Neural Networks and Deep Learning


IMPORTANT NOTICE:
This course will start on January 10, 2023.

Registration

To attend the lectures and receive notifications about any change on course lectures, please register in this file.


This course (9 CFUs) includes three modules of 3 CFUs each: the first module focuses on the theoretical foundations of neural networks and deep learning; the second module covers more advanced topics and recent research trends; the third module covers practical and implementation issues.

Course Program


Part I: Theoretical Foundations

  1. Introduction to neural computing
  2. Hopfield networks
  3. Unsupervised learning
  4. Culstering algorithms
  5. Reinforcement learning
  6. Supervised learning - part 1
  7. Supervised learning - part 2
  8. Radial Basis Function Networks
  9. Towards Deep Neural Networks (DNNs)
  10. Autoencoders
  11. Convolutional Neural Networks
  12. DNNs for object classification
  13. DNNs for object detection
  14. DNNs for image segmentation
  15. Recurrent Neural Networks
  16. Deep Reinforcement Learning
  17. Sample applications and open issues

Part II: Advanced Topics

  1. Generative Adversarial Networks (GANs)
  2. Invariance and equivariance properties
  3. Capsule Networks
  4. Model compression
  5. Semi-supervised learning
  6. Contrastive learning
  7. Deep Clustering
  8. Anchor-free dectection networks
  9. Deformable convolutions
  10. Neural networks for real-time tracking
  11. Adversarial examples
  12. Towards trustoworty AI
  13. Explainable AI
  14. Natural Language Processing
  15. Transformers

Part III: Implementation Issues

  1. Implementing Hopfield networks in C
  2. Implementing Kohonen networks in C
  3. Implementing Reinforcement Learning in C
  4. Implementing Backpropagation in C
  5. Frameworks for deep learning: Keras and Caffe
  6. Frameworks for deep learning: Tensorflow
  7. Overview of the Apollo framework for Autonomous Driving
  8. Networks in Apollo: Perception Module
  9. Introduction to Adversarial Attacks and Defenses
  10. Explainable and Trustworthy AI for safety-critical systems
  11. Introduction to Transformers in Natural Language Processing
  12. Attention mechanisms in computer vision
  13. Implementing DNNs on GPUs platforms
  14. Design and optimization of DNNs accelerators on FPGA

Projects


Suggested readings

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