In the last decade due to the availability of cheap computational power and relevant software tools, several neural networks are explored to advance state-of-the-art of
many hard AI problems. These architectures have successfully advanced various areas such as image searching,
natural language understanding, medical applications,
autonomous vehicles etc. All these problems rely on efficient, accurate and robust
solutions for basic vision tasks such as image classification, localization and
detection. In this course students will be given an exposure to the details of neural networks as well as deep learning architectures and to develop end-to-end
models for such tasks. Students will learn to implement, train and debug their own neural networks. This is a project oriented practical course in which every student
has to develop a complete working model to solve some real-world problem.
This course has no prerequisites.
| Title | Author(s) | Edition |
|---|---|---|
| Deep Learning | Ian Goodfellow, Yoshua Bengio & Aaron Courville | (2016) |
| Dive into Deep Learning | Aston Zhang, Zachary C. Lipton, Mu Li, and Alexander J. Smola | (2020) |