Machine Learning

This repo contains a set of ML algorithms implemented from first principles. These notebooks help to understand the inner workings of modern ML libraries such as Scikit-Learn. Detailed analysis and visualisations are provided along with the code.

For a better experience with notebooks, it is recommended to view the repository at https://nbviewer.org/github/nveshaan/machine_learning/tree/main/

Classification and Regression

• Linear Discriminant Analysis
• Naive Bayes Classifier
• Logistic Regression
• KNN (K nearest neighbor) Classifier
• SVM: Support Vector Machine
• Trees, Forests, Bagging and Boosting
• Gaussian Processes
• Linear Regression
• Generalized Linear Models

Dimensionality Reduction

• PCA: Principal Component Analysis
• t-SNE: t-distributed Stochastic Neighbor Embedding
• UMAP: Uniform Manifold Approximation and Projection

Clustering & Density Estimation

• K-means
• Mixture Models and EM (Expectation-Maximization)
• KDE: Kernel Density Estimation

Inference

• Kalman Filter
• Variational Inference
• Gibbs Sampling
• Importance Sampling

Discovery

• Latent Factor Models (LDA, PCA, GMM)
• HMM: Hidden Markov Model