General Information

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

Syllabus: Machine learning basics; Python and Scikit learn; Data preprocessing; Basic Classifiers; Dimensionality Reduction; Hyperparameter tuning; Multilayer Artificial Neural Network; TinyML.

Duration: 60 hours (18 weeks).

Time: Mondays (17:50 - 21:10) - synchronous (SYN) at CB301 and asynchronous (ASYN) classes (videos).

Grade: Assignments (50%) and Final Project (50%).

TinyML: Combined use of Arduino Nano 33 IoT (link) with Edge Impulse (link).

Lecturer: André Eugenio Lazzaretti.

Preliminary Content

Python Basics:

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

  • Similar material in portuguese: link.

Mathematical Background:

• Linear Algebra: slides, video;

• Probability and Statistics: slides, video;

• Optimization: video, slides.

Track on Signals, Images, and Patterns: link.

Week 2 - 14/03

(ASYN) Lecture 2 - Training Simple Machine Learning Algorithms

• Slides (link);

• Videos (link1, link2);

• Codes (link).

Week 4 - 28/03

(ASYN) Lecture 4 - Building Good Training Sets - Data Preprocessing

• Slides (link);

• Videos (link);

• Codes (link).

Week 6 - 11/04

(SYN) Assignment 1 - Python and Machine Learning Basics

• Guide (link).

Week 8 - 25/04

(SYN) Assignment 2 - Classification with scikit-learn

• Guide (link).

Week 10 - 09/05

(ASYN) Lecture 7 - Implementing a Multilayer Artificial Neural Network from Scratch

• Slides (link);

• Videos (link);

• Codes (link);

• Tutorial for Keras (link).

Week 12 - 23/05

(SYN) Assignment 4 - Embedded Machine Learning - part 2

• Guide (link).

Week 14-17 - 06/06, 13/06, 20/06, and 27/06

(SYN) Development of the final project

• Guide (link).