AI Researcher Hub
GitHubkarpathy/nanoGPT
YouTubeNeural Networks: Zero to Hero
BlogThe Illustrated GPT-2
PaperAttention Is All You Need
GitHubrasbt/LLMs-from-scratch
BookBuild a Large Language Model (From Scratch)
GitHubunslothai/unsloth
GitHubmeta-llama/llama
GitHubopenai/whisper
GitHubgoogle-deepmind/alphafold
GitHubdeepseek-ai/DeepSeek-R1
GitHubgoogle/gemma.cpp
YouTubeTwo Minute Papers
YouTube3Blue1Brown — Neural networks
BlogThe Illustrated Transformer
PaperScaling Laws for Neural LMs
PaperChinchilla
PaperLoRA
PaperInstructGPT
CourseCS231n
CourseCS224n
CoursePractical Deep Learning
ToolHugging Face
ToolWeights & Biases
PersonAndrej Karpathy
PersonYann LeCun
BookMathematics for Machine Learning
BookDive into Deep Learning
GitHubNVIDIA/cuda-samples
ToolPapers With Code
Interview QExplain gradient descent and its variants (SGD, Adam, AdaGrad).
Interview QHow does attention scale similarity search?
Interview QWhen does fine-tuning beat prompting?
12 modules · 108 lessonsFull curriculum