All Sheets
Practical cheat sheets to help you learn and build faster.
U-Net Segmentation – Visual Architecture
A visual guide to U-Net image segmentation, covering encoder–decoder architecture, skip connections, convolutions, tensor shapes, Dice and IoU metrics, training, and practical PyTorch implementation.
Vision Transformer (ViT) – Visual Mental Models & Architecture Guide
A visual guide to Vision Transformers (ViT), explaining image patches, token embeddings, positional encoding, multi-head attention, Transformer encoder blocks, and image classification through diagrams, computed examples, and NumPy code.
How to Verify Statistical Results Generated by AI
A practical visual guide to verifying AI-generated statistical results. Learn to detect incorrect tests, recompute p-values, check assumptions, interpret confidence intervals, and validate A/B testing conclusions using Python, SciPy, and statsmodels.
How to Evaluate RAG Answer Quality – Visual Guide
A 19-page visual guide to evaluating Retrieval-Augmented Generation (RAG) systems. Learn retrieval metrics, faithfulness, answer correctness, LLM-as-judge, RAGAS, test-set design, and production monitoring through diagrams, worked examples, and Python code.
How a Transformer Processes Text – Visual Guide
A 20-page visual guide explaining how Transformers process text, from tokenization and embeddings to self-attention, multi-head attention, next-token prediction, and training, using clear diagrams and worked numerical examples.
Why Is My Python App Slow?
An 8-page visual troubleshooting guide to finding and fixing slow Python applications. Diagnose CPU, I/O, memory, concurrency, database, and GPU bottlenecks with profiling tools, decision trees, code examples, and a step-by-step optimization workflow.
How to Optimize AI-Generated Python Code – Practical Performance Guide
A practical 13-page visual guide to optimizing AI-generated Python code. Learn profiling, faster algorithms, NumPy and pandas vectorization, caching, generators, concurrency, and safe optimization with before-and-after code and measured benchmarks.
Normalization vs Regularization – Visual Beginner's Guide
An 18-page visual beginner's guide to normalization and regularization in machine learning. Learn feature scaling, BatchNorm, LayerNorm, L1/L2 penalties, dropout, early stopping, and overfitting with diagrams, real experiments, and Python examples.
Model Evaluation Recipes – Visual ML Guide
A practical visual guide to evaluating machine learning models. Learn classification and regression metrics, cross-validation, threshold tuning, calibration, data leakage prevention, and model comparison with scikit-learn examples.
Cross-Validation Mistakes
Learn 10 common cross-validation mistakes that produce misleading machine learning scores. This visual guide explains data leakage, preprocessing pipelines, time-series splits, group-aware validation, nested CV, and evaluation metrics with wrong vs correct Python examples.
Activation Functions — Complete Visual Guide for Neural Networks
A 12-page visual guide to neural network activation functions, covering ReLU, Sigmoid, Tanh, GELU, SiLU, Softmax, gradient flow, weight initialization, performance comparisons, and practical PyTorch examples.
Attention in AI
A 14-page visual guide to Attention in AI, covering Q/K/V, scaled dot-product attention, self & cross-attention, masking, multi-head attention, positional encoding, KV cache, FlashAttention, and practical NumPy + PyTorch code.