Foundations of Machine Learning

a
Course
Postgraduate
Semester
Sem. I
Subject Code
MA618
Subject Title
Foundations of Machine Learning

Syllabus

Machine learning basics: capacity, overfitting and underfitting, hyperparameters and validation sets, bias & variance; PAC model; Rademacher complexity; growth function; VC-dimension; fundamental concepts of artificial neural networks; single layer perceptron classifier; multi-layer feed forward networks; single layer feed-back networks; associative memories; introductory concepts of reinforcement learning, Markhov decision process.

Text Books

Same as Reference
 

References

  1. Mohri, M., Rostamizadedh, A., and Talwalkar, A., Foundations of Machine Learning, TheMIT Press (2012).
  2. Jordon, M. I. and Mitchell, T. M., Machine Learning: Trends, perspectives, and prospects, Vol.349, Issue 6245, pp. 255-260, Science 2015.
  3. Shawe-Taylor, J. and Cristianini, N., Kernel Methods for Pattern Analysis, Cambridge Univ. Press (2004).
  4. Haykin, S., Neural Networks: A Comprehensive Foundation, 2nd ed., Prentice Hall (1998).
  5. Hassoun, M. H., Fundamentals of Artificial Neural Networks, PHI Learning (2010).
  6. Ripley, B. D., Pattern Recognition and Neural Networks, Cambridge Univ. Press (2008).
  7. Sutton R. S. and Barto, A. G., Reinforcement Learning: An Introduction, The MIT Press (2017)

Course Outcomes (COs):
CO1: Ensure students grasp fundamental concepts in machine learning, including neural networks, ensemble learning, overfitting, underfitting, bias-variance tradeoff, and reinforcement learning.

CO2: Enable students to apply machine learning techniques practically.

CO3: Equip students with the ability to evaluate and interpret the performance of machine learning models, emphasizing techniques for assessing generalization capabilities and managing bias-variance trade off.