Just some of my notes pytorch notes :)
the notes are quite a mess tho I might consider organizing them at some point
Sentdex build neural networks from scratch playlist --> https://www.youtube.com/watch?v=Wo5dMEP_BbI&list=PLQVvvaa0QuDcjD5BAw2DxE6OF2tius3V3
Statquest neural networks playlist --> https://www.youtube.com/watch?v=zxagGtF9MeU&list=PLblh5JKOoLUIxGDQs4LFFD--41Vzf-ME1 --> really good to reinforce how neural networks work
Andrej Karpathy Makemore series --> https://www.youtube.com/watch?v=VMj-3S1tku0&list=PLAqhIrjkxbuWI23v9cThsA9GvCAUhRvKZ --> he explains transformers in the "Let's buidl GPT" video
Learn how RNN's work --> https://www.youtube.com/watch?v=AsNTP8Kwu80 --> later build a RNN using pytorch
Learn how LSTM's work ---> https://www.youtube.com/watch?v=YCzL96nL7j0&t=893s
Build a LSTM --> https://www.youtube.com/watch?v=RHGiXPuo_pI --> code a LSTM along Statquest using pytorch
Word Embeddings --> https://www.youtube.com/watch?v=viZrOnJclY0&t=800s --> learn to use nn.Embedding and train a simple one
Sequence to sequence --> https://www.youtube.com/watch?v=L8HKweZIOmg&t=608s --> Build a seq2seq encoder decoder LSTM based on statquest's video
Watch statquest's explanation about transformers --> https://www.youtube.com/watch?v=zxQyTK8quyY&t=988s
Watch this explanation of the transformer architecture for more in depth information --> https://www.youtube.com/watch?v=4Bdc55j80l8
Follow Andrej Karpathy Makemore series --> https://www.youtube.com/watch?v=VMj-3S1tku0&list=PLAqhIrjkxbuWI23v9cThsA9GvCAUhRvKZ
Code along the "Let's Build GPT" video and then go back to this video --> https://www.youtube.com/watch?v=4Bdc55j80l8 and build the transformer encoder decoder from scratch with pytorch
book I used to learn the basics --> https://nnfs.io/ book playlist --> https://www.youtube.com/watch?v=Wo5dMEP_BbI&list=PLQVvvaa0QuDcjD5BAw2DxE6OF2tius3V3
really cool mathy book --> https://www.deeplearningbook.org/
a really nice introduction to nlp --> https://learning.oreilly.com/library/view/natural-language-processing/9781491978221/
attention is all you need --> https://arxiv.org/abs/1706.03762