Postgraduate Programme and Module Handbook 2025-2026
Module ENGI48915: Deep Learning for Engineering
Department: Engineering
ENGI48915: Deep Learning for Engineering
Type | Open | Level | 4 | Credits | 15 | Availability | Available in 2025/2026 | Module Cap |
---|
Prerequisites
- None
Corequisites
- As stated in programme regulations.
Excluded Combination of Modules
- As stated in programme regulations.
Aims
- This module is designed solely for students studying Department of Engineering or MISCADA degree programmes.
- To provide a comprehensive understanding of deep learning techniques and their applications in engineering.
- To equip students with the knowledge and skills to design, implement, and evaluate deep learning models for engineering problems.
- To explore the integration of deep learning with engineering methods and domain knowledge.
- To foster critical thinking about the implications and limitations of deep learning in engineering contexts.
Content
- Fundamentals of deep learning architectures and their applications in engineering.
- Advanced deep learning techniques for engineering problems, integrating e.g. physical models, simulations, discovery, and domain knowledge in engineering.
- Practical aspects of implementing, deploying, and scaling deep learning models in real-world engineering systems.
Learning Outcomes
Subject-specific Knowledge:
- A comprehensive understanding of deep learning principles and architectures relevant to engineering applications.
- Knowledge of how deep learning can be integrated with physical models and engineering domain knowledge.
Subject-specific Skills:
- Ability to design and implement deep learning models for various engineering tasks.
- Proficiency in using deep learning frameworks and tools for engineering applications.
- Skills in data preparation, model training, and performance evaluation in engineering contexts.
Key Skills:
- Advanced problem-solving skills in applying deep learning to complex engineering challenges.
- Capacity for independent learning and critical thinking in the rapidly evolving field of AI in engineering.
- Ability to communicate complex technical concepts related to deep learning in engineering effectively.
Modes of Teaching, Learning and Assessment and how these contribute to the learning outcomes of the module
- The Deep Learning for Engineering module is covered in lectures and reinforced by practical programming exercises and case studies.
- Two-hour sessions delivered in a single term.
- Students are encouraged to make use of staff 'Surgeries' (otherwise "Office Hours") to discuss any aspect of the module with teaching staff on a one-to-one basis. These are sign-up sessions available for up to one hour per week.
- Coursework (code and report) is appropriate as a mode of assessment for this module because it allows students to work on realistic engineering problems.
Teaching Methods and Learning Hours
Activity | Number | Frequency | Duration | Total/Hours | |
---|---|---|---|---|---|
Lectures | 10 | Weekly (over one term) | 2 | 20 | |
Revision Classes | 1 | 1 | 1 | ||
Surgeries | 10 | As required, weekly sign-ups available throughout the teaching term | Optional attendance as required | 5 | |
Independent Study | 1 | 50 | |||
Preparation and Reading | 1 | 74 | |||
Total | 150 |
Summative Assessment
Component: Coursework | Component Weighting: 100% | ||
---|---|---|---|
Element | Length / duration | Element Weighting | Resit Opportunity |
Portfolio | 100% | Y |
Formative Assessment:
■ 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