Deep Learning II is an advanced course that builds upon the concepts introduced in Deep Learning I. It delves deeper into specialized topics and advanced applications of deep learning. Topics include: (1) Advanced Neural Network Architectures: Exploring advanced architectures such as GANs (Generative Adversarial Networks), LSTMs (Long Short-Term Memory networks), and Transformers; (2) Transfer Learning: Understanding transfer learning and its application in fine-tuning pre-trained models; (4) Deep Learning for Structured Data: Applying deep learning to structured data, such as tabular data; (5) Ethical Considerations: Discussion of ethical issues and bias in deep learning.
Learning Outcomes
By the end of the module students should be able to:
Obtain knowledge in advanced deep learning techniques and architectures.
Implement the advanced deep learning techniques using the popular deep learning libraries.
Apply advanced deep learning to complex real world problems in areas like Computer Vision, and Pattern Recognition.
Understand various ethical issues in deep learning techniques and AI.