 - Intro & hello
1:00 - My work for the past month
3:00 - Johannes' ML code generator app
6:21 - AlphaFold 2
10:43 - MuZero
16:13 - TensorFlow 2.4
17:56 - Trick yourself into understanding backpropagation
19:45 - CS50 + AI
21:49 - Adaptive Risk Minimization (ARM) (models which adapt to test distribution shift)
25:34 - Software Engineering x AI
27:23 - News anchor replicated with AI
29:03 - Who said robots can't dance?
Connect elsewhere:
Web - https://dbourke.link/web
Get email updates on my work - https://dbourke.link/newsletter
#machinelearning
Sign up to Coursera Plus - https://dbourke.link/courseraplus
Coursera Data Science Curriculum Notion Template - https://dbourke.link/coursera-notion-template
Blog post version of this video - mrdbourke.com/how-to-create-your-own-data-science-curriculum-with-coursera-in-2021
There's no speed limit by Derek Sivers - https://sive.rs/kimo
Timestamps:
0:00 - Intro/storytime
1:25 - The line which changed my whole concept of learning
3:55 - What this curriculum is based off
4:25 - Coursera data science curriculum template with Notion exploration
9:00 - Curriculum outline start
14:12 - How to track your progress with Notion
20:45 - What to do after you've built some data science foundations
Note: I am an affiliate partner with Coursera. This means if you click any of the links and pay for something, the price will be as normal but I may receive a portion of the payment, funds I use to create resources like this.
Connect elsewhere:
Web - mrdbourke.com
Newsletter - mrdbourke.com/newsletter
#datascience #machinelearning
Read about the experiments and see the results - mrdbourke.com/m1-macbook-vs-intel-macbook-speed-comparison
Tests run:
1. Final Cut Pro video export
2. CreateML machine learning model training
3. TensorFlow machine learning model training
Links:
Learn ML (beginner-friendly courses I teach) - mrdbourke.com/ml-courses
ML courses/books I recommend - mrdbourke.com/ml-resources
Read my novel Charlie Walks - charliewalks.com
Timestamps:
0:00 - Intro
1:00 - Mac Specifications
1:23 - Tests we’re running
1:46 - Test 1 (video rendering) start
3:39 - Starting battery life(s)
5:15 - 16-inch test 1 results
6:47 - 13-inch Pro test 1 results
8:41 - 13-inch Air test 1 results
9:57 - Test 2 (CreateML) start
13:35 - 13-inch Air test 2 results
14:55 - 13-inch Pro test 2 results
18:38 - 16-inch Pro test 2 results
19:30 - Test 3 (TensorFlow code) start
21:13 - TensorFlow code tests outline
21:50 - Basic CNN test start
23:03 - Transfer learning test start
24:53 - tensorflow_macos benchmark start
28:40 - Ending battery life(s)
29:44 - Test 3 (TensorFlow code) results
#machinelearning #m1 #tensorflow
Bonus points if you get the reference... ;)
Note: the audio drops between 31:54 and 35:20.
Timestamps:
0:00 - Intro/hello/dancing
3:50 - Does data science or ML have promise in the future?
5:30 - Do ML engineers or data scientists work on a permanent or contract basis?
6:30 - The origin of 69,420
7:40 - Why don't you do more RL?
10:13 - How open are you to collaborate on a project with anyone?
12:40 - How to get overseas opportunities in machine learning engineering?
14:27 - Kaggle vs end to end projects?
16:34 - What was the most challenging skill you needed to learn in your career?
19:27 - Will the singularity come?
21:45 - Will AI increase wealth inequality?
24:22 - Which companies are making great progress in terms of machine learning?
26:22 - Will Python or R programming languages be relevant for machine learning in the future?
27:50 - Which IDE is your favourite for machine learning?
28:01 - How do you wind down at the end of the day?
31:53 - AUDIO DROP START
35:21 - AUDIO DROP STOP (shocking audio quality)
36:31 - GOOD AUDIO RETURNS
37:20 - How do you get better at reimplementing papers?
38:37 - How to get Machine Learning Engineer skills
39:00 - What machine learning projects do you recommend for beginners?
40:05 - How's the progress going on the fitness app you wanted to build?
40:57 - Do you plan on making a fitness course?
45:53 - What are your favourite YouTube channels on ML?
47:50 - How to get paid for doing ML work for clients?/How to get clients?
50:12 - Any tips on getting into blogging?
51:22 - What's something you wish you knew when you were 17 years old?
54:20 - How are you doing?
54:42 - The impact of doing a master's degree in data science on job opportunities
57:44 - Daniel Bourke vs @Ken Jee
58:10 - Prerequisites for learning deep learning
58:37 - How to gain muscles fast?
59:00 - Number 1 rule of coding Python
59:45 - How to get freelance clients in data science
1:00:00 - Can I get ❤️?
1:03:40 - Where's the best place to learn machine learning?
Connect elsewhere:
Web - https://dbourke.link/web
Quora - https://dbourke.link/quora
Medium - https://dbourke.link/medium
Twitter - https://dbourke.link/twitter
LinkedIn - https://dbourke.link/linkedin
And hoho... this issue was an absolute banger! What a phenomenal month on tour for the world of machine learning. Be sure to subscribe/submit your work for next month's letter.
ML Monthly November 2020 - zerotomastery.io/blog/machine-learning-monthly-november-2020
Learn ML (my beginner-friendly course) - https://dbourke.link/ZTMMLcourse
Links mentioned:
My upcoming deep learning with TensorFlow course - github.com/mrdbourke/tensorflow-deep-learning
Alvaro's guide to TorchServe - github.com/alvarobartt/serving-pytorch-models
TensorFlow for Mac - blog.tensorflow.org/2020/11/accelerating-tensorflow-performance-on-mac.html
TensorFlow Recommenders (TFRS) - blog.tensorflow.org/2020/09/introducing-tensorflow-recommenders.html
NYU Deep Learning course - https://cds.nyu.edu/deep-learning/
ML created art - mlart.co
Deep Learning's Most Important Ideas blog post - dennybritz.com/blog/deep-learning-most-important-ideas
Continuous delivery for ML - martinfowler.com/articles/cd4ml.html
Why we need DevOps for ML data - tecton.ai/blog/devops-ml-data
Data Valuation using Reinforcement Learning (DVRL) - ai.googleblog.com/2020/10/estimating-impact-of-training-data-with.html
Estimating Example Difficulty Using Variance of Gradients (VOG) - arxiv.org/abs/2008.11600
AI camerman mistakes bald referee's head for ball - iflscience.com/technology/ai-camera-ruins-soccar-game-for-fans-after-mistaking-referees-bald-head-for-ball
Timestamps:
0:00 - Intro/hello
1:40 - My upcoming TensorFlow course
3:53 - Alvaro's guide to TorchServe
7:10 - TensorFlow for Mac
11:25 - TensorFlow Recommenders
13:37 - Yann LeCun's NYU Deep Learning course
16:15 - Machine learning created art
18:05 - Robot draws poetry on the beach
19:00 - Deep learning's most import ideas by Denny Britz
25:55 - Continuous delivery for machine learning
29:40 - Why we need DevOps for ML data
33:51 - Papers: How hard is your data to model?
34:20 - 📄 Data Valuation Using Reinforcement Learning
36:33 - 📄 Estimating Example Difficulty Using Variance of Gradients
40:00 - AI cameraman mistakes bald referee's head for soccer ball
Connect elsewhere:
Web - https://dbourke.link/web
Private newsletter - https://dbourke.link/newsletter
Medium - https://dbourke.link/medium
Twitter - https://dbourke.link/twitter
LinkedIn - https://dbourke.link/linkedin
Read/Sign up:
ML Monthly October 2020 - zerotomastery.io/blog/machine-learning-monthly-october-2020
Machine Learning Engineering Book - amzn.to/3mbelZq
Send your work through to be featured in a feature episode:
daniel at mrdbourke dot com
Learn ML:
My beginner-friendly course - https://dbourke.link/ZTMMLcourse
Connect elsewhere:
Web - https://dbourke.link/web
Private newsletter - https://dbourke.link/newsletter
Medium - https://dbourke.link/medium
Twitter - https://dbourke.link/twitter
LinkedIn - https://dbourke.link/linkedin
Timestamps:
0:00 - Intro/hello
1:29 - The 10 Commandments of Self-Taught Machine Learning Engineers
3:30 - Kevin's ML powered mask detecting Telegram Bot
6:50 - NLP fire sale (plethora of NLP resources)
7:25 - Modern Practical NLP by Johnathan Mugan
9:25 - Getting started with NLP by Elvis Saravia
10:35 - The Super Duper NLP repo (plenty of NLP examples) by Quantum Stat
12:30 - NLP News by Sebastian Ruder
14:00 - Phenomenal NLP repo by Tae-Hwan Jung
15:46 - State of AI Report 2020
16:40 - A 2020 guide to Data & Infrastructure
19:55 - Putting ML into production course by Made with ML
21:25 - My new favourite ML book: Machine Learning Engineering by Andriy Burkov
23:12 - The NumPy manifesto
25:18 - The Incredible PyTorch (bulk PyTorch examples) by Ritchie Ng
26:35 - Transformers for computer vision
30:15 - Training a custom object detection model for mobile guide by Jim Su from Roboflow
32:25 - Gradient Dissent podcast by Weights & Biases
34:00 - Summary/goodbye 👋
#machinelearning
A big shout out to Nathan and Ian for their huuuuuuge efforts putting this together!
See the full State of AI Report 2020 here: stateof.ai
Connect:
Web - mrdbourke.com
Email updates - mrdbourke.com/newsletter
Timestamps:
0:00 - Intro and hello
1:31 - AI report review start
2:12 - AI definitions
3:00 - SECTION 1: Research
3:37 - Transformers taking over NLP
5:50 - Universities starting AI-based degrees
6:35 - Only 15% of papers published share their code/data
8:20 - PyTorch outpacing TensorFlow in research papers
11:12 - Bigger models, datasets and compute budgets drive performance
15:40 - Increased performance costing more for incremental improvement
18:13 - Deep learning is getting more efficient
21:11 - AI for conversations is getting better
23:02 - Machine translation for code (Python to C++)
25:32 - Many algorithms starting to beat human baseline for NLP on GLUE test
27:04 - Using Transformers for computer vision
30:11 - AI performs incredibly well on mammography tasks across two regions (US and UK)
31:30 - Causal inference in ML
34:30 - ML for synthesizing new molecules
36:26 - AI starts to read DNA-encoded molecules
39:39 - AI generates tennis matches between any tennis players you want
40:46 - Transformers being used for object detection
41:46 - AI which learns from its dreams
44:26 - Really efficient on-device computer vision models
45:04 - Evolving machine learning algorithms from scratch (AutoML Zero)
46:20 - Federated learning is now booming
47:16 - Privacy-preserving ML
48:35 - Using Gaussian Processes for estimating model uncertainty
50:11 - SECTION 2: Talent
50:12 - Many top companies stealing AI professors
52:02 - Abu Dhabi opens the world's first AI university
54:03 - Many Chinese AI PhD's depart China for other countries
54:52 - US based companies and institutions dominate NeurIPS and ICML (ML conferences)
56:13 - Three times more AI job postings then views for AI roles
56:58 - TensorFlow and Keras have more job postings on LinkedIn than PyTorch
57:18 - SECTION 3: Industry
59:06 - INTERMISSION
59:44 - AI predicting metabolic response to food
1:00:45 - FDA acknowledge lack of policy for AI-driven systems
1:01:54 - Less than 1% of AI-based medical imaging studies are high-quality
1:02:48 - First reimbursement approval for deep learning based medical imagining
1:05:16 - Self-driving mileage in California still well above autonomous driving mileage
1:10:36 - Supervised ML improvements seem to follow an S-curve
1:12:13 - A new kind of approach to self-driving cars
1:17:17 - New AI-first chips (competition for NVIDIA)
1:19:41 - The rise of MLOps
1:21:52 - Computer vision for auto insurance claims
1:23:45 - Using NLP to detect money laundering and terrorist schemes on the web
1:25:17 - Robots in stock factories are picking millions of items per month
1:26:23 - HuggingFace's open-source NLP work is driving NLP's explosion
1:28:09 - SECTION 4: Politics
1:29:59 - Creating a search engine for faces
1:33:29 - GPT3 outputs bias predictions like GPT2
1:33:49 - US military adopting deep reinforcement learning techniques
1:35:52 - Fighter pilots vs AI pilots
1:38:28 - Google's People and AI guidebook talks about fairness, interpretability, privacy
1:40:46 - China fronts big cash for chip manufacturing
1:45:00 - A call to tackle climate change, food waste, generating new battery technologies and more with ML
1:45:45 - SECTION 5: Predictions
1:49:22 - A special guest appears
#artificialintelligence #ai #machinelearning
The video is split into two parts:
1. Quick answers to questions about the fast.
2. A video-diary/documentary of each of day.
Links mentioned:
5 day fast blog post (article version of this video) - mrdbourke.com/5-day-fast
Zero Fasting App - zerofasting.com
4 day fast video - youtube.com/watch?v=nZxKKCD0O-I
4 day fast article - mrdbourke.com/4-day-fast
Timestamps:
0:00 - Intro
0:42 - Disclaimer
1:00 - Rapid fire questions start
1:20 - Why do a 5 day fast?
2:05 - How did you start the fast?
3:29 - How much weight did you lose?
5:06 - What did you consume during the fast?
5:49 - Did you exercise during the fast?
7:15 - What was the hardest part about the fast?
8:46 - How did you spend time during the fast?
10:06 - How were you concentration levels?
10:59 - What did you break the fast with?
11:37 - What was your sleep like?
12:44 - What were your blood ketone levels?
13:46 - What as going to the toilet like?
13:57 - Did you ever get hungry?
15:04 - What was the best part about the fast?
15:41 - Would you do it again?
16:20 - Fast starts
19:00 - Day 1
22:51 - 25 hours in
26:58 - Day 2
30:15 - 41 hours in: first weights session
36:42 - Day 3
44:39 - 69 hours in: Sam breaks fast
51:41 - Day 4
55:20 - 85 hours in: the fasters breakfast of choice
1:00:37 - Second weights session
1:03:50 - Day 5
1:10:45 - Buying food to break the fast with
1:16:30 - Breaking the fast
1:17:46 - Day 6 (post fast)
1:21:18 - Progress photos
Connect elsewhere:
Get email updates on my work - https://dbourke.link/newsletter
Web - https://dbourke.link/web
Quora - https://dbourke.link/quora
Medium - https://dbourke.link/medium
Twitter - https://dbourke.link/twitter
LinkedIn - https://dbourke.link/linkedin
#fasting
And as usual, it's been a massive month on tour.
Read the blog post - zerotomastery.io/blog/machine-learning-monthly-september-2020
Learn ML (beginner-friendly course) - https://dbourke.link/mlcourse
Updates on my work - https://dbourke.link/newsletter
Timestamps:
0:00 - Intro and hello
0:57 - How I'd start learning ML again video
1:47 - Shivan's project to analyze my YouTube data
4:16 - Free advanced NLP with spaCy course
5:43 - Explosion AI (one of my favourite AI companies)
6:15 - Text classification with TFIDF vs Word2Vec vs BERT
7:16 - TFIDF formula
8:35 - Super efficient on-device NLP
11:10 - Story of working on a NLP ML project
13:07 - Machine Learning from Scratch book by Danny Friedman
15:33 - 42 day project framework
16:05 - Learning Math for Machine Learning
17:35 - One of my favourite quotes on learning
19:06 - Four great questions for any ML project
19:48 - Data scientists should be more end-to-end
22:43 - Story of being held back on a project
25:34 - GitHub Actions for MLOps & Data Science
27:15 - Microsoft DeepSpeed framework for faster and more efficient model training
30:32 - Roboflow's Ultimate Guide to Object Detection in 2020
33:37 - Using AI and computer vision for agriculture
36:25 - My favourite resource for the month
37:00 - Outro
Support on Patreon - bit.ly/mrdbourkepatreon
Connect elsewhere:
Web - https://dbourke.link/web
Quora - https://dbourke.link/quora
Medium - https://dbourke.link/medium
Twitter - https://dbourke.link/twitter
LinkedIn - https://dbourke.link/linkedin
Thank you to everyone who watched live and offered questions.
If you'd like your question answered on a future stream, feel free to reach out.
Timestamps:
0:00 - Hello and dancing
2:49 - Schedule and disclaimers
4:13 - How to study and implement ML papers
7:30 - Is the ability to deal with suffering what separates people?
10:44 - How do you get over addictions?
15:50 - Does machine learning ever get repetitive?
19:15 - Physical and mental changes during a 5 day fast
24:43 - How many pomodoros do you do a day?
26:43 - What investor would you like to have in front of you? What would you get them to invest in?
34:30 - Python or JavaScript?
35:30 - What field outside of machine learning is worth studying?
41:22 - Alchemy by Rory Sutherland book recommendation
44:16 - How can I improve my focus?
45:52 - How to pick a good deep learning project?
50:53 - What should I do after the ZTM machine learning course?
52:31 - What to do when AGI takes over?
51:11 - Veganism vs vegetarianism
58:42 - How to monetize a machine learning tool you've created?
1:04:21 - How did you conquer maths and imposter syndrome?
1:07:08 - How to identify a sub-specialist machine learning role to go into?
1:15:34 - What motivates you to be great at machine learning?
1:15:53 - Outro and goodbye
Get email updates on my work - https://dbourke.link/newsletter
Support on Patreon - bit.ly/mrdbourkepatreon
Connect elsewhere:
Web - https://dbourke.link/web
Quora - https://dbourke.link/quora
Medium - https://dbourke.link/medium
Twitter - https://dbourke.link/twitter
LinkedIn - https://dbourke.link/linkedin
Timestamps:
0:00 - Intro
2:09 - No more mullet
4:40 - QA Start
4:50 - Is AI mostly overhyped?
9:40 - Does the TensorFlow developer certification give you an edge in interviews?
15:05 - How much experience do you have in Jiu Jitsu?
16:34 - What computer should I use for deep learning?
26:48 - How did you start writing?
39:39 - What courses would you recommend for ML engineering?
43:04 - How are ML models connected with websites?
52:02 - How did you meet up with Andrei (my business partner)
55:05 - Best way to get a machine learning job?
58:00 - What's enough to apply for ML engineer roles?
59:02 - How to build a deep learning powered startup using open source tools?
1:02:48 - How to start learning ML today?
1:05:45 - fastai vs TensorFlow?
1:07:10 - What do you think of GPT-3?
1:12:30 - How do you ensure a fast feedback loop for learning machine learning?
1:13:35 - What was your goal at the start of your learning journey?
1:14:30 - Math first vs applications first vs both at the same time?
1:15:10 - How do you wake up at 5am every day?
1:15:50 - How do you deal with the afternoon 'slump'?
1:16:41 - Is it important to work on your own projects?
1:17:30 - How do I get out of my own way and learn data science?
1:18:35 - Do I need math for machine learning deployment?
1:19:40 - Is your machine learning course enough to get a job in machine learning?
1:22:50 - Do you have a Discord server?
1:23:10 - Outro
Connect elsewhere:
Get email updates on my work - https://dbourke.link/newsletter
Support on Patreon - bit.ly/mrdbourkepatreon
Web - https://dbourke.link/web
Quora - https://dbourke.link/quora
Medium - https://dbourke.link/medium
Twitter - https://dbourke.link/twitter
LinkedIn - https://dbourke.link/linkedin
Get the full scoop here: zerotomastery.io/blog/machine-learning-monthly-august-2020
Other links mentioned:
Visual Neural Networks by @vcubingx - youtu.be/UOvPeC8WOt8
Which GPUs for deep learning by Tim Dettmers - timdettmers.com/2020/09/07/which-gpu-for-deep-learning/#The_Most_Important_GPU_Specs_for_Processing_Speed
fastai2 launch - fast.ai/2020/08/21/fastai2-launch
ML for colonoscopy improvement - ai.googleblog.com/2020/08/using-machine-learning-to-detect.html
minGPT by Andrei Karpathy - github.com/karpathy/minGPT
MLOps tutorial series - madewithml.com/projects/1964/mlops-tutorial-series
Deploying a machine learning model using FastAPI - testdriven.io/blog/fastapi-machine-learning
Nvidia's new 30 series graphics cards - nvidia.com/en-us/geforce/graphics-cards/30-series
On-device supermarket product detection - ai.googleblog.com/2020/07/on-device-supermarket-product.html
Timestamps:
0:00 - Intro
1:50 - How I'd start learning machine learning again blog post
3:30 - Visual neural networks by vcubingx
4:50 - Using machine learning to improve colonoscopies
10:30 - New fastaiv2 announces
14:25 - minGPT by Andrei Karpathy
16:25 - Less supervised computer vision
18:50 - MLOps tutorial series
20:37 - How to deploy and host a ML model with FastAPI and Heroku
22:20 - On-device supermarket product detection
25:20 - Faster ML with Nvidia's new 30 series GPUs
26:35 - Which GPUs should you use for deep learning blog post
28:10 - Sign off
Get email updates on my work - https://dbourke.link/newsletter
Support on Patreon - bit.ly/mrdbourkepatreon
Connect elsewhere:
Web - https://dbourke.link/web
Quora - https://dbourke.link/quora
Medium - https://dbourke.link/medium
Twitter - https://dbourke.link/twitter
LinkedIn - https://dbourke.link/linkedin
#machinelearning
Two things are for sure:
1. I know a lot more than when I started.
2. There's still plenty more to learn.
This video shares what I'd do/tell myself if I was starting again.
Links:
How I'd start learning machine learning again (3 years in) blog post - mrdbourke.com/how-id-start-learning-machine-learning-again-3-years-in
2020 Machine Learning Roadmap - mrdbourke.com/2020-machine-learning-roadmap
Effective Python: 90 Specific Ways to Write Better Python Book - amzn.to/2RgnRfW
Mathematics for Machine Learning Book - mml-book.github.io
Hands-On Machine Learning with Scikit-Learn, Keras and TensorFlow (2nd edition) - amzn.to/3aYexF2
Timestamps:
0:00 - Intro
0:58 - How I got started with machine learning
2:07 - Getting a job
2:30 - Leaving a job
3:44 - Blog post to go along with video
4:20 - Point 1: Avoid credential-seeking mode
6:30 - Point 2: Take the leap
10:00 - Point 3: Use less tools
10:50 - Best programming advice I’ve ever received
12:00 - Two of my favourite books
13:00 - Point 4: If you want to learn something, teach it
13:15 - The things you remember
15:50 - Point 5: Learning something new is hard, so have fun with it
17:10 - How I’d start learning again (specifics)
19:00 - Beginner pathway for getting started
20:51 - Advanced pathway (follows on from beginner)
22:30 - Some of my favourite extra learning materials
23:50 - Example curriculums (of people who have studied online)
24:50 - What to learn vs how to learn
25:15 - Outro
Get email updates on my work - https://dbourke.link/newsletter
Support on Patreon - bit.ly/mrdbourkepatreon
Connect elsewhere:
Web - https://dbourke.link/web
Quora - https://dbourke.link/quora
Medium - https://dbourke.link/medium
Twitter - https://dbourke.link/twitter
LinkedIn - https://dbourke.link/linkedin
#machinelearning #datascience #onlinelearning
Turns out, I needed a lot of help. Thank you Michael, Nvidia (for the TITAN RTX) and the many kind people all over the internet who put out such incredible guides.
The case came with dents in it so we called it "Denty".
Links:
Nvidia TITAN RTX GPU (what powers this beast) - nvda.ws/2X6DiuB
My blog post on the build with a bunch of helpful resources - mrdbourke.com/notes-on-building-a-deep-learning-pc
My PCPartPicker list - au.pcpartpicker.com/list/8KXXjp
Timestamps:
0:00 - Intro and preamble
4:30 - Hardware build start
6:08 - Unboxing Nvidia TITAN RTX
8:30 - Motherboard unboxing
11:00 - CPU unboxing & install
13:00 - CPU fan unboxing & install
19:07 - RAM unboxing & install
22:12 - SSD hard drive unboxing & install
29:00 - Case unboxing (how Denty got its name)
35:00 - Power supply unboxing & install
46:00 - First power on
47:20 - Nvidia TITAN RTX install
52:40 - Second power on
53:51 - Software installation begins
54:55 - Installing Ubuntu
56:16 - Installing Miniconda and Nvidia drivers (CUDA & cuDNN)
56:37 - Software installation test
59:26 - Running first deep learning model on Nvidia TITAN RTX
59:55 - How I plan on using the new deep learning PC
1:01:22 - Outro timelapse
Connect elsewhere:
Get email updates on my work - https://dbourke.link/newsletter
Support on Patreon - bit.ly/mrdbourkepatreon
Web - https://dbourke.link/web
Quora - https://dbourke.link/quora
Medium - https://dbourke.link/medium
Twitter - https://dbourke.link/twitter
LinkedIn - https://dbourke.link/linkedin
GPT3 is the latest in language modelling from OpenAI and self-supervised learning seeks to understand the inherent underlying patterns of the data itself which can then be used for more specific tasks later. It can result in up to 1000x fewer labels being required and still achieve the same results as supervised learning.
Links:
ML Monthly July Edition - zerotomastery.io/blog/machine-learning-monthly-july-2020
Learn Machine Learning - https://dbourke.link/mlcourse
Timestamps:
0:00 - Intro
0:29 - ML monthly July article
1:02 - My work during July
2:05 - All about GPT3
4:00 - GPT3 paper discussion
7:10 - What can GPT3 do?
9:39 - GPT3 vs. humans
11:20 - GPT3 learning resources
13:00 - Two trends I'm noticing in machine learning
17:45 - AutoML-Zero
19:30 - Facebook's self-supervised image classification
21:50 - Learning resources
22:00 - Full-stack deep learning
23:10 - DeepMind's deep learning course
24:37 - Self-supervised learning and computer vision
25:30 - Outro
Connect elsewhere:
Get email updates on my work - https://dbourke.link/newsletter
Support on Patreon - bit.ly/mrdbourkepatreon
Web - https://dbourke.link/web
Quora - https://dbourke.link/quora
Medium - https://dbourke.link/medium
Twitter - https://dbourke.link/twitter
LinkedIn - https://dbourke.link/linkedin
Timestamps:
0:00 - Intro
2:09 - No more mullet
4:40 - QA Start
4:50 - Is AI mostly overhyped?
9:40 - Does the TensorFlow developer certification give you an edge in interviews?
15:05 - How much experience do you have in Jiu Jitsu?
16:34 - What computer should I use for deep learning?
26:48 - How did you start writing?
39:39 - What courses would you recommend for ML engineering?
43:04 - How are ML models connected with websites?
52:02 - How did you meet up with Andrei (my business partner)
55:05 - Best way to get a machine learning job?
58:00 - What's enough to apply for ML engineer roles?
59:02 - How to build a deep learning powered startup using open source tools?
1:02:48 - How to start learning ML today?
1:05:45 - fastai vs TensorFlow?
1:07:10 - What do you think of GPT-3?
1:12:30 - How do you ensure a fast feedback loop for learning machine learning?
1:13:35 - What was your goal at the start of your learning journey?
1:14:30 - Math first vs applications first vs both at the same time?
1:15:10 - How do you wake up at 5am every day?
1:15:50 - How do you deal with the afternoon 'slump'?
1:16:41 - Is it important to work on your own projects?
1:17:30 - How do I get out of my own way and learn data science?
1:18:35 - Do I need math for machine learning deployment?
1:19:40 - Is your machine learning course enough to get a job in machine learning?
1:22:50 - Do you have a Discord server?
1:23:10 - Outro
Connect elsewhere:
Get email updates on my work - https://dbourke.link/newsletter
Support on Patreon - bit.ly/mrdbourkepatreon
Web - https://dbourke.link/web
Quora - https://dbourke.link/quora
Medium - https://dbourke.link/medium
Twitter - https://dbourke.link/twitter
LinkedIn - https://dbourke.link/linkedin
Links:
Ken's channel - youtube.com/channel/UCiT9RITQ9PW6BhXK0y2jaeg
Ken interviewing me - youtu.be/hO_YKK_0Qck
Article version of Ken interviewing me - mrdbourke.com/how-did-you-get-started-with-machine-learning-and-data-science
Timestamps:
0:00 - A data scientists most important job
0:20 - Intro (Daniel introducing Ken)
2:40 - Conversation start
3:11 - Ken's life motto
3:52 - How did you get started with data science?
7:33 - Masters degree vs. studying online
14:52 - How did Ken get his first internship?
17:15 - The project Ken remembers the most from
21:54 - What's it like working as the head of data science?
24:42 - Mock interview phone screen (what Ken looks for in a junior data scientist)
33:06 - The 2 things businesses are looking to solve
34:35 - What Ken's learned reviewing the projects of others
41:03 - How Ken got started with YouTube
47:36 - How does making YouTube videos compare to working on your own data science projects?
52:58 - How would Ken start learning data science again today?
59:31 - Outro
Connect elsewhere:
My machine learning course - https://dbourke.link/mlcourse
Get email updates on my work - https://dbourke.link/newsletter
Support on Patreon - bit.ly/mrdbourkepatreon
Web - https://dbourke.link/web
Quora - https://dbourke.link/quora
Medium - https://dbourke.link/medium
Twitter - https://dbourke.link/twitter
LinkedIn - https://dbourke.link/linkedin
Although the title of this video says machine learning roadmap, you should treat it as a compass. Explore it, follow your curiosity, learn something and use what you learn to create your next steps.
Links:
Interactive Machine Learning Roadmap - https://dbourke.link/mlmap
Machine Learning Roadmap Resources - github.com/mrdbourke/machine-learning-roadmap
Learn ML (beginner-friendly courses I teach) - mrdbourke.com/ml-courses
ML courses/books I recommend - mrdbourke.com/ml-resources
Read my novel Charlie Walks - charliewalks.com
Timestamps:
0:00 - Hello & logistics
0:57 - PART 0: INTRO
1:42 - Brief overview of topics
3:05 - What is machine learning?
4:37 - Machine learning vs. traditional programming
7:41 - Why use machine learning?
8:44 - The number 1 rule of machine learning
10:45 - What is machine learning good for?
14:27 - How Tesla uses machine learning
17:57 - What we're going to cover in this video
20:52 - PART 1: Machine Learning Problems
22:27 - Categories of learning
26:17 - Machine learning problem domains
29:04 - Classification
33:57 - Regression
39:35 - PART 2: Machine Learning Process
41:57 - 6 major steps in a machine learning project
43:57 - Data collection
49:15 - Data preparation
1:04:00 - Training a model
1:23:33 - Analysis/evaluation
1:26:40 - Serving a model
1:29:09 - Retraining a model
1:30:07 - An example machine learning project
1:33:15 - PART 3: Machine Learning Tools
1:34:20 - Machine learning tools overview
1:38:36 - Machine learning toolbox (experiment tracking)
1:39:54 - Pretrained models for transfer learning
1:41:49 - Data and model tracking
1:43:35 - Cloud compute services
1:47:07 - Deep learning hardware (build your own deep learning PC)
1:47:53 - AutoML (automatic machine learning)
1:51:47 - Explainability (explaining the outputs of your machine learning model)
1:53:38 - Machine learning lifecycle (tools for end-to-end projects)
1:59:24 - PART 4: Machine Learning Mathematics
1:59:37 - The main branches of mathematics used in machine learning
2:03:16 - How I learn the math for machine learning
2:06:37 - PART 5: Machine Learning Resources
2:07:17 - A warning
2:08:42 - Where to start learning machine learning
2:14:51 - Made with ML (one of my favourite new websites for ML)
2:16:07 - Wokera ai (test your AI skills)
2:17:17 - A beginner-friendly path to start machine learning
2:19:02 - An advanced path for learning machine learning (after the beginner path)
2:21:43 - Where to learn the mathematics for machine learning
2:22:23 - Books for machine learning
2:24:27 - Where to learn cloud services
2:24:47 - Helpful rules and tidbits of machine learning
2:26:05 - How and why you should create your own blog
2:28:29 - Example machine learning curriculums
2:30:19 - Useful machine learning websites to visit
2:30:59 - Open-source datasets
2:31:26 - How to learn how to learn
2:32:57 - PART 6: Summary & Next Steps
Connect elsewhere:
Get email updates on my work - https://dbourke.link/newsletter
Support on Patreon - bit.ly/mrdbourkepatreon
Web - https://dbourke.link/web
Quora - https://dbourke.link/quora
Medium - https://dbourke.link/medium
Twitter - https://dbourke.link/twitter
LinkedIn - https://dbourke.link/linkedin
#machinelearning #datascience
This month I decided to turn it into a video as well. If you liked this format (or think if anything can be improved), I'd love to know.
Links (in order):
ML Monthly June 2020: zerotomastery.io/blog/machine-learning-monthly-june-2020
How can a beginner like me get experience? - https://dbourke.link/getexperience
How I passed the TensorFlow developer certification - mrdbourke.com/how-i-got-tensorflow-developer-certified
1. Machine Learning road map - https://dbourke.link/mlmap
2. aitextgen (generate text with AI) - github.com/minimaxir/aitextgen
3. Using AI to play like Bach - magenta.tensorflow.org/coconet
4. Data science: expectations vs. reality - dfrieds.com/articles/data-science-reality-vs-expectations.html
5. What I learned from looking at 200 ML tools - huyenchip.com/2020/06/22/mlops.html
5.5 The rise of the DevOps Mindset - https://stackoverflow.blog/2020/06/10/the-rise-of-the-devops-mindset/
6. One neural network to rule them all (once for all network) - https://hanlab.mit.edu/projects/ofa/
7. All of the matrix calculus you need for deep learning - explained.ai/matrix-calculus/index.html
8. Can AI play Minecraft? - aicrowd.com/challenges/neurips-2020-minerl-challenge
9. YOLOV4 (state of the art object detection) - medium.com/@alexeyab84/yolov4-the-most-accurate-real-time-neural-network-on-ms-coco-dataset-73adfd3602fe
10. DETR (end-to-end object detection with transformers) - ai.facebook.com/blog/end-to-end-object-detection-with-transformers
10.5 The transformer (type of architecture) explained) - nostalgebraist.tumblr.com/post/185326092369/the-transformer-explained
Timestamps:
0:00 Introduction
1:39 Welcome (written by AI)
3:27 - My posts for the month
4:45 - 1. Machine learning 2020 roadmap
6:47 - 2 aitextgen (write text with AI)
9:37 - 3 Using AI to play like Bach
11:47 - 4 Data science: expectations vs. reality
16:13 - 5 What the hell is MLOps anyway?
19:38 - 6 Once for all (OFA) network
22:44 - 7 All of the matrix calculus you need for deep learning
24:31 - 8 Can AI play Minecraft?
25:51 - 9 YOLOV4 (state of the art object detection)
28:01 - 10 DETR (end-to-end object detection with transformers)
30:18 - 10.5 The transformer explained
Misc:
My Machine Learning Course - https://dbourke.link/mlcourse
Get email updates on my work - https://dbourke.link/newsletter
Support on Patreon - bit.ly/mrdbourkepatreon
Connect elsewhere:
Web - https://dbourke.link/web
Quora - https://dbourke.link/quora
Medium - https://dbourke.link/medium
Twitter - https://dbourke.link/twitter
LinkedIn - https://dbourke.link/linkedin


