General Information

Objective: Study of the main machine learning methods and applications.

Syllabus: Machine learning basics; Python and Scikit-learn; Data preprocessing; Classifiers; Dimensionality Reduction; Hyperparameter tuning; Regression; Clustering; Recent Topics.

Duration/credits: 12 weeks - three credits.

Time: Fridays (08:20 - 12:00) - online synchronous (SYN) and asynchronous (ASYN) classes.

Grade: Assignments (20%) and Final Project (80%).

Lecturer: André Eugenio Lazzaretti.

Week 1 - 14/06

• (SYN) Lecture 0 - Dates, grades, admin

  • Video (link).

• (SYN) Lecture 1 - Introduction to Machine Learning

• Slides (link);

• Video (link).

• (SYN) Lecture 2 - Training Simple Machine Learning Algorithms

  • Slides (link);

  • Video (link);

  • Codes (link).

• (ASYN) Assignment 1

  • Guide (link).

Week 3 - 28/06

• • (ASYN) Lecture 4 - A Tour of Machine Learning Classifiers Using scikit-learn - part 2 (nonlinear)

    • Slides (link);

    • Video (link);

    • Codes (link).

  • (ASYN) Lecture 5 - Building Good Training Sets - Data Preprocessing

    • Slides (link);

    • Video (link);

    • Codes (link).

Week 5 - 02/08

• (SYN) Lecture 7 - Predicting Continuous Target Variables with Regression Analysis

  • Slides (link);

  • Videos (link);

  • Codes (link).

• (SYN) Lecture 8 - Compressing Data via Dimensionality Reduction

  • Slides (link);

  • Videos (link);

  • Codes (link).

• (ASYN) Assignment 4 - Dimensionality Reduction

  • Guide (link).

Week 7 - 16/08

• (SYN) Lecture 11 - Neural Networks and Backpropagation

  • Slides (slides);

  • Video (link1, link2).

• (ASYN) Assignment 6 - Neural Networks

  • Guide (link).

• (EXTRA): 

• Convolutional Networks (slides, video).

• CNN Architectures (slides, video).

• Transfer Learning (slides, video).

• Sequence Modeling, Recurrent and Recursive Networks (slides, video).

Week 9 - 30/08

• (ASYN) Lecture 13 - Reinforcement Learning

  • Slides (link);

  • Videos (link);

  • Codes (link1, link2).

Week 11 - 13/09

• (SYN) 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: 25/oct. 

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

    • Suggested template: IEEE.

  • Presentation Deadline: 25/oct. 15 minutes for each work (each student will record a video with their presentation and send it by this date).