AI tutorials

General

• MLU-EXPLAIN

Loss Functions

• Understanding Categorical Cross-Entropy Loss, Binary Cross-Entropy Loss, Softmax Loss, Logistic Loss, Focal Loss and all those confusing names

Transformer

• Wolfram: What Is ChatGPT Doing … and Why Does It Work?
• The Illustrated Transformer
• Transformers Explained Visually — Not Just How, but Why They Work So Well

Visualizations

• LLM Visualization
• Transformer Explainer (paper)
• Phrase completion
• Karpathy: Tiktoken Emoji

LLM

• A Survey on Large Language Models: Applications, Challenges, Limitations, and Practical Usage
• Aman AI: Overview of Large Language Models
• Awesome-LLM: Curated list of LLM projects
• 2025-01: Foundations of Large Language Models

Other Visualizations

• Inside the Matrix: Visualizing Matrix Multiplication, Attention and Beyond
• Neural network training makes beautiful fractals