Deep Learning techniques belong to the machine learning paradigm. In this course, students will gain insight into the Deep learning algorithms, how they work, their strengths, challenges that lie ahead of them and when to apply them. We will investigate various Deep Learning models from the supervised and unsupervised learning domain. We will examine various existing pipelines used for handling real-world applications. The focus will be on Artificial Neural Networks (ANN), Convolution Neural Networks (CNN), and various generative models.
Computer Science - 144 CRs
Ian Goodfellow and Yoshua Bengio (2016), Deep Learning, MIT Press.
content serial | Description |
---|
1 | Why go deep? |
2 | ANN |
3 | CNNs for classification |
4 | CNNs for semantic segmentation |
5 | Recurrent Neural Networks |
6 | Hyper-parameters |
7 | 7-th week exam |
8 | Restricted Boltzmann machines |
9 | Autoencoders |
10 | Basics of GANs |
11 | Performance measures |
12 | 12-th week exam |
13 | Deep models and reinforcement learning |
14 | Explainable AI basics |
15 | Revision |
16 | Final exam |
Start your application