nlp101

Brandon Foltz's Probability and Statistics lectures are posted on Youtube and is rather short, so it can be easily accessed during daily commute.

A coursebook on calculus written by professor Gilbert Strang. There is no need to go through the whole book, but chapters 2-4, 11-13, 15-16 are very worth studying.

A calculus lecture by the channel 3Blue1Brown mentioned above, helpful for those who want an overview of calculus likewise.

A Linear algebraic lecture on Youtube channel 3Blue1Brown. Could be a big help for those planning to take undergraduate-level linear algebra since it allows overall understanding. It provides intutitively understandable visual aids to getting the picture of Linear algebra.

A legendary lecture of professor Gilbert Strang.

A book on all the mathematical knowledge accompanied with machine learning. Mathematic knowledge within the collegiate level of natural sciences or engineering is preferable here, as the explanations are mainly broad-brush.

Word2Vec Tutorial - The Skip-Gram Model

Understanding LSTM Networks

A Light Introduction to Transfer Learning for NLP

Visualizing memorization in RNNs

Illustrated Word2vec

How to Develop a Neural Machine Translation System from Scratch

A code-first NLP lecture by Rachel Thomas, the co-founder of fast.ai. The motivation that Rachel Thomas gives is mind blowing.

Awesome NLP lecture from Stanford. It has the 2019 version, dealing with the latest trends.

An NLP lecture that was revalued since the advent of GLUE benchmark. Recommended to be taken after CS224N, and its merit is that it provides exercises in Pytorch.

A Deep Learning lecture of the renouned professor Andrew Ng, who has recently founded a startup on AI education.

A book written by Ian Goodfellow, the father of GAN, and other renouned professors.

While the 'Deep Learning Book' above has theoretical explanation, this book also includes the codes to check how the notion is actually immplemented.

Sequence to Sequence tool kit by Facebook written in Pytorch.

A tokenizer library that Hugging Face maintains. It boosts fast operations as the key functions are written in Rust. The latest tokenizers such as BPE can be tried out with Hugging Face tokenizers.

A library based on Transformer provided by Hugging Face that allows easy access to pre-trained models. One of the key NLP libraries to not only developers but researchers as well.

Stanford's lecture CS231N deals with NumPy, which is fundamental in machine learning calculations.

An awesome tutorial on Pytorch provided by Facebook with great quality.

Google's open source library that builds BPE-based vocabulary using subword information.