Deep learning course for the Engineering in IA degree at UCU.
--
Gonzalo Chiarlone.
María Eugenia Pais.
Matias Di Martino.
The course introduces the fundamentals of neural networks and deep learnon. We will follow closely the book "Hands-On Machine Learning with Scikit-Learn and PyTorch" by Aurélien Géron. We will cover the main architectures used in deep learning, including feedforward neural networks, convolutional neural networks (CNNs), recurrent neural networks (RNNs), and transformers. The course will also address practical aspects such as model training, evaluation, and deployment. At the end of the course, you should be able to design, implement, and evaluate deep learning models for various applications.
| Week | Class | Topic | Readings | Assignment |
|---|---|---|---|---|
| 09/03 | C00 | Introduction to this course and deep learning | — | Notebook 0 |
| 16/03 | C01 | Supervised learning | Prince Ch 2 | Notebook 1 |
| 23/03 | C02 | Shallow neural networks | Prince Ch 3, Geron Ch 9 | Notebook 2 |
| 30/03 | Holiday | — | — | — |
| 06/04 | C03 | Deep neural networks | Prince Ch 4, Geron Ch 10 | Notebook 3 |
| 13/04 | C04 | Loss functions and optimizers | Prince Ch 5, 6, 7, Geron Ch 11 | Notebook 4 |
| 20/04 | C05 | Measuring performance and regularization | Prince Ch 8, 9 | Notebook 5 |
| 27/04 | C06 | Convolutional and residual networks | Prince Ch 10, 11, Geron Ch 12 | Notebook 6 |
| 04/05 | — | Midterm | — | — |
| 11/05 | C07 | Transformers and attention mechanisms | Prince Ch 12, Geron Ch 15, 16 | Notebook 7 |
| 18/05 | C08 | Generative models | Prince Ch 15, 18, Geron Ch 18 | Notebook 8 |
| 25/05 | Holiday | — | — | — |
| 01/06 | C09 | Contrastive Learning | — | Notebook 9 and Open Challenge kick off |
| 08/06 | C10 | Why does deep learning work? | Prince Ch 20 | Open Challenge |
| 15/06 | Holiday | — | — | — |
| 22/06 | C11 | Consultation Session | — | Open Challenge |
| 29/06 | - | Final exam | — | — |
- [1] "Understanding Deep Learning" by Simon J.D Prince. MIT Press, 2024.
- [2] "Hands-On Machine Learning with Scikit-Learn and PyTorch" by Aurélien Géron. O'Reilly Media, 2025.
- [3] "Deep Learning" by Ian Goodfellow, Yoshua Bengio, and Aaron Courville. MIT Press, 2016.
- Assignments: 25%
- Midterm exam: 35%
- Final exam: 40%
You are encouraged to actively participate in class discussions and complete all assignments on time. Collaboration on assignments is allowed, but each student must submit their own work. Plagiarism or cheating will result in severe penalties, including failure of the course. Regular attendance is expected, and students are responsible for any material covered in missed classes. You are also encouraged to use all AI tools available, you can use them to assist coding, writting and any creative task, but you must always own understanding, I will ask you to explain any piece of code or text you submit and you WILL FAIL THE CLASS IF YOU CAN'T EXPLAIN WHAT YOU SUBMIT.