Neural Networks and Deep Learning
IMPORTANT NOTICE:
This course will start on January 7, 2025, at 9:00.
Lectures will be opened to everybody and will be given online on the following channel.
Please, connect 10 minutes before 9:00 to avoid disturbing the lecture.
 IMPORTANT NOTICE:
Please look at the new schedule, since some dates have been changed.

Registration

 To access the channel of the lectures and receive notifications about any change on course lectures, please register here by December 15th.

Certification of attendance

 If you need a certification of attendance, be aware that the number of hours that will be certified are those recorded by Teams.

Course Program and Lectures Schedule

 This course includes four modules:
  1. The first module (20 hours) focuses on the theoretical foundations of neural networks.
  2. The second module (20 hours) focuses on deep neural networks.
  3. The third module (20 hours) covers more advanced topics and recent research trends.
  4. The fourth module (30 hours) covers practical and implementation issues.

Part I: Theoretical Foundations

  1. Introduction to neural computing
  2. Hopfield networks
  3. Unsupervised learning: PCA
  4. Unsupervised learning: Self-Organizing Maps
  5. Clustering algorithms - part 1
  6. Clustering algorithms - part 2
  7. Reinforcement learning - part 1
  8. Reinforcement learning - part 2
  9. Reinforcement learning - part 3
  10. Supervised learning: The Perceptron
  11. Supervised learning: Backpropagation
  12. Supervised learning: Performance metrics
  13. Radial Basis Function Networks

Part II: Deep Learning
  1. Towards Deep Neural Networks (DNNs)
  2. Autoencoders
  3. Convolutional Neural Networks
  4. CNNs for object classification
  5. CNNs for object detection
  6. CNNs for image segmentation
  7. Deformable Convolutions
  8. Recurrent Neural Networks - part 1
  9. Recurrent Neural Networks - part 2
  10. Transformers

Part III: Advanced Topics
  1. Deep reinforcement learning - part 1
  2. Deep reinforcement learning - part 2
  3. Generative networks
  4. Semi-supervised learning
  5. Adversarial attacks and defenses
  6. Real-world adversarial attacks
  7. Explainable and interpretable AI
  8. Anomaly detection and out-of-distribution generalization
  9. Domain generalization and domain adaptation
  10. Attention mechanisms in computer vision

Part IV: Implementation Issues
  1. Implementing neural networks in C: Self Organizing Maps
  2. Implementing neural networks in C: Q-learning
  3. Implementing neural networks in C: Backpropagation
  4. Programming frameworks for deep learning      Examples
  5. Modeling DNNs in Tensorflow and PyTorch      Examples
  6. Functional components in autonomous driving
  7. The Apollo framework for autonomous driving
  8. Accelerating deep networks on FPGA
  9. Simulators for autonomous driving
  10. GPU programming in CUDA
  11. DNN optimization for embedded platforms
  12. The NVIDIA TensorRT framework
  13. Accelerating deep networks on embedded GPU platforms - part1
  14. Accelerating deep networks on embedded GPU platforms - part2
  15. The Xilinx Deep Processing Unit

Exam

 The exam (for those that need to take it) consists in a project development. The project is one, independently on the number of modules attended, but the number of hours that will be certified are those recorded by Teams. The completion of the exam requires the project discussion and the delivery of the project code, including a report describing the work done. Please, read carefully the project rules in the link below.

Videos
  1. Hopfield network demo
  2. Kohonen network demo 1: 2D input space
  3. Kohonen network demo 2: image mapping
  4. Kohonen network demo 3: optimization
  5. K-means online demo
  6. Gaussian mix demo
  7. Q-learning: The amoeba
  8. Q-learning: cart-pole demo
  9. Q-learning: grid world demo
  10. Q-learning: crossroads demo
  11. Q-learning: shooting moving targets
  12. Q-learning: target camera tracking
  13. Q-learning: car driving demo
  14. Supervised learning: function approximator
  15. Supervised learning: overfitting example
  16. Supervised learning: simple classifier
  17. Supervised learning: character classifier
  18. Supervised learning: face classifier

Suggested readings

 Books Introductory readings For those who like to look into the future