DA 224-O Practical Machine Learning 3:1 (January 2022)

Course Instructor: Deepak Subramani, CDS

Course description: This four-credit course will be offered every year in the January-May term as an elective course of the Data Science and Business Analytics (DSBA) Online M.Tech programme. This course is aimed to be a graduate-level (200-series) course. The course introduces and trains students in different data-driven modeling approaches and machine learning techniques to succeed in industry and research. Emphasis is laid on both understanding different methods and applying them in practice. At the end of the course, students would be able to use machine learning to model and solve data science problems.

Syllabus

Data-Driven Modelling Concepts: Computational Thinking; Software for Machine Learning: Introduction to Scikit-Learn, Keras and TensorFlow.

Supervised Learning: Linear Models for Classification and Regression, Regularization, Optimization Algorithms in Machine Learning, Support Vector Machines (Linear and Kernel), Decision Trees and Ensemble Methods; Dimensionality Reduction: Projection (PCA, kernel PCA), and Manifold Learning (LLE, t-SNE).

Unsupervised Learning: Clustering with K-means, DBSCAN, Gaussian Mixture Models, Anomaly Detection.

Basics of Reinforcement Learning: Markov Decision Process, Dynamic Programming, Q-Learning;

Bayesian Learning: Bayesian methods in Machine Learning. Basics of Neural Networks and Deep Learning.

Textbooks / References

  1. Aurelien Geron (2019). Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow. O'Reilly Media Inc.
  2. Trevor Hastie, Robert Tibshirani, and Jerome Friedman (2013). The Elements of Statistical Learning: Data Mining, Inference, and Prediction. Springer.
  3. Selected chapters, review papers, and online material provided by the instructor.

Prerequisites: DA 202-O, Introduction to Data Science

Grading:

  • Homeworks (Mini Projects) 30%
  • Midterm 20%
  • Final Project 20%
  • Final exam 30%.