| | The module is a deep dive into the details of deep learning architectures with a focus on learning end-to-end models for signal processing (e.g. time series, images, audio, text, etc).
The module will present some of the basics of deep neural networks as well as more recent ones, with their applications to various AI tasks.
Indicative Syllabus
- Neural Networks Architectures (e.g. CNNs, Transformers, GNNs)
- Neural Networks Optimization (e.g. Backpropagation)
- Transfer Learning, contrastive learning, and fine-tuning performance
- Limits and issues with deep learning
- Use of standard frameworks for deep learning (e.g. Pytorch, TensorFlow, deep graph library)
By the end of the module, it is expected that students will have significant familiarity with the subject and be able to apply Deep Learning to a variety of tasks (e.g. robotics, computer vision, etc.). |
DEEP LEARNING 
