SYST C4606 - Deep Learning

Module Title:Deep Learning
Language of Instruction:English
Credits: 5
NFQ Level:8
Module Delivered In 1 programme(s)
Teaching & Learning Strategies: This module will be delivered through a mix of lectures, laboratory assignments, and projects including a professional write-up. It will employ a mixture of active/task-based learning, reflective learning, and problem-based learning
Module Aim: Deep neural networks can inform both the contents of an image or video frame and the content's location within the image boundaries. Additionally, neural networks can manipulate images and video frames. This module investigates methods of image classification, location, and manipulation. The module also examines optimisation of the computation and storage of these neural network models' immense data to provide the student with a demonstrable understanding of the advanced neural network features.
Learning Outcomes
On successful completion of this module the learner should be able to:
LO1 Design AI modules that identify features in images.
LO2 Develop AI modules to track the movement of features in images.
LO3 Manage image manipulation within image sets, e.g., using GANs.
LO4 Improve the performance of the neural network model.
LO5 Complete a project as an individual or in a small group to design and implement a solution for a real world problem.
Pre-requisite learning
Module Recommendations

This is prior learning (or a practical skill) that is recommended before enrolment in this module.
9271 COMP C4602 Computer Vision
9655 ELEC C4602 Artificial Intelligence and Machine Learning
Incompatible Modules
These are modules which have learning outcomes that are too similar to the learning outcomes of this module.
No incompatible modules listed
Co-requisite Modules
No Co-requisite modules listed
Requirements
This is prior learning (or a practical skill) that is mandatory before enrolment in this module is allowed.
No requirements listed
 

Module Content & Assessment

Indicative Content
Image classification and localisation
Models to find the best classification accuracy and localisation of images. Localisation of objects in an image or video stream.
Semantic segmentation
Location and movement of items within a frame.
Image Manipulation
Generative variational auto-encoders, generative adversarial Networks (GANs), spectral normalisation.
Optimisation
Optimisation techniques such as pruning, activation functions, compression, and alternative number representation.
Ethics, Safety, and Trustworthiness
Algorithm and data bias, model safety and EU trustworthiness policy, GDPR considerations.
Assessment Breakdown%
Continuous Assessment20.00%
Project40.00%
Practical40.00%
Continuous Assessment
Assessment Type Assessment Description Outcome addressed % of total Assessment Date
Short Answer Questions n/a 1,2 20.00 Week 4
Project
Assessment Type Assessment Description Outcome addressed % of total Assessment Date
Project n/a 1,2,3,4,5 40.00 Sem 2 End
Practical
Assessment Type Assessment Description Outcome addressed % of total Assessment Date
Practical/Skills Evaluation n/a 1,2,3,4 40.00 Every Week
No End of Module Formal Examination

SETU Carlow Campus reserves the right to alter the nature and timings of assessment

 

Module Workload

Workload: Full Time
Workload Type Frequency Average Weekly Learner Workload
Lecture Every Week 2.00
Laboratory Every Week 3.00
Independent Learning Every Week 6.00
Total Hours 11.00
 

Module Delivered In

Programme Code Programme Semester Delivery
CW_EEROB_B Bachelor of Engineering (Honours) in Robotics and Automated Systems 8 Mandatory