Indian Institute of Information Technology, Allahabad

Introduction to Machine Learning

July-Dec 2026 Semester

Course Information

Course Description: In this course, students learn the concepts of machine learning and practice them in python.

Course Outline:

• Unit 1: Unit I — Regression and Generalized Linear Models: Introduction to Machine Learning, Learning Paradigms and the ML Workflow. Linear Regression - Least-Squares Cost, Normal Equations and Probabilistic Interpretation. Gradient Descent - Batch, Stochastic and Mini-Batch Gradient Descent. Locally Weighted Regression. Logistic Regression - Sigmoid Function, Log-Likelihood and Newton’s Method. The Exponential Family and Generalized Linear Models - Linear, Logistic and Softmax Regression. Regularization Techniques - Ridge and Lasso Regression. Model Evaluation - Overfitting, Bias-Variance Tradeoff, Cross-Validation and Regression Metrics including MSE, MAE and R2
• Unit II — Generative Learning, SVMs, and Ensemble Methods: Generative and Discriminative Learning Approaches. Gaussian Discriminant Analysis. Maximum Likelihood Estimation (MLE) and Maximum A Posteriori (MAP) Estimation, Bayesian Priors. Näıve Bayes Classification. Support Vector Machines. k-Nearest Neighbors. Decision Trees - Entropy, Information Gain and Pruning. Ensemble Methods - Bagging, Random Forests and AdaBoost. Classification Evaluation Metrics - Confusion Matrix, Precision, Recall, F1-Score, ROC and AUC.
• Unit III — Artificial Neural Networks and Introduction to Deep Learning: Perceptron and Its Limitations, Multi-Layer Perceptron, Activation Functions - Sigmoid, Tanh, ReLU and Softmax. Forward Propagation and Backpropagation Algorithm using Chain Rule. Loss Functions and Softmax Cross-Entropy Loss. Weight Initialization Techniques, Optimization using SGD, Momentum and Adam Optimizer. Regularization Techniques - Dropout, Early Stopping and Weight Decay. Introduction to Deep Learning - Overview of Convolutional Neural Networks including Convolution, Pooling, Basic CNN Architecture and Applications in Computer Vision.
• Unit IV — Unsupervised Learning and Dimensionality Reduction: k-Means Clustering and Its Objective Function. Gaussian Mixture Models and Expectation-Maximization (EM) Algorithm with Intuitive Treatment. Principal Component Analysis (PCA) using Eigenvalue Decomposition and Singular Value Decomposition (SVD) for Compression and Visualization. Introduction to Reinforcement Learning: Agent, Environment, States, Actions, Rewards, Exploration versus Exploitation, Markov Decision Process Concepts and Q-Learning. Applications in Games, Robotics and Autonomous Systems.

Course Instructor

Dr. Shiv Ram Dubey

TAs

• Vivek Singh - RSI2026001
• Priyam Pandey - RSI2022510
• S Gokul Raj - PMM2024002
• Preyesh Nandkumar Parab - MML2025007
• Sambhav Goel - MHC2025002

Class Schedule (Section C)

Class: Thursday 11:00 am - 01:00 pm and Friday 02:30 pm - 03:30 pm, Lab: Thursday 02:30 pm - 04:30 pm

Course Ethics

• Students are strictly advised to avoid the unethical practices in the course including tests and practice components.
• It is best to try to solve problems on your own, since problem solving is an important component of the course.
• You are allowed to discuss class material, problems, and general solution strategies with your classmates. But, when it comes to formulating or writing solutions you must work/implement by yourself.
• You are not allowed to take the codes from any source, including online, books, your classmate, etc. in the assignments and exams.
• You may use free and publicly available sources (at idea level only), such as books, journal and conference publications, web pages, AI Tools as research material for your answers with proper credit.
• You may not use any paid service and you must clearly and explicitly cite all outside sources and materials that you made use of.
• Students are not allowed to post the code/report/any other material of course assignment/project in public domain or share with any one else without written permission from course instructors.
• We consider the use of uncited external sources as portraying someone else's work as your own, and as such it is a violation of the Institute's policies on academic dishonesty.
• Instances will be dealt with harshly and typically result in a failing course grade.
• Cheating cases will attract severe penalties.

Schedule

Grading

• Internal (35%)
• Mid Exam (25%)
• End Exam (40%)

Prerequisites

• Ability to deal with abstract mathematical concepts
• Problem Solving
• Computer Programming

Books/References

• 1. Tom M. Mitchell, Machine Learning, 1st Edition, McGraw-Hill Education, 1997.
• 2. Christopher M. Bishop, Pattern Recognition and Machine Learning, 1st Edition, Springer, 2006.
• 3. Kevin P. Murphy, Machine Learning: A Probabilistic Perspective, 1st Edition, MIT Press, 2012.
• 4. Hal Daume III, ́ A Course in Machine Learning, 2017.
• 5. Trevor Hastie, Robert Tibshirani and Jerome Friedman, The Elements of Statistical Learning, 2nd Edition, Springer, 2009.
• 6. Ethem Alpaydin, Introduction to Machine Learning, 4th Edition, MIT Press, 2020.
• 7. Ian Goodfellow, Yoshua Bengio and Aaron Courville, Deep Learning, 1st Edition, MIT Press, 2016.

Disclaimer

The content (text, image, and graphics) used in this slide are adopted from many sources for Academic purposes. Broadly, the sources have been given due credit appropriately. However, there is a chance of missing out some original primary sources. The authors of this material do not claim any copyright of such material.