21CS644/21AI604 Machine Learning
(Odd Semester 2023-2024)
(I SEM -MTech(CSE/AI) (SoftCore1/Core))
Instructor: Dr. Mansi Sharma
Lectures: Monday (Slot 3), Tuesday (Slot 6), Thursday (Slot 3)
Lab Sessions: Wed (Slot 8-9)
Room No. - AB3 GF C102
Lab Room No. - AB3 GF A103
Course Description
This course provides a concise introduction of the fundamental concepts in machine learning algorithms. The basic concepts of machine learning will be introduced from a mathematically well motivated perspective. The course will be accompanied by hands-on problem solving with programming in Python, covering different learning paradigms and some of the more popular algorithms and architectures used in each of these paradigms.
Prerequisite
BASICS OF LINEAR ALGEBRA, PROBABILITY THEORY AND OPTIMIZATION
Syllabus
Flavours of Machine Learning: Unsupervised, Supervised, Reinforcement, Hybrid Models;
Linear Algebra: Scalars, Vectors, Tensors, Basic Operations, Norms, Linear Combinations, Span, Linear Independence, Matrix Operations, Special Matrices, Matrix Decompositions;
Probability Theory: Introduction to Probability Theory, Discrete and Continuous Random Variables, Conditional, Joint, Marginal Probabilities, Sum Rule and Product Rule, Bayes' Theorem, Independence, Conditional Independence, Chain Rule of Probability, Expectation, Variance Covariance;
Regression Models: Simple Linear Regression, Multiple Linear Regression, Least Square Regression, Multivariate Regression, Ridge Regression, Lasso Regression, Bayesian Regression, Regression with Basic Functions;
Classification - Linear Models: Linear Classification, Logistic Regression;
Discriminant Functions and Models: Discriminant Function under Multivariate Normal Distribution, Decision Boundary under various cases of Covariance Matrices;
Decision Trees: Introduction, Regression Trees, Stopping Criteria & Pruning, Loss Functions for Classification,
Categorical Attributes, Multiway Splits, Missing Values, Imputation & Surrogate Splits, Instability, Smoothness & Repeated Subtrees;
Ensemble Methods: Bagging, Boosting, Random Forest;
Instance Based Learning: k-Nearest Neighbour, Feature Selection, Feature Extraction, Collaborative Filtering;
Support Vector Machine: SVM for Classification, Linear Machine, Multiclass Support Vector Machine,
SVM : Dual Formulation and Kernel Trick, Nonlinear SVM and Kernel Function, SVM : Solution to
Dual Problem, SVM for Regression;
Statistical Decision Theory: Regression, Classification, Evaluation of Classifiers, Evaluation, Cross-Validation, Bias and Variance in Machine Learning;
Neural Networks: McCulloch Pitts Neuron, Thresholding Logic, Perceptron, Perceptron Learning Algorithm,
Linearly Separable Boolean Functions, Representation Power of a Network of Perceptrons, Representation Power of Multilayer Network of Sigmoid Neurons, Feedforward Neural Networks (a.k.a multilayered network of neurons), Backpropagation Learning, Initialization, Training & Validation;
Introduction to Clustering: Kmeans Clustering, PAM (Partitioning Around Clustering), Agglomerative Hierarchical Clustering, DBSCAN - Density Based Clustering Algorithm, Gaussian Mixture Models
Expectation Maximization;
Graphical Models: Bayesian Learning, Naive Bayes, Bayesian Networks, Undirected Graphical Models, Hidden Markov Models;
Dimensionality Reduction: Principal Component Analysis, Singular Value Decomposition;
Evaluation Plan
Mid Term Exam - 15 Marks
Lab Evaluation 1 - 7 Marks
Lab Evaluation 2 - 8 Marks
End Semester Evaluation 30 Marks
Mini Project Implementation - 20 Marks
Viva - 10 Marks
Tentative Exam Schedule
Lab Evaluation 1 - Sep 13th 2023
Mid Term Exam - Sep 19th 2023
Lab Evaluation 2 - Nov 8th 2023
End Semester Evaluation - Dec 1st 2023
TextBooks/References