Machine Learning course from Stanford University

• the repo will contain the coding asssignments provided by the course

Univariate and multivariate Linear Regression using Gradient Descent

Logistic Regression - the basic and the regularised variants

Still Logistic Regression, but regularised and also forward propagation for Neural Networks

Both forward propagation and backpropagation for the same Neural Netowrk as before

Analysis and visualisation of the Bias - Variance dilemma in Machine Learning

SVM with both linear and gaussian kernels in order to fit complex decision boundaries with as good a margin as possible

Unsipervised Learning (K-Means) and PCA; K-Means is used both to cluster point in 2D and 3D space, but also for image compression

Anomaly Detection by using gaussian distributions and a Recommender System which predicts movie ratings