Program Overview

Deep Learning for Robotics and Artificial Intelligence (COMP0220)

Key Information

Faculty and Teaching Department

The module is part of the Faculty of Engineering Sciences, with the Computer Science department being the teaching department.

Credit Value and Restrictions

• The credit value for this module is 15.
• Module delivery for UG (FHEQ Level 6) is available on MEng Robotics and Artificial Intelligence.

Alternative Credit Options

There are no alternative credit options available for this module.

Description

Aims

The aims of this module are to:

• Provide the foundations of deep learning necessary for the successful completion of this degree.
• Support students in developing a breadth of knowledge and understanding in the fundamentals of deep learning concepts and algorithms.

Intended Learning Outcomes

On successful completion of the module, a student will be able to:

1. Understand basic concepts of deep learning.
2. Develop a systematic approach to developing and analyzing deep learning algorithms.
3. Evaluate the quality and suitability of different deep learning methods for different scenarios.
4. Identify and interpret properties of deep learning algorithms.

Indicative Content

The module will typically cover:

• Feedforward neural networks.
• Backpropagation.
• Convolutional neural networks.
• RNNs and LSTMs.
• Geometric deep learning (e.g., graph neural networks).
• Attention mechanism.
• Meta learning (e.g., MAML).
• Neural architecture search.
• Transformers.

Requisite Conditions

To be eligible to select this module as optional or elective, a student must be registered on a programme and year of study for which it is formally available.

Module Deliveries for 2026/27 Academic Year

Intended Teaching Term

The intended teaching term for this module is Term 1, Undergraduate (FHEQ Level 6).

Teaching and Assessment

Mode of Study

The mode of study for this module is in person.

Intended Teaching Location

The intended teaching location is UCL East.

Methods of Assessment

The methods of assessment include:

• 50% In-class activity (2 assessments).
• 50% Group activity.

Mark Scheme

The mark scheme uses numeric marks.

Other Information

Number of Students on Module in Previous Year

There were 49 students on this module in the previous year.

Module Leader

The module leader is Dr. Zezhi Tang.