GRADUATE COURSE · DAS410058

Machine Learning

Foundational mathematical and algorithmic concepts in machine learning, from supervised methods to neural networks, reinforcement learning, and unsupervised learning.

Graduate Program in Automation and Systems Engineering2 credits4 class hours per weekTwo-month course

Syllabus

Regression, classification, neural networks, reinforcement learning, and unsupervised learning.

Learning objectives

The course aims to provide a solid understanding of fundamental machine learning concepts and algorithms, emphasizing core principles, mathematical intuition, and algorithmic foundations. Students develop familiarity with supervised learning for regression and classification, neural networks, reinforcement learning, and unsupervised methods.

Course topics

The following is a topic sequence, not a semester calendar:

  1. Course introduction; machine learning and supervised learning
  2. Regression
  3. Classification and regularization
  4. Neural networks I — foundations
  5. Neural networks II — training and modeling
  6. Reinforcement learning I
  7. Reinforcement learning II; introduction to Convolutional Neural Networks
  8. Unsupervised learning and clustering
  9. Project presentations and discussion

Assessment model

40%One exam (oral or written)
40%One project
20%Up to three practical assignments
The assessment distribution reflects the supplied teaching plan and is shown as a reference model. Requirements and formats for a particular offering are established in the current official teaching plan.

References

  1. T. M. Mitchell. Machine Learning. McGraw-Hill, 1997.
  2. I. Goodfellow, Y. Bengio, and A. Courville. Deep Learning. MIT Press, 2016. Free online edition.
  3. R. O. Duda, P. E. Hart, and D. G. Stork. Pattern Classification, 2nd ed. Wiley, 2001.
  4. R. S. Sutton and A. G. Barto. Reinforcement Learning: An Introduction, 2nd ed. MIT Press, 2018.
  5. T. Hastie, R. Tibshirani, and J. Friedman. The Elements of Statistical Learning, 2nd ed. Springer, 2011.
  6. E. Alpaydin. Introduction to Machine Learning, 2nd ed. MIT Press, 2009.
  7. S. Haykin. Neural Networks: A Comprehensive Foundation (Portuguese edition: Redes Neurais: Princípios e Prática).

← All courses · Generative AI →