Course Contents

• Introduction to ML, When is learning possible?
• Structure of a ML methodology
• Basics of Linear Algebra, Probability
• Matrix operations, Eigenvalues, quadratic forms
• Probability, expectation, variance, Bayes theorem, Linear Regression
• Formulation and error metric, Polynomial regression,Bias Variance Trade-off and overfitting
• Regularization (Ridge and Lasso), Classification, Bayesian approaches, LDA, Naïve Bayes
• K-nearest Neighbours, Cross validation and model selection
• Perceptron model (PLA), Generalization, Support vector machines, Hard margin classifier
• Soft margin classifier, Discussion on projects
• Logistic regression, Cross entropy loss, Gradient Descent algorithms
• Gradient descent, stochastic gradient descent, minibatch gradient descent
• Kernel Methods, Non-linearity in feature space, Decision Trees, Random Forest
• Bragging and Boosting, Neural Networks
• Activation functions and nonlinearities, Backpropagation
• Loss functions, Unsupervised learning, Clustering using K-means,Three rules
• Occam’s razor, Data snooping, Model to match Sample complexity

System of Evaluation

A participant is awarded a grade based on his/her performance in examinations/assignments in every course registered by him/her. These grades are described by the letter
AA, AB, BB, etc. and have a numerical equivalent called grade points as given below: