CMC701/Semester 7
Machine Learning
29 notes written · 64% syllabus coverage (28 of 44 topics)
CMC701 — Machine Learning
Detailed Syllabus
Module I — Introduction to Machine Learning (4 hours)
- 1.1 Machine Learning basics
- 1.2 Types of Machine Learning
- 1.3 Issues in Machine Learning
- 1.4 Application of Machine Learning
- 1.5 Steps in developing a Machine Learning Application
- 1.6 Training Error, Generalization Error
- 1.7 Overfitting, Underfitting
- 1.8 Bias-Variance Trade-off
Module II — Learning with Regression and Trees (9 hours)
2A. Learning with Regression
- 2.1 Linear Regression
- 2.2 Multivariate Linear Regression
- 2.3 Logistic Regression
2B. Learning with Trees
- 2.4 Decision Trees
- 2.5 Constructing Decision Trees using Gini Index (Regression)
- 2.6 Classification and Regression Trees (CART)
2C. Performance Metrics
- 2.7 Confusion Matrix
- 2.8 Kappa Statistics
- 2.9 Sensitivity, Specificity
- 2.10 Precision, Recall, F-measure
- 2.11 ROC Curve
Module III — Ensemble Learning (6 hours)
- 3.1 Understanding Ensembles
- 3.2 K-Fold Cross Validation
- 3.3 Boosting
- 3.4 Stumping
- 3.5 XGBoost
- 3.6 Bagging, Subagging
- 3.7 Random Forest
- 3.8 Comparison with Boosting
- 3.9 Different Ways to Combine Classifiers
Module IV — Learning with Classification (8 hours)
- 4.1 Support Vector Machine — Constrained Optimization
- 4.2 Optimal Decision Boundary, Margins and Support Vectors
- 4.3 SVM as Constrained Optimization Problem
- 4.4 Quadratic Programming
- 4.5 SVM for Linear and Nonlinear Classification
- 4.6 Basics of Kernel Trick
- 4.7 Support Vector Regression
- 4.8 Multiclass Classification
Module V — Learning with Clustering (7 hours)
- 5.1 Introduction to Clustering
- Overview of Distance Metrics
- Major Clustering Approaches
- 5.2 Graph-Based Clustering: Clustering with Minimal Spanning Tree
- 5.3 Model-Based Clustering: Expectation Maximization Algorithm
- 5.4 Density-Based Clustering: DBSCAN
Module VI — Dimensionality Reduction (5 hours)
- 6.1 Dimensionality Reduction Techniques
- 6.2 Principal Component Analysis (PCA)
- 6.3 Linear Discriminant Analysis (LDA)
- 6.4 Singular Value Decomposition (SVD)
Text Books
| # | Title | Author(s) | Publisher |
|---|---|---|---|
| 1 | Machine Learning in Action | Peter Harrington | DreamTech Press |
| 2 | Introduction to Machine Learning | Ethem Alpaydın | MIT Press |
| 3 | Machine Learning | Tom M. Mitchell | McGraw Hill |
| 4 | Machine Learning: An Algorithmic Perspective | Stephen Marsland | CRC Press |
References
| # | Title | Author(s) | Publisher |
|---|---|---|---|
| 1 | Data Mining Concepts and Techniques | Han Kamber | Morgan Kaufmann |
| 2 | Data Mining: Introductory and Advanced Topics | Margaret H. Dunham | Pearson Education |
| 3 | Machine Learning: A Probabilistic Perspective | Kevin P. Murphy | — |
| 4 | Introduction to Soft Computing | Samir Roy & Chakraborty | Pearson |
| 5 | Pattern Classification (2nd Ed.) | Richard Duda, Peter Hart, David G. Stork | Wiley |
Online References
| # | Resource |
|---|---|
| 1 | Kaggle Datasets |
| 2 | UCI Machine Learning Repository |
| 3 | Machine Learning — Coursera |
| 4 | Towards Data Science — ML |
| 5 | NPTEL: Machine Learning |
CML706 — Machine Learning Lab
List of Experiments
| Sr. No. | Experiment Title | Hours |
|---|---|---|
| 01 | To implement Linear Regression | 2 |
| 02 | To implement Logistic Regression | 2 |
| 03 | To implement Ensemble Learning (Bagging/Boosting) | 2 |
| 04 | To implement Multivariate Linear Regression | 2 |
| 05 | To implement SVM | 2 |
| 06 | To implement PCA / SVD / LDA | 2 |
| 07 | To implement Graph-Based Clustering | 2 |
| 08 | To implement DBSCAN | 2 |
| 09 | To implement CART | 2 |
| 10 | To implement LDA | 2 |
Assignments / Tutorials
| Sr. No. | Description | Hours |
|---|---|---|
| 01 | Assignment covering Modules I–III (limited to 3 questions) | 2 |
| 02 | Assignment covering Modules IV–VI (limited to 3 questions) | 2 |
Lab Text Books & References
(Same as theory — see Text Books and References sections above.)