Deep Learning (DEEP-0001) UTFPR-CPGEI 2025/03

Final Project Rules

• Final Project - Rules:

  • It can be in pairs.

  • Something more than getting data and network 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 (example): Classify EEG signals to identify movement intentions.

    • Inappropriate answer (example): 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.

  • Do you need HW (GPU)? The LABIC cluster may be made available.

  • What techniques do you intend to use and why?

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

• Final Project - Presentation:

  • Final Report Deadline: Mar XXX (2026). 

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

    • Suggested template: IEEE.

  • Presentation Deadline: XXX Mar (2026). 15 minutes for each work + 5 minutes for questions. 

Week 2 (Shallow and Deep Networks)

Content: 

• Shallow Neural Networks (slides, video).

• Deep Neural Networks (slides, video).

Assignment 02:

• Shallow Neural Networks (part1, part2).

• (optional) Deep Neural Networks (link).

Week 4 (Gradients and Backprop)

Content: 

• Gradients and backprop (slides, video1, video2).

Assignment 04:

• Check slides (homework slides).

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

Week 6 (CNNs)

Content: 

• CNNs (slides, video).

Assignment 05:

• Simpsons Character Classification (link).

Practical Aspects with Pytorch:

• CNN in Pytorch and other resources (CNN, Save-Load Models, Transfer Learning and Fine Tuning, Custom Image Datasets, Data Augmentation).

Week 8 (Graph NNs and Reinforcement Learning)

Content: 

• Graph NNs (slides, video).

• Reinforcement Learning (slides, video).

Week 10 (Variational Autoencoders and Diffusion Models)

Content: 

• Variational Autoencoders (slides, video).

• Diffusion Models (slides, video).