Deep Learning
with code in Python
Course Description
This is a graduate computer science course that aim to introduce the use of deep learning in Python. In this course, we focus on both theoritical concepts and practical use of different deep learning models.
Course outline:
[pdf] Lecture#01: Introduction and course overview
[pdf] Lecture#02: Blocks of neural networks
[pdf] Lecture#03: Convolutional neural networks
[pdf] Lecture#04: Recurrent neural networks
[pdf] Lecture#05: Hands on project
[pdf] Lecture#06: Modern training techniques
[pdf] Lecture#07: Common network architecture design
[pdf] Lecture#08: Autoencoding and self-supervision
[pdf] Lecture#09: Object detection
[pdf] Lecture#10: Generative adversarial networks
[pdf] Lecture#11: Attention mechanisms
[pdf] Lecture#12: Sequence-to-sequence
[pdf] Lecture#13: Project discussion
[pdf] Lecture#14: Revision and open discussion
[pdf] Lecture#02: Blocks of neural networks
[pdf] Lecture#03: Convolutional neural networks
[pdf] Lecture#04: Recurrent neural networks
[pdf] Lecture#05: Hands on project
[pdf] Lecture#06: Modern training techniques
[pdf] Lecture#07: Common network architecture design
[pdf] Lecture#08: Autoencoding and self-supervision
[pdf] Lecture#09: Object detection
[pdf] Lecture#10: Generative adversarial networks
[pdf] Lecture#11: Attention mechanisms
[pdf] Lecture#12: Sequence-to-sequence
[pdf] Lecture#13: Project discussion
[pdf] Lecture#14: Revision and open discussion
Labs (showcases)
- [Notebook] CNN showcase
- [Notebook] RNN showcase
Final examination (sample questions)
[pdf] MCQ questions
Reference Books
- Francois Chollet (2021), Deep Learning with Python, Second Edition, Manning.
- Edward Raff (2022), Inside Deep Learning: Math, Algorithms, Models, Manning.
- Andreas C. Mueller and Sarah Guido (2016), Introduction to Machine Learning with Python: A Guide for Data Scientists, O'Reilly Media
Instructor
Essam Rashed, Ph.D.