Bibliography and Support Materials

Books:

• Theory:

  • Bishop, C. Pattern Recognition and Machine Learning. Springer, 2006.

  • Theodoridis, S. Machine Learning: A Bayesian and Optimization Perspective. Academic Press, 2020.

  • Deisenroth, M. P.; Faisal, A. A. & Ong, C. S. (2020), Mathematics for Machine Learning, Cambridge University Press.

• Practical:

  • Raschka, S. Python Machine Learning. Packt, 2020.

Linear Algebra:

• Slides (link);

• Video (link1, link2).

Vector Calculus:

• Slides (link);

• Video (link).

Probability and Statistics:

• Slides (link);

• Video (link).

Optimization:

• Slides (link);

• Video (link).

Python Basics:

• General overview: link (Part II - L03 and L04).

Week 2 - 21/06

• (SYN) Lecture 3 - A Tour of Machine Learning Classifiers Using scikit-learn - part 1 (linear)

  • Slides (link1, link2);

  • Video (link1, link2);

  • Codes (link).

• (ASYN) Assignment 2 - Python and Machine Learning Basics

  • Guide (link).

Week 4 - 05/07

• (SYN) Lecture 6 - Learning Best Practices for Model Evaluation and Hyperparameter Tuning

  • Slides (link);

  • Videos (link);

  • Codes (link).

• (ASYN) Assignment 3 - Real Problem

  • Guide (link).

Week 6 - 16/08

• (SYN) Lecture 9 - Working with Unlabeled Data

  • Slides (link);

  • Videos (link);

  • Codes (link).

• (SYN) Lecture 10 - Anomaly Detection

  • Slides (link);

  • Videos (link);

  • Codes (link).

• (ASYN) Assignment 5 - Clustering

  • Guide (link).

Week 8 - 30/08

• (SYN) Lecture 12 - Reinforcement Learning

  • Slides (link);

  • Videos (link);

  • Codes (link1, link2).

Week 10 - 13/09

• Final Project Discussion.

• Final Project - Rules:

  • It can be in pairs.

  • Something more than getting data and model already available is expected.

  • Important to detail and interpret the results.

  • Important: it could become a publication in a conference/journal.

• Project Proposals - Guidelines:

  • What is the problem to be solved? Preferably a real problem that can be solved via deep learning. 

    • Appropriate answer: perform classification of EEG signals to identify movement intentions.

    • Inappropriate answer: I have this dataset (own, Kaggle, etc.) and intend to use a CNN to check the classification result.

  • Dataset available? Few data may make it unfeasible.

  • What techniques do you intend to use and why?

  • If you have a comparison parameter (papers, kaggle, etc).

• Final Project - Presentation:

  • Final Report Deadline: TBD. 

    • Must contain: Introduction (detailing the addressed problem); Methodology; Results (with comparisons, if possible); Conclusions. 

    • Suggested template: IEEE.

  • Presentation Deadline: TBD. 15 minutes for each work + 5 minutes for questions.