Learn core machine learning algorithms with clear explanations, diagrams, and practical intuition — from KNN to LSTM and Transformers.
Learning area
These pages are grouped as a learning collection. More lecture notes, examples, and practical tools can be added without changing the page structure.
Available resources
Available resources
This category combines current MuhammadLab pages that match the topic. More lecture guides and interactive tools can be added here as the lab grows.
Upload CSV data, standardize numeric features, compute PCA step by step, visualize PC1/PC2, and cluster samples with k-means.
Explore one-variable, two-variable, and multi-variable analysis using sample data or your own uploaded dataset.
Learn the diffusion idea: add noise, denoise step-by-step, and how text-to-image works at a high level.
Learn TF-IDF with editable example documents, term scoring, query ranking, cosine similarity, and top-keyword tables.
Interactive classification playground: upload a CSV, choose features + target, and compare tree-based classifiers (Random Forest mode and XGBoost boosting). See accuracy, confusion matrix, precision/recall/F1, and export Python code.
Draw and interpret a trisurface plot for zoo_data.csv with a browser-based 3D surface, Python command example, custom CSV upload, and student-friendly explanations.
Train a perceptron step by step, watch the decision boundary move, inspect weight updates, and classify new points.
Understand Transformers with self-attention intuition, why they scale, and common model variants (encoder/decoder).
Learn boosting intuition, why XGBoost works, and how regularization/shrinkage help.
Interactive regression playground: compare linear regression, polynomial regression, ridge (L2), lasso (L1), and elastic net on one dataset. See the learned equation, R², MSE, and the fitted curve.
Learn what BERT is, masked language modeling, embeddings, and typical NLP uses.
Learn how Random Forests combine many trees with bootstrapping and feature randomness.
Learn convolution, kernels/filters, pooling, feature maps, and why CNNs work for images.
Learn how ViT uses patches + attention for vision tasks and how it differs from CNNs.
Learn decision trees: splits, Gini/entropy, overfitting, pruning, and interpretability.
Learn logistic regression, decision boundaries, logits, and regularization for classification.
Learn gradient descent intuition, learning rate, momentum, and why optimization can be tricky.
Learn how LSTMs use gates and a memory cell to handle longer dependencies in sequence data.
Learn how SVM separates classes with maximum margin, kernels, and where it performs best.
Learn K-means clustering: centroids, assignments, inertia, and how to pick k.
Learn PCA: variance, principal components, dimensionality reduction, and when to use it.
Learn how Word2Vec creates vector embeddings and why semantics emerge from co-occurrence.
Understand KNN classification and regression with distance intuition, scaling tips, and how to choose k.
Learn Bayes’ rule, conditional independence, and why Naive Bayes is strong for text.