Course Code |
Course Title |
Weekly Hours* |
ECTS |
Weekly Class Schedule |
T |
P |
AID401 |
Deep Learning |
3 |
2 |
6 |
|
Prerequisite |
None |
It is a prerequisite to |
|
Lecturer |
|
Office Hours / Room / Phone |
|
E-mail |
|
Assistant |
|
Assistant E-mail |
|
Course Objectives |
1. To learn the basics of deep learning, including the key concepts, terminology, and tools.
2. To gain hands-on experience in building and training deep neural networks using Keras and TensorFlow, two popular deep learning frameworks.
3. To explore various types of deep neural networks, such as convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and transformers.
4. To apply deep learning techniques to various domains such as computer vision, natural language processing, speech recognition, and reinforcement learning.
5. To understand the current challenges and limitations of deep learning and how to overcome them.
|
Textbook |
Required textbooks for this course are:
[1] Chollet, F. (2017). Deep learning with Python. Manning Publications Co.
[2] Géron, A. (2019). Hands-on machine learning with Scikit-Learn, Keras, and TensorFlow: Concepts, tools, and techniques to build intelligent systems. O’Reilly Media, Inc.
|
Additional Literature |
- Recommended textbooks for this course are:
- [1] Goodfellow, I., Bengio, Y., & Courville, A. (2016). Deep learning. MIT Press.
- [2] Raschka, S., & Mirjalili, V. (2019). Python machine learning: Machine learning and deep learning with Python, scikit-learn, and TensorFlow 2. Packt Publishing.
|
Learning Outcomes |
After successful completion of the course, the student will be able to: |
- 1. Explain the main components and operations of a deep neural network, such as layers, activation functions, loss functions, optimizers, and regularization techniques.
- 2. Implement basic deep neural networks using Keras and TensorFlow and train them on various datasets.
- 3. Compare and contrast different types of deep neural networks, such as CNNs, RNNs, GANs, and transformers, and understand their advantages and disadvantages.
- 4. Apply deep neural networks to various tasks such as image classification, object detection, text generation, machine translation, speech recognition, and game playing.
- 5. Evaluate the performance and robustness of deep neural networks and troubleshoot common issues such as over
|
Teaching Methods |
There will be a 1 hour of theory and explaining the background of the topic, then we will continue with the programming and practice |
Teaching Method Delivery |
Face-to-face |
Teaching Method Delivery Notes |
|
WEEK |
TOPIC |
REFERENCE |
Week 1 |
Introduction to Deep Learning and Keras |
DLP: Ch. 1; HML: Ch. 10 & 11 |
Week 2 |
Neural Networks Basics and TensorFlow Assignment 1: Neural Networks with Keras and TensorFlow |
DLP: Ch. 2; HML: Ch. 12 & 13 |
Week 3 |
Convolutional Neural Networks for Computer Vision |
DLP: Ch. 5; HML: Ch. 14 & 15 |
Week 4 |
Recurrent Neural Networks for Natural Language Processing Assignment 2: Image Classification with CNNs |
DLP: Ch. 6; HML: Ch. 16 & 17 |
Week 5 |
Generative Adversarial Networks for Image Generation |
DLP: Ch. 8; HML: Ch. 18 & 19 |
Week 6 |
Transformers for Sequence Modeling and Attention Mechanisms Assignment 3: Text Generation with RNNs |
DLP: Ch. 11; HML: Ch. 20 & 21 & Appendix A & B & C |
Week 7 |
Midterm exam |
|
Week 8 |
Machine Learning for Cybersecurity |
Hands-on |
Week 9 |
Reinforcement Learning and Deep Q-Networks for Game Playing Assignment 4: Image Generation with GANs |
DLP: Ch. 18; HML: Ch. 22; Appendix A |
Week 10 |
Advanced Topics in Deep Learning (I) - Self-Supervised Learning and Contrastive Learning |
DLP: Ch. 12; HML: Ch. 23; Appendix B |
Week 11 |
Advanced Topics in Deep Learning (II) - Graph Neural Networks and Geometric Deep Learning Assignment 5: Transformers for Sequence Modeling and Attention Mechanisms |
DLP: Ch. 14; HML: Ch. 24; Appendix C |
Week 12 |
Advanced Topics in Deep Learning (III) - Meta-Learning and Few-Shot Learning |
DLP: Ch. 15; HML: Ch. 25; Appendix D |
Week 13 |
Deep Reinforcement Learning |
Hands-on |
Week 14 |
Deep Learning for Computer Vision |
Hands-on |
Week 15 |
Final Project Presentations |
Final Project Report and Presentation |