Neural Networks and Deep Learning
IMPORTANT NOTICE:
This course will start on January 10, 2023, 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.
Registration
To attend the lectures and receive notifications about any change on course lectures,
please register in this file by January 5th.
This course 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
- Introduction to neural computing
- Hopfield networks
- Unsupervised learning: PCA
- Unsupervised learning: Kohonen networks
- Clustering algorithms
- Reinforcement learning
- Supervised learning - part 1
- Supervised learning - part 2
- Radial Basis Function Networks
- Towards Deep Neural Networks (DNNs)
- Autoencoders
- Convolutional Neural Networks
- DNNs for object classification
- DNNs for object detection
- DNNs for image segmentation
- Recurrent Neural Networks
- Deep Reinforcement Learning
- Sample applications and open issues
Part II: Advanced Topics
- Generative Adversarial Networks (GANs)
- Capsule Networks
- Anchor-free dectection networks
- Deformable convolutions
- Model compression
- Semi-supervised learning
- Contrastive learning
- Towards trustworthy AI
- Adversarial attacks and defenses
- Explainable AI
- Natural Language Processing
- Transformers
- Models for real-time tracking
Part III: Implementation Issues
- Implementing neural networks in C
- Implementing Reinforcement Learning in C
- Implementing Backpropagation in C
- Frameworks for deep learning: Keras and Caffe
- Frameworks for deep learning: Tensorflow and Pytorch
- Functional components in autonomous driving
- The Apollo framework for Autonomous Driving
- Simulation environments for neural control
- Visual tracking with drones
- DNN optimization for embedded platforms
- Accelerating deep networks on GPGPUs
- GPU-based real-time neural vision
- Accelerating deep networks on FPGA
- Design and optimization of DNNs accelerators on FPGA
Projects
- Projects rules
- Projects list (to be published soon)
- Project availability (to be published soon)
Suggested readings
Books
- Ian Goodfellow, Yoshua Bengio, Aaron Courville. Deep Learning, MIT Press, 2017.
- François Chollet. Deep Learning with Python, Manning, 2017.
- Richard S. Sutton and Andrew G. Barto. Reinforcement Learning: An Introduction, Second edition, The MIT Press, 2018.
Introductory readings
For those who like to look into the future