All Sheets
Practical cheat sheets to help you learn and build faster.
Diagnosing Model Degradation – Visual MLOps Guide
A 12-page visual guide to diagnosing model degradation in production. Learn data drift, concept drift, model monitoring, PSI, KS tests, slice analysis, root-cause diagnosis, and retraining strategies through diagrams, simulated graphs, and Python examples.
Neural Networks – Visual Mental Models & Training Guide
Master neural networks visually with this 14-page beginner-friendly guide. Understand neurons, layers, activation functions, forward propagation, backpropagation, gradient descent, overfitting, and training loops through diagrams, worked examples, and runnable Python code.
Open-Source AI Models – Complete Visual Guide
A 20-page visual guide to open-source AI models, from beginner fundamentals to advanced deployment. Compare Llama, Qwen, DeepSeek, Gemma and other models, learn Ollama and LM Studio, explore hardware requirements, and build AI applications using Python, RAG and fine-tuning.
OPTICS Clustering – Visual Guide with Python
A 15-page visual guide to OPTICS density-based clustering. Learn core distance, reachability plots, cluster extraction, parameter tuning, and how OPTICS compares with DBSCAN, k-means, and HDBSCAN through worked examples, computed charts, and Python code.
Passive-Aggressive Algorithms – Visual Guide
A 14-page visual guide to Passive-Aggressive Algorithms for online machine learning. Learn PA, PA-I, PA-II, hinge loss, margin-based updates, regularization, concept drift, and streaming classification through worked examples, computed graphs, and Python code.
Quadratic Discriminant Analysis (QDA) – Visual Guide
A 14-page visual guide to Quadratic Discriminant Analysis (QDA). Understand Gaussian classification, covariance matrices, curved decision boundaries, QDA vs LDA, regularization, and practical Python implementations with worked examples and computed graphs.
How to Evaluate RAG Answer Quality – Visual Guide
A 16-page visual guide to evaluating Retrieval-Augmented Generation (RAG) systems. Learn context relevance, faithfulness, answer correctness, Precision@k, Recall@k, MRR, nDCG, LLM-as-judge, golden datasets, and production evaluation with worked examples and Python code.
Ridge Regression – Visual Guide to L2 Regularization
Learn Ridge Regression visually with clear diagrams, worked examples, simulated graphs, and Python code. Understand L2 regularization, coefficient shrinkage, overfitting, and how to choose the best regularization strength.
Reinforcement Learning – Visual Mental Models
A 16-page visual guide to reinforcement learning, from agent-environment loops and Q-learning to DQN, PPO, and RLHF. Includes diagrams, worked calculations, simulation graphs, and Python examples.
Diagnosing Sampling Bias – Visual Guide with Python
A 9-page visual guide to identifying, measuring, and correcting sampling bias. Learn eight common bias patterns through diagrams, simulated graphs, diagnostic workflows, worked examples, and tested Python code.
Transformers Explained Visually – ViT & BioBERT Guide
A 17-page visual guide to Transformers, Vision Transformers (ViT), and BioBERT. Learn tokenization, self-attention, encoder architecture, model parameters, biomedical AI applications, fine-tuning, and practical Python examples.
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.