The Attention Mechanism in Large Language Models @SerranoAcademy

Serrano.Academy Attention mechanisms are crucial to the huge boom LLMs have recently had.
In this video you'll see a friendly pictorial explanation of how attention mechanisms work in Large Language Models.
This is the first of a series of three videos on Transformer models.

Video 1: The attention mechanism in high level (this one)
Video 2: The attention mechanism with math: youtube.com/watch?v=UPtG_38Oq8o
Video 3: Transformer models youtube.com/watch?v=qaWMOYf4ri8

Learn more in LLM University! https://llm.university

updated 1 year ago

The Attention Mechanism in Large Language Models

Serrano.Academy 2023-07-25 | Attention mechanisms are crucial to the huge boom LLMs have recently had.
In this video you'll see a friendly pictorial explanation of how attention mechanisms work in Large Language Models.
This is the first of a series of three videos on Transformer models.

Video 1: The attention mechanism in high level (this one)
Video 2: The attention mechanism with math: youtube.com/watch?v=UPtG_38Oq8o
Video 3: Transformer models youtube.com/watch?v=qaWMOYf4ri8

Learn more in LLM University! https://llm.university

Reinforcement Learning with Human Feedback - How to train and fine-tune Transformer Models

Serrano.Academy 2024-02-12 | Reinforcement Learning with Human Feedback (RLHF) is a method used for training Large Language Models (LLMs). In the heart of RLHF lies a very powerful reinforcement learning method called Proximal Policy Optimization. Learn about it in this simple video!

This is the first one in a series of 3 videos dedicated to the reinforcement learning methods used for training LLMs.

Full Playlist: youtube.com/playlist?list=PLs8w1Cdi-zvYviYYw_V3qe6SINReGF5M-

Video 0 (Optional): Introduction to deep reinforcement learning youtube.com/watch?v=SgC6AZss478
Video 1: Proximal Policy Optimization youtube.com/watch?v=TjHH_--7l8g
Video 2 (This one): Reinforcement Learning with Human Feedback
Video 3 (Coming soon!): Deterministic Policy Optimization

00:00 Introduction
00:48 Intro to Reinforcement Learning (RL)
02:47 Intro to Proximal Policy Optimization (PPO)
4:17 Intro to Large Language Models (LLMs)
6:50 Reinforcement Learning with Human Feedback (RLHF)
13:08 Interpretation of the Neural Networks
14:36 Conclusion

Get the Grokking Machine Learning book!
manning.com/books/grokking-machine-learning
Discount code (40%): serranoyt
(Use the discount code on checkout)

Proximal Policy Optimization (PPO) - How to train Large Language Models

Serrano.Academy 2024-01-24 | Reinforcement Learning with Human Feedback (RLHF) is a method used for training Large Language Models (LLMs). In the heart of RLHF lies a very powerful reinforcement learning method called Proximal Policy Optimization. Learn about it in this simple video!

This is the first one in a series of 3 videos dedicated to the reinforcement learning methods used for training LLMs.

Full Playlist: youtube.com/playlist?list=PLs8w1Cdi-zvYviYYw_V3qe6SINReGF5M-

Video 0 (Optional): Introduction to deep reinforcement learning youtube.com/watch?v=SgC6AZss478
Video 1 (This one): Proximal Policy Optimization
Video 2: Reinforcement Learning with Human Feedback youtube.com/watch?v=Z_JUqJBpVOk
Video 3 (Coming soon!): Deterministic Policy Optimization

00:00 Introduction
01:25 Gridworld
03:10 States and Action
04:01 Values
07:30 Policy
09:39 Neural Networks
16:14 Training the value neural network (Gain)
22:50 Training the policy neural network (Surrogate Objective Function)
33:38 Clipping the surrogate objective function
36:49 Summary

Get the Grokking Machine Learning book!
manning.com/books/grokking-machine-learning
Discount code (40%): serranoyt
(Use the discount code on checkout)

The Attention Mechanism for Large Language Models #AI #llm #attention

Serrano.Academy 2023-12-19 | This is how the attention mechanism works for large language models.
For more information, follow me, and check out https://llm.university

Stable Diffusion - How to build amazing images with AI

Serrano.Academy 2023-12-12 | This video is about Stable Diffusion, the AI method to build amazing images from a prompt.

If you like this material, check out LLM University from Cohere!
https://llm.university

Get the Grokking Machine Learning book!
https://manning.com/books/grokking-ma...
Discount code (40%): serranoyt
(Use the discount code on checkout)

0:00 Introduction
1:27 How does Stable Diffusion work?
2:55 Embeddings
12:55 Diffusion Model
15:00 Numerical Example
17:39 Embedding Example
19:37 Image Generator Example
28:37 The Sigmoid Function
34:39 Diffusion Model Example
41:03 Summary

How Large Language Models are Shaping the Future

Serrano.Academy 2023-11-13 | Livestream with FourthBrain and Cohere
fourthbrain.ai

What are Transformer Models and how do they work?

Serrano.Academy 2023-11-02 | This is the last of a series of 3 videos where we demystify Transformer models and explain them with visuals and friendly examples.

Video 1: The attention mechanism in high level youtube.com/watch?v=OxCpWwDCDFQ

Video 2: The attention mechanism with math youtube.com/watch?v=UPtG_38Oq8o

Video 3 (This one): Transformer models

If you like this material, check out LLM University from Cohere!
https://llm.university

Get the Grokking Machine Learning book!
manning.com/books/grokking-machine-learning
Discount code (40%): serranoyt
(Use the discount code on checkout)

00:00 Introduction
01:50 What is a transformer?
04:35 Generating one word at a time
08:59 Sentiment Analysis
13:05 Neural Networks
18:18 Tokenization
19:12 Embeddings
25:06 Positional encoding
27:54 Attention
32:29 Softmax
35:48 Architecture of a Transformer
39:00 Fine-tuning
42:20 Conclusion

The math behind Attention: Keys, Queries, and Values matrices

Serrano.Academy 2023-08-31 | This is the second of a series of 3 videos where we demystify Transformer models and explain them with visuals and friendly examples.

Video 1: The attention mechanism in high level youtu.be/OxCpWwDCDFQ
Video 2: The attention mechanism with math (this one)
Video 3: Transformer models youtube.com/watch?v=qaWMOYf4ri8

If you like this material, check out LLM University from Cohere!
https://llm.university

00:00 Introduction
01:18 Recap: Embeddings and Context
04:46 Similarity
11:09 Attention
20:46 The Keys and Queries Matrices
25:02 The Values Matrix
28:41 Self and Multi-head attention
33:54: Conclusion

The Binomial and Poisson Distributions

Serrano.Academy 2022-11-08 | If on average, 3 people enter a store every hour, what is the probability that over the next hour, 5 people will enter the store? The answer lies in the Poisson distribution. In this video you'll learn this distribution, starting from a much simpler one, the Binomial distribution.

Euler number video: youtube.com/watch?v=oikl9FCISqU

Grokking Machine Learning book:
bit.ly/grokkingML
40% discount code: serranoyt

Eulers number, derivatives, and the bank at the end of the universe

Serrano.Academy 2022-10-14 | Euler's number, e, is defined as a limit. The function e to the x is (up to multiplying by a constant) the only function that is its own derivative. How are these two related? In this video you'll find an explanation for this phenomenon using banking interest rates, and a very particular bank, located at the end of the universe.

Decision trees - A friendly introduction

Serrano.Academy 2022-09-30 | A video about decision trees, and how to train them on a simple example.

Accompanying blog post: medium.com/@luis.serrano/splitting-data-by-asking-questions-decision-trees-74afed9cd849

For a code implementation, check out this repo:
github.com/luisguiserrano/manning/tree/master/Chapter_9_Decision_Trees

Helper videos:
- Gini index: youtube.com/watch?v=u4IxOk2ijSs
- Entropy and information gain: youtube.com/watch?v=9r7FIXEAGvs
- Machine learning error and metrics: youtube.com/watch?v=aDW44NPhNw0

Grokking Machine Learning book:
www.manning.com/books/grokking-machine-learning
40% discount code: serranoyt

Thank you for 100K subscribers! I’m planning tons of new content coming soon, so excited!

Serrano.Academy 2022-09-20 | ...

How do you minimize a function when you cant take derivatives? CMA-ES and PSO

Serrano.Academy 2022-09-18 | What happens when you want to minimize a function, say, the error function in order to train a machine learning model, but the function has no derivatives, or they are very hard to calculate? You can use Gradient-Free optimizers. In this video, I show you two of them:
- CMA-ES (Covariance matrix adaptation strategy)
- PSO (Particle swarm optimization)

This video is a sequel to "What is Quantum Machine Learning"
youtube.com/watch?v=j0DV_75LkFo
and also part of the blog post:
zapatacomputing.com/why-generative-modeling-is-leading-the-race-to-practical-quantum-advantage

Introduction: (0:00)
CMA-ES: (1:23)
PSO (9:17)
Conclusion: (14:00)

What is Quantum Machine Learning?

Serrano.Academy 2022-09-07 | This video is a friendly introduction to quantum computing and machine learning. No knowledge required.

This video is part of a blog post with Zapata computing:
zapatacomputing.com/why-generative-modeling-is-leading-the-race-to-practical-quantum-advantage

QCBM Paper: nature.com/articles/s41534-019-0157-8

Video 2: Non-gradient optimizers, CMA-ES and PSO youtube.com/watch?v=oi5GQvJzy5I
Video 3: The mathematics behind qubits (coming soon!)

Introduction: (0:00)
Quantum and classical machine learning: (1.46)
Probability: (5:12)
The qubit: (8:23)
Quantum measurement: (12:08)
Qubits as generative models: (13:42)
Measuring with different bases: (14:15)
Quantum gates: (22:27)
Quantum entanglement: (25:23)
Entanglement gates: (35:31)
Quantum machine learning (36:04)
Training models: (39:50)
Loss functions and KL divergence: (47:55)
Labs, code, etc: (49:59)

Denoising and Variational Autoencoders

Serrano.Academy 2022-01-15 | A video about autoencoders, a very powerful generative model. The video includes:
Intro: (0:25)
Dimensionality reduction (3:35)
Denoising autoencoders (10:50)
Variational autoencoders (18:15)
Training autoencoders (23:36)

Github repo: www.github.com/luisguiserrano/autoencoders

Recommended videos:
Generative adversarial networks: youtube.com/watch?v=8L11aMN5KY8
Restricted Boltzmann machines: youtube.com/watch?v=Fkw0_aAtwIw
Matrix factorization: youtube.com/watch?v=ZspR5PZemcs
Singular value decomposition: youtube.com/watch?v=DG7YTlGnCEo
Neural networks: youtube.com/watch?v=BR9h47Jtqyw
Convolutional neural networks: youtube.com/watch?v=2-Ol7ZB0MmU
Recurrent neural networks: youtube.com/watch?v=2-Ol7ZB0MmU
Logistic regression: youtube.com/watch?v=jbluHIgBmBo
Shannon entropy: youtube.com/watch?v=9r7FIXEAGvs

Book by Luis Serrano! Grokking Machine Learning. bit.ly/grokkingML
40% discount code: serranoyt

0:00 Introduction
0:13 Generative models
3:03 Variational autoencoders
3:45 Dataset of images
10:16 Denoising autoencoders
10:27 Linear methods
10:53 A friendly introduction to deep learning and neural networks
11:58 Mapping the real numbers to the interval (0,1)
12:23 Sigmoid function
12:41 Perceptron
15:02 Correct noise
18:20 Autoencoders as generators
20:16 Latent space
23:41 Training a neural network - loss function
25:18 Training an autoencoder
25:32 Training autoencoders
25:46 Reconstruction loss (Mean squared error)
26:31 Reconstruction loss (log-loss)
27:11 Training a variational auto encoder

Correction: At 30:05, the number in the middle of the red graph should be 0.4, not 0.3.

Eigenvectors and Generalized Eigenspaces

Serrano.Academy 2021-10-17 | A video about the nice geometric intuitions behind eigenvectors and eigenvalues, and their generalized counterparts, generalized eigenvectors and generalized eigenvalues.

Announcement: Book by Luis Serrano! Grokking Machine Learning. bit.ly/grokkingML
40% discount code: serranoyt

Thompson sampling, one armed bandits, and the Beta distribution

Serrano.Academy 2021-07-06 | Thompson sampling is a strategy to explore a space while exploiting the wins. In this video we see an application to winning at a game of one-armed bandits.

Beta distributions video: youtube.com/watch?v=juF3r12nM5A

Tom Denton blog: inventingsituations.net

Icons made by Freepik from flaticon.com

Announcement: Book by Luis Serrano! Grokking Machine Learning. bit.ly/grokkingML
40% discount code: serranoyt

The Beta distribution in 12 minutes!

Serrano.Academy 2021-06-13 | This video is about the Beta distribution, a very important distribution in probability, statistics, and machine learning. It is explained using a simple example involving flipping coins.

One armed bandits video: youtube.com/watch?v=nkyDGGQ5h60

Useful links:
Bayes theorem video: youtube.com/watch?v=Q8l0Vip5YUw

Beta distribution (3blue1brown)
youtube.com/watch?v=ZA4JkHKZM50
http://youtube.com/watch?v=8idr1WZ1A7Q

Grokking Machine Learning Book: manning.com/books/grokking-machine-learning
40% discount promo code: serranoyt

Machine Learning Testing and Error Metrics
https://www.youtube.com/watch?v=aDW44...

Announcement: Book by Luis Serrano! Grokking Machine Learning. bit.ly/grokkingML
40% discount code: serranoyt

A friendly introduction to deep reinforcement learning, Q-networks and policy gradients

Serrano.Academy 2021-05-24 | A video about reinforcement learning, Q-networks, and policy gradients, explained in a friendly tone with examples and figures.

Introduction to neural networks: youtube.com/watch?v=BR9h47Jtqyw

Introduction: (0:00)
Markov decision processes (MDP): (1:09)
Rewards: (5:39)
Discount factor: (8:51)
Bellman equation: (10:48)
Solving the Bellman equation: (12:43)
Deterministic vs stochastic processes: (16:29)
Neural networks: (19:15)
Value neural networks: (21:44)
Policy neural networks: (25:44)
Training the policy neural network: (30:46)
Conclusion: (34:53)

Announcement: Book by Luis Serrano! Grokking Machine Learning. bit.ly/grokkingML
40% discount code: serranoyt

The Gini Impurity Index explained in 8 minutes!

Serrano.Academy 2021-02-28 | The Gini Impurity Index is a measure of the diversity in a dataset. In this short video you'll learn a very simple way to calculate it using probabilities.

Announcement: Book by Luis Serrano! Grokking Machine Learning. bit.ly/grokkingML
40% discount code: serranoyt

The covariance matrix

Serrano.Academy 2020-12-29 | CORRECTION: At 10:56 we shouldn't divide by 4 to get the covariance, we should divide by 1+1+1+1/3, which is 10/3. That means the covariances are the following:
Var(x) = 1.056
Var(y) = 0.864
Cov(x,y) = 0.768
(Thank you Shivkumar Pippal!)

Mean, variance, covariance, and the covariance matrix for a dataset and a weighted dataset.

Announcement: Book by Luis Serrano! Grokking Machine Learning. bit.ly/grokkingML
40% discount code: serranoyt

0:00 Introduction
0:09 The covariance matrix
2:22 Average
3:23 X-variance
5:06 Problem: Same variances
7:59 Formulas
10:30 Center points

Gaussian Mixture Models

Serrano.Academy 2020-12-28 | Covariance matrix video: youtu.be/WBlnwvjfMtQ
Clustering video: youtu.be/QXOkPvFM6NU

A friendly description of Gaussian mixture models, a very useful soft clustering method.

Announcement: New Book by Luis Serrano! Grokking Machine Learning. bit.ly/grokkingML
40% discount code: serranoyt

0:00 Introduction
0:13 Clustering applications
1:56 Hard clustering - soft clustering
3:36 Step 1: Colouring points
6:10 Step 2: Fitting a Gaussian
10:33 Gaussian Mixture Models (GMM)

Singular Value Decomposition (SVD) and Image Compression

Serrano.Academy 2020-09-08 | Github repo: http://www.github.com/luisguiserrano/singular_value_decomposition

Grokking Machine Learning Book:
manning.com/books/grokking-machine-learning
40% discount promo code: serranoyt

In this video, we learn a very useful matrix trick called singular value decomposition (SVD), in which we express a matrix as a product of two rotation matrices and one scaling matrix.
We also show a very interesting application to image compression.

Similar videos:
Principal component analysis (PCA): youtube.com/watch?v=g-Hb26agBFg
Matrix factorization and Netflix recommendations: youtube.com/watch?v=ZspR5PZemcs

Introduction: (0:00)
Transformations: (0:50)
A puzzle: (1:27)
A harder puzzle: (2:21)
Linear transformations: (3:50)
Dimensionality reduction: (10:50)
Image compression: (23:57)

ROC (Receiver Operating Characteristic) Curve in 10 minutes!

Serrano.Academy 2020-07-15 | The ROC curve is a very effective way to make decisions on your machine learning model based on how important is it to not allow false positives or false negatives. In this video we introduce the ROC curve with a simple example.

Grokking Machine Learning Book: manning.com/books/grokking-machine-learning
40% discount promo code: serranoyt

Machine Learning Testing and Error Metrics
youtube.com/watch?v=aDW44NPhNw0

Restricted Boltzmann Machines (RBM) - A friendly introduction

Serrano.Academy 2020-07-07 | CORRECTION: The score for BE is 6 and for BD is -1.

A simple introduction to Restricted Boltzmann Machines (RBM) and their training process, using a real-life example with people and pets.

Grokking Machine Learning Book: manning.com/books/grokking-machine-learning
40% discount promo code: serranoyt

Images downloaded from www.freepik.com
freepik.com/free-photos-vectors/banner
freepik.com/free-photos-vectors/dog
freepik.com/free-photos-vectors/people
freepik.com/free-photos-vectors/background

Introduction: (0:00)
Mystery: (0:17)
Scores: (4:39)
Probabilities: (7:30)
Training (11:09)
Contrastive Divergence: (13:37)
Small Problem: (15:33)
Gibbs Sampling: (16:33)
Updating Weights: (20:56)
Sampling Problems: (22:58)
Independent Sampling: (24:27)
Picking Random Samples with Conditions: (28:30)
Picking Completely Random Samples: (31:05)
Summary: (35:03)
Conclusion: (35:57)

A Friendly Introduction to Generative Adversarial Networks (GANs)

Serrano.Academy 2020-05-05 | Code: http://www.github.com/luisguiserrano/gans
What is the simplest pair of GANs one can build? In this video (with code included) we build a pair of ONE-layer GANs which will generate some simple 2x2 images (faces).

Grokking Machine Learning Book: manning.com/books/grokking-machine-learning
40% discount promo code: serranoyt

GANs from Scratch 1: A deep introduction. With code in PyTorch and TensorFlow: medium.com/ai-society/gans-from-scratch-1-a-deep-introduction-with-code-in-pytorch-and-tensorflow-cb03cdcdba0f

You are much better at math than you think

Serrano.Academy 2020-04-20 | In this video, we see two math problems that require the exact same logic to solve. However, one is very easy and one is very hard. Why?

For information on my book "Grokking Machine Learning":
manning.com/books/grokking-machine-learning
Discount code (40%): serranoyt

Live chat with Luis Serrano!

Serrano.Academy 2020-03-27 | For more info: http://serrano.academy

Live stream celebrating 50K subscribers and 3M views.
Friday, March 27, 11am EST

Training Latent Dirichlet Allocation: Gibbs Sampling (Part 2 of 2)

Serrano.Academy 2020-03-22 | This is the second of a series of two videos on Latent Dirichlet Allocation (LDA), a powerful technique to sort documents into topics. In this video, we learn to train an LDA model using Gibbs sampling.
The first video is here: youtube.com/watch?v=T05t-SqKArY

Latent Dirichlet Allocation (Part 1 of 2)

Serrano.Academy 2020-03-19 | Latent Dirichlet Allocation is a powerful machine learning technique used to sort documents by topic. Learn all about it in this video!

This is part 1 of a 2 video series.
Video 2: youtube.com/watch?v=BaM1uiCpj_E

For information on my book "Grokking Machine Learning": manning.com/books/grokking-machine-learning
Discount code (40%): serranoyt

0:00 Introduction
0:11 The problem
3:47 Machine that generates documents
5:13 Blueprint for the LDA machine
5:49 Probability of a document
9:22 Quiz: Which one for topics?
11:06 A distribution of distributions
11:30 More topics? More dimensions
12:20 In More dimensions
12:55 Quiz: Where to put the topics?
14:05 Two Dirichlet distributions
14:22 Latent Dirichlet Allocation
22:05 Best settings on the machine
22:37 The winning arrangements
25:28 Series of two videos
25:48 Acknowledgements
26:30 Thank you!

Book by Luis Serrano - Grokking Machine Learning (40% off promo code)

Serrano.Academy 2019-07-31 | You can find the book here: manning.com/books/grokking-machine-learning
40% discount promo code: serranoyt
Grokking Machine Learning will give you the tools to learn and apply machine learning, with easy to follow examples and exercises. Check it out!

Serrano.Academy - The art of understanding

Serrano.Academy 2019-02-24 | Announcement: New Book by Luis Serrano! Grokking Machine Learning. bit.ly/grokkingML
40% Discount code: serranoyt

Welcome! I believe that math concepts can be learned through simple explanations, analogies and easy-to-understand visualizations. I am passionate about teaching math concepts in relatable, friendly and simple ways. My videos are designed so that beginners can clearly learn new concepts while experts can see them under a new light. I hope you enjoy the channel and please drop me a line if you have any comments or suggestions. Twitter: @luis_likes_math.

Naive Bayes classifier: A friendly approach

Serrano.Academy 2019-02-11 | Announcement: New Book by Luis Serrano! Grokking Machine Learning. bit.ly/grokkingML
40% discount code: serranoyt

A visual description of Bayes' Theorem and the Naive Bayes algorithm, and an application to spam detection.
No previous knowledge is needed, aside from knowing how to multiply and divide, a visual mind and a desire to learn.

For a code implementation, check out this repo:
github.com/luisguiserrano/manning/tree/master/Chapter_8_Naive_Bayes

0:00 Introduction
0:39 Spam Detector
4:59 Problem
10:34 Naive Bayes Classifier
17:00 Bayes Theorem

Math and OCD - My story with the Thue-Morse sequence

Serrano.Academy 2019-02-10 | Announcement: New Book by Luis Serrano! Grokking Machine Learning. bit.ly/grokkingML
40% discount code: serranoyt

The story of how I once stumbled upon a famous sequence, the Thue-Morse sequence, while walking on the sidewalks as a child,, and the subsequent tale of how this sequence satisfies amazing properties regarding sums of powers of integers.

Principal Component Analysis (PCA)

Serrano.Academy 2019-02-10 | Announcement: New Book by Luis Serrano! Grokking Machine Learning. bit.ly/grokkingML
40% discount code: serranoyt

A conceptual description of principal component analysis, including:
- variance and covariance
- eigenvectors and eigenvalues
- applications
As usual, very little formulas, lots and lots of pictures!

0:00 Introduction
0:46 Taking a picture
1:13 Dimensionality Reduction
2:02 Housing Data
5:09 Mean
7:46 Variance?
12:47 Covariance matrix
13:58 Linear Transformations
18:12 Eigenstuff
19:16 Eigenvalues
19:53 Eigenvectors
20:51 Principal Component Analysis (PCA)
26:05 Thank you!

Clustering: K-means and Hierarchical

Serrano.Academy 2019-01-28 | Announcement: New Book by Luis Serrano! Grokking Machine Learning. bit.ly/grokkingML
40% discount code: serranoyt

A friendly description of K-means clustering and hierarchical clustering with simple examples. No math is needed, only a visual mind and a will to learn.

0:00 Introduction
0:24 Customer Segmentation
2:43 Clustering goal: group data
7:22 K-Means Clustering
7:47 Elbow method
13:17 Dendrogram
15:58 Applications

Support Vector Machines (SVMs): A friendly introduction

Serrano.Academy 2019-01-27 | For a code implementation, check out this repo:
github.com/luisguiserrano/manning/tree/master/Chapter_11_Support_Vector_Machines

Announcement: New Book by Luis Serrano! Grokking Machine Learning. bit.ly/grokkingML
40% discount code: serranoyt

An introduction to support vector machines (SVMs) that requires very little math (no calculus or linear algebra), only a visual mind.
This is the third of a series of three videos.
- Linear Regression: youtube.com/watch?v=wYPUhge9w5c
- Logistic Regression: youtube.com/watch?v=jbluHIgBmBo

0:00 Introduction
1:42 Classification goal: split data
3:14 Perceptron algorithm
6:00 Split data - separate lines
7:05 How to separate lines?
12:01 Expanding rate
18:19 Perceptron Error
19:26 SVM Classification Error
20:34 Margin Error
25:13 Challenge - Gradient Descent
27:25 Which line is better?
28:24 The C parameter
30:16 Series of 3 videos
30:30 Thank you!

Logistic Regression and the Perceptron Algorithm: A friendly introduction

Serrano.Academy 2019-01-01 | For a code implementation, check out these repos:
github.com/luisguiserrano/manning/tree/master/Chapter_5_Perceptron_Algorithm
github.com/luisguiserrano/manning/tree/master/Chapter_6_Logistic_Regression

Announcement: New Book by Luis Serrano! Grokking Machine Learning. bit.ly/grokkingML
40% discount code: serranoyt

An introduction to logistic regression and the perceptron algorithm that requires very little math (no calculus or linear algebra), only a visual mind.

0:00 Introduction
0:08 Series of 3 videos
0:41 E-mail spam classifier
7:19 Classification goal: split data
11:36 How to move a line
12:21 Rotating and translating
18:47 Perceptron Trick
23:20 Correctly and incorrectly classified points
24:20 Positive and negative regions
27:18 Perceptron Error
29:40 Gradient Descent
34:36 A friendly introduction to deep learning and neural networks
37:48 Activation function (sigmoid)
38:31 Log-Loss Error
41:37 Perceptron Algorithm
42:45 Logistic regression algorithm
44:48 Thank you!

Linear Regression: A friendly introduction

Serrano.Academy 2018-12-23 | For a code implementation, check out this repo:
github.com/luisguiserrano/manning/tree/master/Chapter_3_Linear_Regression

Announcement: New Book by Luis Serrano! Grokking Machine Learning. bit.ly/grokkingML
40% discount code: serranoyt

An introduction to linear regression that requires very little math (no calculus or linear algebra), only a visual mind.

0:00 Introduction
0:44 Housing Prices
6:08 Changing the slope - Rotation
6:34 Changing the y-intercept - Translation
7:01 How to move a line
9:16 Moving a line
11:18 Linear regression algorithm
14:27 Positive and negative distance
19:34 One rule to rule them all
26:35 Square error
29:02 Absolute error
29:52 Absolute trick
30:26 Series of 3 videos

How does Netflix recommend movies? Matrix Factorization

Serrano.Academy 2018-09-08 | Announcement: New Book by Luis Serrano! Grokking Machine Learning. bit.ly/grokkingML
40% discount code: serranoyt

A friendly introduction to recommender systems with matrix factorization and how it's used to recommend movies in Netflix.
Accompanying Notebook by Yannet Interian: github.com/yanneta/pytorch-tutorials/blob/master/collaborative-filtering-nn.ipynb

Gradient descent video mentioned at the end: youtube.com/watch?v=BR9h47Jtqyw

What is Machine Learning: (0:05)
How do recommendations work - Netflix example (0:40)
How to figure out dependencies - Matrix Factorization (7:35)
Matrix Factorization Benefits 20:38 How to find the right factorization (16:03)
Error Function for factorization (26:35)
How to use the factors to predict ratings - Inference (30:14)

(Thanks for the timings, Samarth Piano Posts!)

Deep Neural Networks - USF Data Science Seminar by Luis Serrano

Serrano.Academy 2018-04-17 | Announcement: New Book by Luis Serrano! Grokking Machine Learning. bit.ly/grokkingML
40% discount code: serranoyt

A Friendly Introduction to Neural Networks
Thanks to the University of San Francisco Data Science Seminar Series for the video, and to Professor Yannet Interian for the invitation.

⭐ Kite is a free AI-powered coding assistant that will help you code faster and smarter. The Kite plugin integrates with all the top editors and IDEs to give you smart completions and documentation while you’re typing. I've been using Kite for 6 months and I love it! kite.com/get-kite/?utm_medium=referral&utm_source=youtube&utm_campaign=luisserrano&utm_content=description-only

A friendly introduction to Bayes Theorem and Hidden Markov Models

Serrano.Academy 2018-03-27 | Announcement: New Book by Luis Serrano! Grokking Machine Learning. bit.ly/grokkingML
40% discount code: serranoyt

A friendly introduction to Bayes Theorem and Hidden Markov Models, with simple examples. No background knowledge needed, except basic probability.
Accompanying notebook:
github.com/luisguiserrano/hmm

Shannon Entropy and Information Gain

Serrano.Academy 2017-11-04 | Announcement: New Book by Luis Serrano! Grokking Machine Learning. bit.ly/grokkingML
40% discount code: serranoyt

Accompanying blog post: medium.com/p/5810d35d54b4

0:00 Shannon Entropy and Information Gain
2:22 What ball will we pick?
4:33 Quiz
5:06 Question
5:14 Game
7:17 Probability of Winning
7:45 Products
11:00 What if there are more classes?
12:34 Sequence 2
13:44 Sequence 3
14:57 Naive Approach
15:34 Sequence 1
19:44 General Formula

A friendly introduction to Recurrent Neural Networks

Serrano.Academy 2017-08-18 | Announcement: New Book by Luis Serrano! Grokking Machine Learning. bit.ly/grokkingML
40% discount code: serranoyt

A friendly explanation of how computers predict and generate sequences, based on Recurrent Neural Networks.
For a brush up on Neural Networks, check out this video: youtube.com/watch?v=BR9h47Jtqyw

0:00 A friendly introduction to Recurrent Neural Networks
1:38 A friendly introduction to Deep Learning and Neural Networks
2:11 Vectors
5:22 Perfect Roommate
7:13 Simple Neural Network
7:54 Simple (Recurrent) Neural Network
10:03 Cooking Schedule
11:47 More Complicated RNN
12:06 Food
13:31 Weather
14:38 Add
16:02 Merge
20:53 Start with random weights
21:05 Use Gradient Descent
21:41 New Error Function

A friendly introduction to Convolutional Neural Networks and Image Recognition

Serrano.Academy 2017-03-21 | Announcement: New Book by Luis Serrano! Grokking Machine Learning. bit.ly/grokkingML
40% discount code: serranoyt

A friendly explanation of how computer recognize images, based on Convolutional Neural Networks.
All the math required is knowing how to add and subtract 1's. (Bonus if you know calculus, but not needed.)
For a brush up on Neural Networks, check out this video: youtube.com/watch?v=BR9h47Jtqyw

For a code implementation, check out this repo:
github.com/luisguiserrano/manning/tree/master/Chapter_10_Neural_Networks

0:00 Introduction
0:22 Simple World
1:05 Keyboard
1:33 Image recognition software
4:39 Image Recognition Classifier
6:12 Artificial Intelligence
8:47 Gradient Descent
10:26 Slightly More Complex World
11:47 Previous Knowledge
24:27 Convolutional Neural Network
28:27 Advanced World

Machine Learning: Testing and Error Metrics

Serrano.Academy 2017-03-16 | Announcement: New Book by Luis Serrano! Grokking Machine Learning. bit.ly/grokkingML
40% discount code: serranoyt

A friendly journey into the process of evaluating and improving machine learning models.
- Training, Testing
- Evaluation Metrics: Accuracy, Precision, Recall, F1 Score
- Types of Errors: Overfitting and Underfitting
- Cross Validation and K-fold Cross Validation
- Model Evaluation Graphs
- Grid Search

For a code implementation, check out this repo:
github.com/luisguiserrano/manning/tree/master/Chapter_4_Testing_Overfitting_Underfitting

0:00 Introduction
0:37 Which model is better
1:31 Why Testing?
3:27 Golden Rule # 1
4:21 How do we not 'lose' the training data?
4:38 K-Fold Cross Validation
5:20 Randomizing in Cross Validation
5:38 Evaluation Metrics
7:53 Medical Model
8:05 Spam Classifier Model
9:25 Confusion Matrix Diagnosis
11:50 Accuracy
19:47 Precision and Recall
20:54 Credit Card Fraud
22:36 Harmonic mean
24:08 F1 Score
27:16 Types of Errors
27:56 Classification
30:03 Error due to variance (overfitting)
30:18 Error due to bias (underfitting)
31:45 Tradeoff
37:55 Solution: Cross Validation Testing
39:16 Training a Logistic Regression Model
40:04 Training a Decision Tree
40:49 Training a Support Vector Machine
41:14 Grid Search Cross Validation
41:59 Parameters and Hyperparameters
42:56 How to solve a problem
43:20 How to use machine learning
44:04 Thank you!

A friendly introduction to Deep Learning and Neural Networks

Serrano.Academy 2016-12-27 | A friendly introduction to neural networks and deep learning.

For a code implementation, check out this repo
github.com/luisguiserrano/manning/tree/master/Chapter_10_Neural_Networks

This is a follow up to the Introduction to Machine Learning video.
youtube.com/watch?v=IpGxLWOIZy4

Note: In this tutorial I use natural logarithms. If you used logarithms base 10, you may get different answers that I got, although at the end it doesn't matter, since using a different base for the logarithm just scales all the logarithms by a constant.

Announcement: New Book by Luis Serrano! Grokking Machine Learning. bit.ly/grokkingML
40% discount code: serranoyt

00:00 What is machine learning?
2:22 Gradient descent
5:07 Neural network
10:11 logistic regression
12:28 Probability
14:57 Activation Function
19:56 Error function
22:34 Node(Neuron)
24:07 Non-linear regions
31:22 Deep neural network

A Friendly Introduction to Machine Learning

Serrano.Academy 2016-09-09 | Grokking Machine Learning Book: manning.com/books/grokking-machine-learning
40% discount promo code: serranoyt

A friendly introduction to the main algorithms of Machine Learning with examples.
No previous knowledge required.

What is Machine Learning: (0:05)
Linear Regression: (2:25)
Gradient Descent: (4:10)
Naive Bayes: (6:20)
Decision Trees: (10:35)
Logistic Regression: (13:20)
Neural networks: (17:00)
Support Vector Machines: (18:50)
Kernel trick: (20:05)
K-Means clustering: (26:00)
Hierarchical Clustering: (28:30)
Summary: (29:40)

(Thanks to Nick Kartha for breaking down the topics!)

If you like this, there's an extended version in this playlist:
youtube.com/playlist?list=PLAwxTw4SYaPknYBrOQx6UCyq67kprqXe3

Bayes theorem, false positives, and why Im terrified of going to the doctor

Serrano.Academy 2016-05-09 | Announcement: New Book by Luis Serrano! Grokking Machine Learning. bit.ly/grokkingML
40% discount code: serranoyt

An interesting application of Bayes' Theorem.

⭐ Kite is a free AI-powered coding assistant that will help you code faster and smarter. The Kite plugin integrates with all the top editors and IDEs to give you smart completions and documentation while you’re typing. I've been using Kite for 6 months and I love it! kite.com/get-kite/?utm_medium=referral&utm_source=youtube&utm_campaign=luisserrano&utm_content=description-only

Geometric series and my Irish heritage

Serrano.Academy 2016-05-09 | Announcement: New Book by Luis Serrano! Grokking Machine Learning. bit.ly/grokkingML
40% discount code: serranoyt

A fun introduction to geometric series.

⭐ Kite is a free AI-powered coding assistant that will help you code faster and smarter. The Kite plugin integrates with all the top editors and IDEs to give you smart completions and documentation while you’re typing. I've been using Kite for 6 months and I love it! kite.com/get-kite/?utm_medium=referral&utm_source=youtube&utm_campaign=luisserrano&utm_content=description-only