Chart Gallery
121 Charts | Updated: 2025-12-16
N-grams (9) Embeddings (13) RNN/LSTM (13) Seq2Seq (8) Transformers (7) Pre-trained (10) Scaling (11) Tokenization (9) Decoding (8) Fine-tuning (10) Efficiency (8) Ethics (9) Summarization (4) Other Charts (2)
Week 1: N-grams 9
Addk Smoothing
Bigram Calculation Steps
Conditional Probability Tree
Corpus Statistics
Ngram Context Windows
Ngrams
Perplexity Comparison
Smoothing Comparison
Vocabulary Probability
Week 2: Embeddings 13
Cbow Architecture
Context Movement 3D
Cultural Analogies 3D
Embeddings
Landmark Analogies 3D
Negative Sampling Process
Semantic Clusters 3D
Semantic Space 2D
Skipgram Architecture
Skipgram Training Steps
Word2Vec Architectures
Word Arithmetic 3D
Word As Vector Concept
Week 3: RNN/LSTM 13
Forward Pass Flowchart
Gate Activation Heatmap
Gradient Flow Comparison
Gradient Flow Comparison
LSTM Architecture
LSTM Architecture
LSTM Architecture Overview
LSTM Gates Simple
RNN-LSTM
RNN Simple Unrolled
RNN Unrolled
Vanishing Gradient
Vanishing Gradient Problem
Week 4: Seq2Seq 8
Attention Heatmap
Attention Heatmap
Encoder Decoder Architecture
Seq2Seq
Week4 Attention Heatmap
Week4 Beam Search Tree
Week4 Encoder Decoder Flow
Week4 Seq2Seq Architecture Minimalist
Week 5: Transformers 7
3D Multihead Attention
3D Transformer Architecture
Multihead Attention
Positional Encoding 3D
Positional Encoding
Sr 16 Transformer Architecture Annotated
Transformers
Week 6: Pre-trained 10
BERT Architecture
BERT Finetuning Process
BERT Results Glue
BERT Vs GPT Architecture
Classifier Head Architecture
GPT3 Capabilities
GPT Architecture
Pretraining Finetuning Paradigm
Pretraining Workflow
Transfer Learning Visual
Week 7: Scaling 11
Accuracy Size Pareto
Compute Scaling
Data Performance Curves
Emergent Abilities Chart
Emergent Abilities Chart
Model Scale Timeline
Model Scale Timeline
Parameter Spectrum
Scaling
Scaling Laws
Scaling Laws
Week 8: Tokenization 9
BPE Progression Visual
BPE Progression Visual
BPE Visualization
Rare Word Handling Visual
Tokenization
Tokenization Comparison
Tokenization Comparison Visual
Tokenization Impact
Vocab Size Oov Visual
Week 9: Decoding 8
Beam Search Tree
Beam Search Tree Graphviz
Contrastive Vs Nucleus
Decoding
Degeneration Problem
Llm Pipeline Graphviz
Temperature Effects
Topk Example
Week 10: Fine-tuning 10
Adapter Architecture
Catastrophic Forgetting
Deployment Inference Pipeline
Deployment Pipeline
Finetuning
Finetuning Pipeline
Finetuning Vs Prompting
Lora Explanation
Lora Explanation
Unified Framework
Week 11: Efficiency 8
Distillation Architecture
Distillation Architecture
Efficiency
Model Compression Landscape
Model Compression Landscape
Practical Methods Coverage
Quantization Comparison
Quantization Levels
Week 12: Ethics 9
AI Ethics Landscape
Bias Sources Flowchart
Bias Sources Flowchart
Ethics
Fairness Metrics Comparison
Fairness Metrics Comparison
Harm Taxonomy Tree
Harm Taxonomy Tree
Real World Harms
Module: Summarization 4
Bleu Comparison
Evaluation Metrics
Map Reduce Summarization
RAG Summarization Pipeline
Other Charts 2
Pretrained
Training Evolution