The following syllabus will be covered as part of this course. The syllabus is just for reference. We will be covering The approach was exploraratory and case study based. We used inuition in place of abstraction. By the end of the course, the students were able to get the right intuition for the importance of machine learning, classical and modern techniques, regression, and classification etc in data science related applications.

Sl. No. Topic
1 Introduction to foundations of machine learning through case studies
2 Matrices, probability and optimisation
3 Linear Algebra - Eigenvalues and eigenvectors, Symmetric matrices, SVD
4 Introduction to Unsupervised Learning - Representation learning - PCA
5 Unsupervised Learning Clustering - K-means/Kernel K-means
6 Unsupervised Learning - Estimation - Recap of MLE + Bayesian estimation, Gaussian Mixture Model - EM algorithm.
7 Supervised Learning - Regression - Least Squares; Bayesian view; Regression - Ridge/LASSO
8 Supervised Learning - Classification - K-NN, Decision tree
9 Supervised Learning - Classification - Generative Models - Naive Bayes
10 Discriminative Models - Perceptron; Logistic Regression
11 Support Vector Machines
12 Artificial Neural networks: Multiclass classification.