All Sheets
Practical cheat sheets to help you learn and build faster.
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.
Gradient Descent vs SGD vs Adam
A 10-page visual beginner’s guide to Gradient Descent, SGD, mini-batch SGD, Adam and AdamW, with learning-rate guidance, momentum, real experiments, optimizer comparisons, and practical NumPy & PyTorch code.
Perceptron vs Multilayer Neural Network
A visual beginner’s guide to perceptrons and multilayer neural networks, covering hidden layers, XOR, activation functions, backpropagation, training, and practical Python examples.
Feature Selection Methods in Python
A 17-page visual guide to feature selection in Python covering filter, wrapper, and embedded methods, 12+ selectors, leakage-safe pipelines, practical scikit-learn code, benchmarks, and model-selection strategies.
Hyperparameter Tuning Guide
An 11-page visual hyperparameter tuning guide covering GridSearchCV, RandomizedSearchCV, Optuna, Bayesian optimization, search spaces, nested cross-validation, leakage prevention, early stopping, and practical model-tuning workflows.
Feature Scaling Methods in Python
Master feature scaling in Python with this 9-page visual guide to StandardScaler, MinMaxScaler, RobustScaler, MaxAbsScaler, PowerTransformer, QuantileTransformer and more, including scikit-learn examples, leakage-safe pipelines and a practical scaler decision flowchart.
Feature Engineering: Visual Guide
A practical 12-page visual guide to feature engineering in Python. Learn how to transform, encode, create, select, reduce, and validate features using pandas and scikit-learn while avoiding data leakage.
Bad Data Diagnostic Flowchart
A practical 10-page visual guide for diagnosing and fixing bad data in Python. Covers missing values, outliers, duplicates, class imbalance, label noise, leakage, validation, drift, and production monitoring with pandas and scikit-learn examples.
Which Sampling Method Should I Use?
A visual decision guide to sampling methods, sample size, statistical power, margin of error, weighting, and practical Python implementation.
Which Probability Distribution Fits My Problem?
A visual decision guide to 15 core probability distributions—learn when to use each, compare common choices, match real-world problems, and fit distributions in Python with SciPy.
Which Regression Model Fits My Data?
A visual guide to choosing the right regression model based on your target, data shape, and constraints—with decision flowcharts, model comparisons, diagnostics, validation tips, and scikit-learn code.