NLP
Modern NLP — language models, embeddings, transformers, and beyond.
01NLP (1): Introduction and Text Preprocessing
A first-principles introduction to NLP and text preprocessing. We trace the four eras of the field, build the cleaning …
02NLP (2): Word Embeddings and Language Models
Understand how Word2Vec, GloVe, and FastText turn words into vectors that capture meaning. Learn the math, train your …
03NLP (3): RNN and Sequence Modeling
How RNNs, LSTMs, and GRUs process sequences with memory. We derive vanishing gradients from first principles, build a …
04NLP (4): Attention Mechanism and Transformer
From the bottleneck of Seq2Seq to Attention Is All You Need. Build intuition for scaled dot-product attention, …
05NLP (5): BERT and Pretrained Models
How BERT made bidirectional pretraining the default in NLP. We unpack the architecture, the 80/10/10 masking rule, …
06NLP (6): GPT and Generative Language Models
From GPT-1 to GPT-4: understand autoregressive language modeling, decoding strategies (greedy, beam search, top-k, …
07NLP (7): Prompt Engineering and In-Context Learning
From prompt anatomy to chain-of-thought, self-consistency and ReAct: a working theory of in-context learning, the …
08NLP (8): Model Fine-tuning and PEFT
A deep dive into Parameter-Efficient Fine-Tuning. Why LoRA's low-rank update works, the math and memory accounting …
09NLP (9): Deep Dive into LLM Architecture
Inside modern LLMs: pre-norm + RMSNorm + SwiGLU + RoPE + GQA, KV cache mechanics, FlashAttention's IO-aware schedule, …
10NLP (10): RAG and Knowledge Enhancement Systems
Build production-grade RAG systems from first principles: the retrieve-then-generate decomposition, vector indexes …
11NLP (11): Multimodal Large Language Models
A deep dive into multimodal LLMs: contrastive vision-language pre-training with CLIP, parameter-efficient bridging with …
12NLP (12): Frontiers and Practical Applications
Series finale: agents and tool use (Function Calling, ReAct), code generation (Code Llama, Codex), long-context …