This post contains resources which I believe to be the best at teaching what they do. When I find improved resources I will make sure to replace older resources.

Table of Contents

1. Videos
2. Blog Posts
3. Data Science
4. Courses or Course Material
5. Personalities
6. Summary Material

Videos

Programming

• Full course in python programming from beginners to introduction of classes (ref)

Mathematics

• (6-7) Linear algebra for beginners (ref)

Neural Networks

• Playlist by 3Blue1Brown on fully connected neural networks (ref)

Deep Learning

• Tutorial in PyTorch (ref)

Transformer and Attention

• Brief introduction to transformer models (ref)
• Step by step explanation of transformers (ref)

Blog Posts

Machine Learning

• Wonderful blog by OpenAI engineer on NN and ML (ref)

Transformers and Attention

• A blogpost explaining the transformer: The Illustrated Transformer (ref)
• The annotated transformer (ref)
• Transformers are GNN (ref)
• A blogpost explaing Attention in Machine Translation (ref)
• The annotated encoder decoder with Bahdanau attention. Similar to the annotated transformer but with the paper introducing attention by Bahdanau (ref)

Courses or Course Material

NLP

• NLP Course (ref) and associated github (ref)

Deep Learning

• Deep learning (ref)

Machine Learning

• Course in general ML by fast.ai (ref)

Personalities

Mathematics

• (10) 3Blue1Brown by Grant Sanderson (ref)

Machine Learning and statistics

• StatQuest by Josh Starmer (ref)

Books

Data Vizualization

• A book on data vizualization (ref)

Data

Machine Learning

• State-of-the-art (ref)

NLP

• State-of-the-art (ref)
• Common Crawl (ref)

Resource Collection

Data Science

• A look up resource for data science concepts (ref)

PyTorch

• A list of pytorch resources (ref)

Summary Material

• Spectra Pub, a Machine Learning Review Paper Competition. Full of great review papers of entire fields. (ref)