Deep Learning (DEEP-0001) UTFPR-CPGEI-DAELN

2026/02

2026/03

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 (13:50 - 17:30) - online with synchronous online (SYN) classes.

Lecturers: André Eugenio Lazzaretti.

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).
Linear Algebra Review (slides, video).
Statistics Review (slides, video).
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/.

Pre-content - Only for undergraduate students

18/08:

Rules.
Introduction to Machine Learning

Slides (link);

Training Simple Machine Learning Algorithms
- Slides (link);
- Codes (link).

Assignment 1
- Guide (link).

25/08:

- A Tour of Machine Learning Classifiers Using scikit-learn - part 1 (linear)
  - Slides (link1, link2);
  - Codes (link).

01/09:

- Assignment 2: Python and Machine Learning Basics
  - Guide (link).

08/09:

- A Tour of Machine Learning Classifiers Using scikit-learn - part 2 (nonlinear)
  - Slides (link);
  - Codes (link).
- Learning Best Practices for Model Evaluation and Hyperparameter Tuning
  - Slides (link);
  - Codes (link).

15/09:

- Assignment 3 - Real Problem
  - Guide (link) (video).

22/09:

- Predicting Continuous Target Variables with Regression Analysis
  - Slides (link);
  - Codes (link).
- Compressing Data via Dimensionality Reduction
  - Slides (link);
  - Codes (link).

29/09:

- Assignment 4 - Dimensionality Reduction
  - Guide (link).

Week 1 (Intro and Supervised Learning) - 06/10

Content:

Rules (video)
Intro (slides, video). Recommended reading: Chapter 1 - UDL Book.
Supervised Learning (slides, video). Recommended reading: Chapter 2 - UDL Book.

Assignment 01:

Code and math intro (link).
Supervised learning (link).

Week 2 (Shallow and Deep Networks) - 13/10

Content:

Shallow Neural Networks (slides, video). Recommended reading: Chapter 3 - UDL Book.
Deep Neural Networks (slides, video). Recommended reading: Chapter 4 - UDL Book.

Assignment 02:

Shallow Neural Networks (part1, part2).
(optional) Deep Neural Networks (link).

Week 3 (Loss Functions and Fitting Models) - 20/10

Content:

Loss Functions (slides, video). Recommended reading: Chapter 5 - UDL Book.
Fitting Models (slides, video). Recommended reading: Chapter 6 - UDL Book.

Assignment 03:

Binary Cross Entropy Loss (link).
Gradient Descent (link). Line Search Solved (here).

Week 4 (Gradients and Backprop) - 27/10

Content:

Gradients and backprop (slides, video1, video2). Recommended reading: Chapter 7 (7.1 - 7.4) - UDL Book.

Assignment 04:

(optional) Backpropagation (link). Solution (here).

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.

Practical Aspects with Pytorch:

Pytorch (video1, video2).
MLP in Pytorch (video).

Assignment 05:

Spaceship Titanic (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 06:

Simpsons Character Classification (link).

Week 7 (Recurrent Models and Transformers) - 17/11

Content:

RNNs (slides, video).
Transformers (slides, video). Recommended reading: Chapter 12 - UDL Book.

Assignment 07:

Zero-shot and Few-shot NLP with Instruction-tuned Transformers (link).

Practical Aspects with Pytorch:

LSTM example in Pytorch (video).
Transformer (video0, video1, video2).

Week 8 (Graph NNs and Reinforcement Learning) - 24/11

Content:

Reinforcement Learning (slides, video). Recommended reading: Chapter 19 - UDL Book.
Graph NNs (slides, video). Recommended reading: Chapter 13 - UDL Book.

Week 9 (GANs) - 01/12

Content:

GANs (slides, video). Recommended reading: Chapter 15 - UDL Book.

Assignment 08:

GANs to Generate Simpsons Characters (link).

Practical Aspects with Pytorch:

GAN (GAN, DCGAN, WGAN).
Conditional GAN (video).

Week 10 (Variational Autoencoders and Diffusion Models) - 08/12

Content:

Variational Autoencoders (slides, video). Recommended reading: Chapter 17 - UDL Book.
Diffusion Models (slides, video). Recommended reading: Chapter 18 - UDL Book.

Week 11 (Project Proposals) - 15/12

Guidelines and submission (form).

Final Project - 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: 26/02/2026 and 27/02/2026.
  - 10 minutes for each work + 5 minutes for questions.
  - 27/02/2026 - Exclusively for those who choose to present in English!

Google Sites

Report abuse