Uploaded May 2023 | Updated November 2026, 3 hours ago
Let's talk word embeddings in NLP!
SPONSOR
Get 20% off and be apart of a Premium Software Engineering Community for career advice and guidance: jointaro.com/r/ajayh486
ABOUT ME
β Subscribe: youtube.com/c/CodeEmporium?sub_confirmation=1
π Medium Blog: medium.com/@dataemporium
π» Github: github.com/ajhalthor
π LinkedIn: linkedin.com/in/ajay-halthor-477974bb
RESOURCES
[1 π] A Neural Probabilistic Language Model (Bengio et al., 2003): jmlr.org/papers/volume3/bengio03a/bengio03a.pdf
[2 π] Fast Semantic Extraction Using a Novel Neural Network Architecture (Collobert et al., 2008): aclanthology.org/P07-1071.pdf
[3 π] Word2Vec: arxiv.org/pdf/1301.3781.pdf
[4 π] ELMo: arxiv.org/abs/1802.05365
[5 π] Transformer Paper: arxiv.org/pdf/1706.03762.pdf
[6 π] BERT video: youtube.com/watch?v=xI0HHN5XKDo
[7 π] BERT Paper: arxiv.org/abs/1810.04805
[8 π] ChatGPT: openai.com/blog/chatgpt
PLAYLISTS FROM MY CHANNEL
β Transformers from scratch playlist: youtube.com/watch?v=QCJQG4DuHT0&list=PLTl9hO2Oobd97qfWC40gOSU8C0iu0m2l4
β ChatGPT Playlist of all other videos: youtube.com/playlist?list=PLTl9hO2Oobd9coYT6XsTraTBo4pL1j4HJ
β Transformer Neural Networks: youtube.com/playlist?list=PLTl9hO2Oobd_bzXUpzKMKA3liq2kj6LfE
β Convolutional Neural Networks: youtube.com/playlist?list=PLTl9hO2Oobd9U0XHz62Lw6EgIMkQpfz74
β The Math You Should Know : youtube.com/playlist?list=PLTl9hO2Oobd-_5sGLnbgE8Poer1Xjzz4h
β Probability Theory for Machine Learning: youtube.com/playlist?list=PLTl9hO2Oobd9bPcq0fj91Jgk_-h1H_W3V
β Coding Machine Learning: youtube.com/playlist?list=PLTl9hO2Oobd82vcsOnvCNzxrZOlrz3RiD
Let's talk word embeddings in NLP!
SPONSOR
Get 20% off and be apart of a Premium Software Engineering Community for career advice and guidance: jointaro.com/r/ajayh486
ABOUT ME
β Subscribe: youtube.com/c/CodeEmporium?sub_confirmation=1
π Medium Blog: medium.com/@dataemporium
π» Github: github.com/ajhalthor
π LinkedIn: linkedin.com/in/ajay-halthor-477974bb
RESOURCES
[1 π] A Neural Probabilistic Language Model (Bengio et al., 2003): jmlr.org/papers/volume3/bengio03a/bengio03a.pdf
[2 π] Fast Semantic Extraction Using a Novel Neural Network Architecture (Collobert et al., 2008): aclanthology.org/P07-1071.pdf
[3 π] Word2Vec: arxiv.org/pdf/1301.3781.pdf
[4 π] ELMo: arxiv.org/abs/1802.05365
[5 π] Transformer Paper: arxiv.org/pdf/1706.03762.pdf
[6 π] BERT video: youtube.com/watch?v=xI0HHN5XKDo
[7 π] BERT Paper: arxiv.org/abs/1810.04805
[8 π] ChatGPT: openai.com/blog/chatgpt
PLAYLISTS FROM MY CHANNEL
β Transformers from scratch playlist: youtube.com/watch?v=QCJQG4DuHT0&list=PLTl9hO2Oobd97qfWC40gOSU8C0iu0m2l4
β ChatGPT Playlist of all other videos: youtube.com/playlist?list=PLTl9hO2Oobd9coYT6XsTraTBo4pL1j4HJ
β Transformer Neural Networks: youtube.com/playlist?list=PLTl9hO2Oobd_bzXUpzKMKA3liq2kj6LfE
β Convolutional Neural Networks: youtube.com/playlist?list=PLTl9hO2Oobd9U0XHz62Lw6EgIMkQpfz74
β The Math You Should Know : youtube.com/playlist?list=PLTl9hO2Oobd-_5sGLnbgE8Poer1Xjzz4h
β Probability Theory for Machine Learning: youtube.com/playlist?list=PLTl9hO2Oobd9bPcq0fj91Jgk_-h1H_W3V
β Coding Machine Learning: youtube.com/playlist?list=PLTl9hO2Oobd82vcsOnvCNzxrZOlrz3RiD


![LLM (Parameter Efficient) Fine Tuning - Explained!
Parameter efficient fine tuning is increasingly important in NLP and genAI. Lets talk about it.
RESOURCES
[1 π] RNNs were the SOTA for sequence tasks: https://arxiv.org/pdf/1409.0473
[2 π] Then transformers came on the scene: https://arxiv.org/pdf/1706.03762
[3 π] Pretraining and Finetuning architectures like BERT came along: https://arxiv.org/pdf/1810.04805
[4 π] But LLMs are huge: https://informationisbeautiful.net/visualizations/the-rise-of-generative-ai-large-language-models-llms-like-chatgpt/
[5 π] Few shot learning by GPT-3 tries to address the issue: https://arxiv.org/pdf/2005.14165
[6 π] Parameter Efficient Transfer Learning reduces the trainable parameters via additive adapters (the first PEFT technique): https://arxiv.org/pdf/1902.00751
[7 π] Since 2019, there have been many PEFT techniques introduced: https://arxiv.org/pdf/2312.12148
[8 π] Other notable techniques include prefix-tuning: https://arxiv.org/pdf/2101.00190
[9 π] And LoRA: https://arxiv.org/pdf/2106.09685
[10 π] And a quantized version of LoRA called QLoRA: https://arxiv.org/pdf/2305.14314
[11 π] We see these adapters in use in LLMs today like Llama: https://arxiv.org/pdf/2303.16199
ABOUT ME
β Subscribe: https://www.youtube.com/c/CodeEmporium?sub_confirmation=1
π Medium Blog: https://medium.com/@dataemporium
π» Github: https://github.com/ajhalthor
π LinkedIn: https://www.linkedin.com/in/ajay-halthor-477974bb/
PLAYLISTS FROM MY CHANNEL
β Deep Learning 101: https://www.youtube.com/playlist?list=PLTl9hO2Oobd_NwyY_PeSYrYfsvHZnHGPU
β Natural Language Processing 101: https://www.youtube.com/playlist?list=PLTl9hO2Oobd_bzXUpzKMKA3liq2kj6LfE
β Reinforcement Learning 101: https://youtube.com/playlist?list=PLTl9hO2Oobd9kS NgVz0EPNyEmygV1Ha&si=AuThDZJwG19cgTA8
Natural Language Processing 101: https://youtube.com/playlist?list=PLTl9hO2Oobd_bzXUpzKMKA3liq2kj6LfE&si=LsVy8RDPu8jeO-cc
β Transformers from Scratch: https://youtube.com/playlist?list=PLTl9hO2Oobd_bzXUpzKMKA3liq2kj6LfE
β ChatGPT Playlist: https://youtube.com/playlist?list=PLTl9hO2Oobd9coYT6XsTraTBo4pL1j4HJ
CHAPTERS
0:00 Introduction
1:00 Pass 1: What & Why PEFT
6:27 Quiz 1
7:26 Pass 2: Details
16:20 Quiz 2
17:11 Pass 3: Performance Evaluation
20:49 Quiz 3
21:43 Summary
MATH COURSES (7 day free trial)
π Mathematics for Machine Learning: https://imp.i384100.net/MathML
π Calculus: https://imp.i384100.net/Calculus
π Statistics for Data Science: https://imp.i384100.net/AdvancedStatistics
π Bayesian Statistics: https://imp.i384100.net/BayesianStatistics
π Linear Algebra: https://imp.i384100.net/LinearAlgebra
π Probability: https://imp.i384100.net/Probability
OTHER RELATED COURSES (7 day free trial)
π β Deep Learning Specialization: https://imp.i384100.net/Deep-Learning
π Python for Everybody: https://imp.i384100.net/python
π MLOps Course: https://imp.i384100.net/MLOps
π Natural Language Processing (NLP): https://imp.i384100.net/NLP
π Machine Learning in Production: https://imp.i384100.net/MLProduction
π Data Science Specialization: https://imp.i384100.net/DataScience
π Tensorflow: https://imp.i384100.net/Tensorflow LLM (Parameter Efficient) Fine Tuning - Explained!](https://i.ytimg.com/vi/HcVtpLAGMXo/mqdefault.jpg)
![Vision Transformers - Explained!
In this video, we take a look at Vision Transformers (ViT). What is it? Why do we have it? How do we pretrain and fine tune it?
ABOUT ME
β Subscribe: https://www.youtube.com/c/CodeEmporium?sub_confirmation=1
π Medium Blog: https://medium.com/@dataemporium
π» Github: https://github.com/ajhalthor
π LinkedIn: https://www.linkedin.com/in/ajay-halthor-477974bb/
RESOURCES
[1 π] Slides: https://link.excalidraw.com/p/readonly/6S2vdCqfNqdfLTeMY3UB
[2 π] Paper that introduced Vision Transformers: https://arxiv.org/pdf/2010.11929
[3 π] Paper that introduced transformers: https://arxiv.org/pdf/1706.03762
[4 π] Playlist of Transformers from scratch: https://youtu.be/QCJQG4DuHT0?si=UllVN6odQKC-nsvb
PLAYLISTS FROM MY CHANNEL
β Reinforcement Learning: https://youtube.com/playlist?list=PLTl9hO2Oobd9kS NgVz0EPNyEmygV1Ha&si=AuThDZJwG19cgTA8
Natural Language Processing: https://youtube.com/playlist?list=PLTl9hO2Oobd_bzXUpzKMKA3liq2kj6LfE&si=LsVy8RDPu8jeO-cc
β Transformers from Scratch: https://youtube.com/playlist?list=PLTl9hO2Oobd_bzXUpzKMKA3liq2kj6LfE
β ChatGPT Playlist: https://youtube.com/playlist?list=PLTl9hO2Oobd9coYT6XsTraTBo4pL1j4HJ
β Convolutional Neural Networks: https://youtube.com/playlist?list=PLTl9hO2Oobd9U0XHz62Lw6EgIMkQpfz74
β The Math You Should Know : https://youtube.com/playlist?list=PLTl9hO2Oobd 5sGLnbgE8Poer1Xjzz4h
β Probability Theory for Machine Learning: https://youtube.com/playlist?list=PLTl9hO2Oobd9bPcq0fj91Jgk h1H_W3V
β Coding Machine Learning: https://youtube.com/playlist?list=PLTl9hO2Oobd82vcsOnvCNzxrZOlrz3RiD
MATH COURSES (7 day free trial)
π Mathematics for Machine Learning: https://imp.i384100.net/MathML
π Calculus: https://imp.i384100.net/Calculus
π Statistics for Data Science: https://imp.i384100.net/AdvancedStatistics
π Bayesian Statistics: https://imp.i384100.net/BayesianStatistics
π Linear Algebra: https://imp.i384100.net/LinearAlgebra
π Probability: https://imp.i384100.net/Probability
OTHER RELATED COURSES (7 day free trial)
π β Deep Learning Specialization: https://imp.i384100.net/Deep-Learning
π Python for Everybody: https://imp.i384100.net/python
π MLOps Course: https://imp.i384100.net/MLOps
π Natural Language Processing (NLP): https://imp.i384100.net/NLP
π Machine Learning in Production: https://imp.i384100.net/MLProduction
π Data Science Specialization: https://imp.i384100.net/DataScience
π Tensorflow: https://imp.i384100.net/Tensorflow
CHAPTERS
00:00 What is ViT?
01:41 Why do we have ViTs?
09:50 Pretraining
15:13 Fine tuning
19:22 Quiz Time
20:19 Summary Vision Transformers - Explained!](https://i.ytimg.com/vi/Hnsrm1ezI3g/mqdefault.jpg)


![Inception Net - Explained! (with code)
In this video, we take a look the inception network architecture. What is it? What does it look so funky? How do we code it out? How well does it perform?
ABOUT ME
β Subscribe: https://www.youtube.com/c/CodeEmporium?sub_confirmation=1
π Medium Blog: https://medium.com/@dataemporium
π» Github: https://github.com/ajhalthor
π LinkedIn: https://www.linkedin.com/in/ajay-halthor-477974bb/
RESOURCES
[1 π] Slides used in the video: https://link.excalidraw.com/p/readonly/ELTzuU0KIrfMYo3Q7N31
[2 π] Main paper of the video: https://arxiv.org/pdf/1409.4842
[3 π] Code for inception network: https://github.com/ajhalthor/computer-vision-101/blob/main/Inception_network.ipynb
[4 π] Code to show Alexnet training with comparable performance: https://github.com/ajhalthor/computer-vision-101/blob/main/pointwise_convolution/pointwise_convolutions.ipynb
[5 π] Research that bolstered the hypothesis that the optimal network was a very sparse one: https://arxiv.org/pdf/1310.6343
[6 π] Here is the paper with the visualizations of what convolution layers learn: https://arxiv.org/pdf/1311.2901
PLAYLISTS FROM MY CHANNEL
β Reinforcement Learning: https://youtube.com/playlist?list=PLTl9hO2Oobd9kS NgVz0EPNyEmygV1Ha&si=AuThDZJwG19cgTA8
Natural Language Processing: https://youtube.com/playlist?list=PLTl9hO2Oobd_bzXUpzKMKA3liq2kj6LfE&si=LsVy8RDPu8jeO-cc
β Transformers from Scratch: https://youtube.com/playlist?list=PLTl9hO2Oobd_bzXUpzKMKA3liq2kj6LfE
β ChatGPT Playlist: https://youtube.com/playlist?list=PLTl9hO2Oobd9coYT6XsTraTBo4pL1j4HJ
β Convolutional Neural Networks: https://youtube.com/playlist?list=PLTl9hO2Oobd9U0XHz62Lw6EgIMkQpfz74
β The Math You Should Know : https://youtube.com/playlist?list=PLTl9hO2Oobd 5sGLnbgE8Poer1Xjzz4h
β Probability Theory for Machine Learning: https://youtube.com/playlist?list=PLTl9hO2Oobd9bPcq0fj91Jgk h1H_W3V
β Coding Machine Learning: https://youtube.com/playlist?list=PLTl9hO2Oobd82vcsOnvCNzxrZOlrz3RiD
MATH COURSES (7 day free trial)
π Mathematics for Machine Learning: https://imp.i384100.net/MathML
π Calculus: https://imp.i384100.net/Calculus
π Statistics for Data Science: https://imp.i384100.net/AdvancedStatistics
π Bayesian Statistics: https://imp.i384100.net/BayesianStatistics
π Linear Algebra: https://imp.i384100.net/LinearAlgebra
π Probability: https://imp.i384100.net/Probability
OTHER RELATED COURSES (7 day free trial)
π β Deep Learning Specialization: https://imp.i384100.net/Deep-Learning
π Python for Everybody: https://imp.i384100.net/python
π MLOps Course: https://imp.i384100.net/MLOps
π Natural Language Processing (NLP): https://imp.i384100.net/NLP
π Machine Learning in Production: https://imp.i384100.net/MLProduction
π Data Science Specialization: https://imp.i384100.net/DataScience
π Tensorflow: https://imp.i384100.net/Tensorflow
CHAPTERS
00:00 What is Inception network?
01:20 Why does the network look like this?
11:35 Code
13:11 Quiz Time
14:08 Summary Inception Net - Explained! (with code)](https://i.ytimg.com/vi/Iisq7T1KlJA/mqdefault.jpg)


![Swin transformer - Explained!
In this video, we take a look at Swin Transformers. What is it? Why do we have it? How does it look?
ABOUT ME
β Subscribe: https://www.youtube.com/c/CodeEmporium?sub_confirmation=1
π Medium Blog: https://medium.com/@dataemporium
π» Github: https://github.com/ajhalthor
π LinkedIn: https://www.linkedin.com/in/ajay-halthor-477974bb/
RESOURCES
[1 π] Main Paper: https://arxiv.org/pdf/2103.14030
[2 π] Slides: https://link.excalidraw.com/p/readonly/GDnU1EEBGfAyUoEtVyj8
[3 π] Feature Pyramid Networks: https://youtu.be/i4GKvPGoGxY?si=fgWUV1DYQH3YeU-6
[4 π] Playlist of Transformers from scratch: https://youtu.be/QCJQG4DuHT0?si=UllVN6odQKC-nsvb
[5 π] Faster R-CNN: https://youtu.be/ws0nlxCWWI8?si=om9yCa-mKWxTtFmQ
[6 π] DETR: https://youtu.be/r3lDNWYDGF4?si=N4XehrgljW0A7XPQ
PLAYLISTS FROM MY CHANNEL
β Reinforcement Learning: https://youtube.com/playlist?list=PLTl9hO2Oobd9kS NgVz0EPNyEmygV1Ha&si=AuThDZJwG19cgTA8
Natural Language Processing: https://youtube.com/playlist?list=PLTl9hO2Oobd_bzXUpzKMKA3liq2kj6LfE&si=LsVy8RDPu8jeO-cc
β Transformers from Scratch: https://youtube.com/playlist?list=PLTl9hO2Oobd_bzXUpzKMKA3liq2kj6LfE
β ChatGPT Playlist: https://youtube.com/playlist?list=PLTl9hO2Oobd9coYT6XsTraTBo4pL1j4HJ
β Convolutional Neural Networks: https://youtube.com/playlist?list=PLTl9hO2Oobd9U0XHz62Lw6EgIMkQpfz74
β The Math You Should Know : https://youtube.com/playlist?list=PLTl9hO2Oobd 5sGLnbgE8Poer1Xjzz4h
β Probability Theory for Machine Learning: https://youtube.com/playlist?list=PLTl9hO2Oobd9bPcq0fj91Jgk h1H_W3V
β Coding Machine Learning: https://youtube.com/playlist?list=PLTl9hO2Oobd82vcsOnvCNzxrZOlrz3RiD
MATH COURSES (7 day free trial)
π Mathematics for Machine Learning: https://imp.i384100.net/MathML
π Calculus: https://imp.i384100.net/Calculus
π Statistics for Data Science: https://imp.i384100.net/AdvancedStatistics
π Bayesian Statistics: https://imp.i384100.net/BayesianStatistics
π Linear Algebra: https://imp.i384100.net/LinearAlgebra
π Probability: https://imp.i384100.net/Probability
OTHER RELATED COURSES (7 day free trial)
π β Deep Learning Specialization: https://imp.i384100.net/Deep-Learning
π Python for Everybody: https://imp.i384100.net/python
π MLOps Course: https://imp.i384100.net/MLOps
π Natural Language Processing (NLP): https://imp.i384100.net/NLP
π Machine Learning in Production: https://imp.i384100.net/MLProduction
π Data Science Specialization: https://imp.i384100.net/DataScience
π Tensorflow: https://imp.i384100.net/Tensorflow
CHAPTERS
00:00 What is the Swin Transformer?
01:30 Historical context to understand why Swin Transformers exist
04:45 Problems with vanilla transformer architectures with images
08:23 Swin Transformer architecuture at a high level
09:40 What is the βSwin Transformer Blockβ
10:14 Deep dive into the Swin Transformer block architecture
11:06 Windowed-Multi-head Self Attention
16:10 Shifted Window Multi-head self attention
21:43 Patch Merging
22:36 Swin Transformer + Feature Pyramid Network as backbone
23:46 Performance
24:51 Quiz Time
26:05 Summary Swin transformer - Explained!](https://i.ytimg.com/vi/KEu6HVK_rzE/mqdefault.jpg)
