General Information
Objective: Study of the main deep learning methods and their applications.
Syllabus: Machine learning basics; Deep Feedforward Networks; Convolutional Neural Networks (CNNs), Recurrent Neural Networks; Transformers and Natural Language Processing (NLP); Generative Adversarial Networks (GANs); Graph Neural Networks; Reinforcement Learning; Variational Autoencoders; Diffusion Models; Frameworks for deep learning and Practical Aspects; Applications of deep learning models for real-world problems.
Duration/credits: 45 hours/3 credits (12 weeks).
Time: Tuesdays (15:50 - 19:30) - online with synchronous online (SYN) classes.
Lecturers: André Eugenio Lazzaretti and Guilherme Luiz Moritz.
Prerequisites: Linear algebra; Probability and statistics; Differential and integral calculus; Programming (Python).
Python Basics (Lecture 3 and 4 from this link; Lectures 1.2, 1.3, 1.4, 1.5, 2.1, 2.2, 2.3, 2.4, and 2.5 from this link).
Full course on math for ML (link).
Full course on Machine Learning (link).
Grade: Assignments (20%) and Final Project (80%).
Book: Prince, S. J. D. Understanding Deep Learning. MIT Press, 2023: https://udlbook.github.io/udlbook/.
Cluster: LABIC.
Week 4 (Gradients and Backprop) - 27/10 - ASYNC
Content:
Gradients and backprop (slides, video1, video2, video3). Recommended reading: Chapter 7 (7.1 - 7.4) - UDL Book.
Codes (logistic regression 1, logistic regression 2).
Recommended exercises:
Backpropagation (link).
Week 5 (Initialization, Performance and Regularization) - 03/11
Content:
Initialization (slides, video). Recommended reading: Chapter 7 (7.5 - 7.7) - UDL Book.
Performance (slides, video). Recommended reading: Chapter 8 - UDL Book.
Regularization (slides, video). Recommended reading: Chapter 9 - UDL Book.
(extra) Practical Aspects with Pytorch:
Assignment 01:
Neural Networks from Scratch (link)
Week 6 (CNNs) - 10/11
Content:
CNNs (slides, video1, video2). Recommended reading: Chapter 10 (CNN) and Chapter 11 (ResNet) - UDL Book.
Practical Aspects with Pytorch:
CNN in Pytorch and other resources (CNN, Save-Load Models, Transfer Learning and Fine Tuning, Custom Image Datasets, Data Augmentation, UNET).
Assignment 02:
Simpsons Character Classification (link).
Week 10 (Diffusion Models and Representation learning + Self-supervised) - 08/12
Content:
Diffusion Models (slides, video). Recommended reading: Chapter 18 - UDL Book.
Representation learning + self-supervised (slides, video)
Week 11 (Final Project) - 15/12
Final Project
Guidelines and proposal submission (form).
Presentation:
Final Report Deadline: 25/02/2026.
Must contain: Introduction (detailing the addressed problem); Methodology; Results (with comparisons, if possible); Conclusions.
Suggested template: IEEE.
Presentation Deadline: 22/02/2027 - 26/02/2027.
10 minutes for each work + 5 minutes for questions.
26/02/2026 - Exclusively for those who choose to present in English!
Project Update - First week of February/27
Updates on the developments.
Project Presentations - 22/02/2027 - 26/02/2027
Link and schedule.