Module COMP3547: DEEP LEARNING

Department: Computer Science

COMP3547: DEEP LEARNING

Prerequisites

• (COMP2261 Artificial Intelligence AND COMP2271 Data Science)

Corequisites

• None

Excluded Combination of Modules

• None

Aims

• To enable students to be able to approach complex ill-defined problems that require deep layers of learning, and understand how this relates to learning in nature.
• To equip students with the ability to use modern deep learning libraries in order to effectively design, train, and test neural networks in different applications.

Content

• Foundations of deep learning and learning in nature
• PyTorch programming
• Designing deep neural network architectures
• Adversarial models
• Energy-based models and Flow models
• Sequential models and Transformers
• Implicit representations
• Generalisation theory
• Meta and manifold learning

Learning Outcomes

• On completion of the module, students will be able to demonstrate:
• an understanding of state-of-the-art deep neural network architectures and neural network architecture components.
• an understanding of statistical learning theory with deep learning approaches.
• an understanding of the algorithms and approaches to design and evaluate deep neural networks.

• On completion of the module, students will be able to demonstrate:
• an ability to use modern deep learning libraries to design, train, validate and test deep neural networks.
• an ability to design neural networks with respect to the task or dataset.
• an ability to identify inherent issues in dataset bias prior to training or architecture design.

• On completion of the module, students will be able to demonstrate:
• the scientific approach to design, training, validation, and testing of deep neural networks in a broad range of applications.
• an ability to learn, understand, and visualise the underlying structure of datasets.
• an ability to design and implement state-of-the-art generative models and bespoke deep neural network architectures.

Modes of Teaching, Learning and Assessment and how these contribute to the learning outcomes of the module

• Lectures enable the students to learn new material relevant to deep learning, manifold learning and meta learning as well as their applications.
• Practicals enable students to acquire necessary coding skills, learn about the relevant libraries and packages and receive feedback on their work.
• Summative assessments assess the knowledge of deep learning libraries and application of methods and techniques.

Teaching Methods and Learning Hours

Summative Assessment

Formative Assessment:

Example formative exercises are given during the course. The first few lab practicals are specifically dedicated to formative assignments aimed at familiarising students with state-of-the-art deep learning packages and libraries. Feedback will be provided to the students on the summative assignments and lecture materials during the practicals. Additional revision lectures may be arranged in the module's lecture slots in the 3rd term.

■ Attendance at all activities marked with this symbol will be monitored. Students who fail to attend these activities, or to complete the summative or formative assessment specified above, will be subject to the procedures defined in the University's General Regulation V, and may be required to leave the University