Objectives:
There have been many recent advances in the field of deep learning. The objective of the course is to provide exposure to these advances and facilitate in depth discussions on chosen topics. The course requires that students have done the deep learning course.
Course contents:
- Recent Advances in Generative Adversarial Networks (GANs)
- Recent Advances in Variational Autoencoders and extensions
- Advanced Convolutional Neural Networks
- Advanced architectures for Deep Neural Networks
- Advanced Optimization methods for Deep Neural Networks
- Recent Advances in Sequence Modelling Using Deep Neural Networks
- Model Compression techniques for Deep Neural Networks
- Recent Advances in Hierarchical and Multimodal Attention Mechanisms
- Recent Advances in Memory Augmented Architectures for Deep Neural Networks
- Recent Advances in Deep Generative Models
- Recent Advances in Deep Learning
- Recent Applications of Deep Learning (case studies)
Text Books:
Ian Goodfellow and Yoshua Bengio and Aaron Courville (2016) Deep Learning
Book.
References:
Various research papers.
