README.md

Machine Learning - Coursera - Stanford

Contains the Assignments from the Machine Learning course taught by Prof. Andrew Ng in Coursera.

Environment used - MATLAB, Octave

1. Linear Regression

Linear regression with one variable - Plotting the Data, Gradient Descent, Debugging, Visualizing. Linear regression with multiple variables - Feature Normalization, Gradient Descent, Normal Equations.

2. Logistic Regression

Visualizing, Implementation - Sigmoid function, Cost function and Gradient, fminunc Learning, Evaluation. Regularized logistic regression - Visualizing, Feature mapping, Cost function and Gradient, fminunc Learning, Plotting the decision boundary.

3. Multi-class Classification and Neural Networks

Vectorizing - Cost Function, Gradient, Regularized Logistic Regression. One-vs-all Classification & Prediction. Neural Networks - Model Representation, Feedforward Propagation and Prediction.

4. Neural Networks

Visualizing, Model Representation, Feedforward and cost function, Regularized cost function. Backpropagation - Sigmoid Gradient, Random initialization, Algorithm, Gradient checking, Regularized Neural Networks, fmincg Learning. Visualizing Hidden Layer.

5. Regularized Linear Regression and Bias Vs Variance

Regularized Linear Regression - Visualizing, Cost Function, Gradient, Fitting Linear Regression. Bias-variance - Learning curves. Polynomial Regression - Learning, Adjusting the regularization parameter, Using Cross Validation set to get lambda, Computing Test Set Error, Plotting.

6. Support Vector Machines

SVM with Gaussian Kernels, Spam Classification - Preprocessing Emails, Extracting Features, Training SVM, Top Predictors for Spam.

7. K-means Clustering and Principal Component Analysis

K-means Clustering - Finding Closest Centroids, Computing Centroid Means, Random initialization, Image compression with K-means. PCA - Dimensionality Reduction, Projecting the data onto the principal components, Reconstructing an approximation of the data, Visualizing, PCA for faces.

8. Anomaly Detection and Recommender Systems

Anomaly detection - Gaussian distribution, Estimating parameters for a Gaussian, Selecting threshold, High dimensional dataset. Recommender Systems - Movie ratings dataset, Collaborative filtering learning algorithm, Cost function, Gradient, Regularized Cost function, Gradient, Learning movie recommendations, Recommendations.