🧠
Learn AI with Subhojit Dey
Learn AI
🧠 Learn AI
🏠
Home
🌱
AI for Noobs
🧠
Models & Platforms
⚡
Master Claude
🔧
Build with AI
⚡
AI Working for You
🏢
Enterprise AI
🛡️
Governance & Safety
🏭
AI in Industry
🔬
Deep Dive
Math Foundations
Neural Networks
Transformer Architecture
LLM Pre-training
Scaling
Fine-tuning & Adaptation
Alignment Techniques
Model Architectures
Reasoning Internals
Hardware & Compute
Interpretability
Research Skills
📰
News
✅
Best Practices
🔬
Deep Dive
How AI works under the hood — math, architectures, training, and research
Math Foundations
Linear Algebra
Probability & Statistics
Calculus & Optimization
Information Theory
Neural Networks
Feedforward Networks
Backpropagation
CNNs
RNNs & LSTMs
Encoder-Decoder
Transformer Architecture
Attention Mechanism
Multi-Head Attention
Transformer Block
Positional Encoding
Transformer Variants
LLM Pre-training
Tokenization
Pre-training Objectives
Data Curation
Scaling
Scaling Laws
Chinchilla
Emergent Abilities
Fine-tuning & Adaptation
Supervised Fine-Tuning (SFT)
LoRA & QLoRA
Prompt Tuning
Alignment Techniques
RLHF
DPO
Constitutional AI
Reward Modeling
Model Architectures
GPT Series
LLaMA
Mixture of Experts (MoE)
Mistral & Mixtral
DeepSeek
Reasoning Internals
Chain of Thought
Test-Time Compute
o1 & o3 Internals
DeepSeek-R1 Internals
Hardware & Compute
GPU Architecture
TPU vs GPU
Memory Bandwidth
FLOPs & MFU
Distributed Training
Interpretability
Mechanistic Interpretability
Attention Visualization
Circuits & Features
Research Skills
Reading Papers
Research Venues
Replication