Machine Learning

Learn the diffusion idea: add noise, denoise step-by-step, and how text-to-image works at a high level.

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.

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.