ES3H3-15 Intelligent System Design
Introductory description
ES3H3-15 Intelligent System Design
Module aims
By the end of the module the student should be able to:
- Describe the typical software and hardware architectures of intelligent systems in various domains
- Apply machine learning techniques to solve real-world problems
- Apply computer vision techniques for solving problems such as face recognition and motion estimation.
Outline syllabus
This is an indicative module outline only to give an indication of the sort of topics that may be covered. Actual sessions held may differ.
Computer Vision Topics:
- Edges, corners, gradients
- Feature detectors
- Motion estimation / Tracking
- Camera model / Stereo
- Object detection
Machine Learning Topics: - Linear/Ridge/Lasso Regression
- Model fitting techniques: gradient descent, Newton's method.
- Classification: Logistic Regression, Naive Bayes, GDA
- Neural Networks: Back-propagation, shallow and deep architectures
Learning outcomes
By the end of the module, students should be able to:
- 1. Describe the typical software and hardware architectures of intelligent systems in various domains
- 2. Select, apply and evaluate machine learning techniques for solving real-world problems
- 3. Select, apply and evaluate computer vision techniques for solving problems such as face recognition and motion estimation
Indicative reading list
Lei, B., Xu, G., Feng, M., van der Heijden, F., Zou, Y., de Ridder, D. and Tax, D.M., 2017.
“Classification, parameter estimation and state estimation: an engineering approach using
MATLAB”. John Wiley & Sons.
- Murphy, Kevin P. “Machine learning: a probabilistic perspective”. MIT press, 2012. · Gomaa, Hassan. “Real-Time Software Design for Embedded Systems”. Cambridge University Press, 2016.
Subject specific skills
Systems Engineering approach, Software Engineering, Programming.
Transferable skills
Project Management, Team work, Presentations.
Study time
Type | Required | Optional |
---|---|---|
Project supervision | 2 sessions of 2 hours (3%) | |
Practical classes | 13 sessions of 2 hours (17%) | |
Online learning (independent) | (0%) | 2 sessions of 2 hours |
Private study | 120 hours (80%) | |
Total | 150 hours |
Private study description
120 hours guided independent study
Costs
No further costs have been identified for this module.
You must pass all assessment components to pass the module.
Assessment group A3
Weighting | Study time | Eligible for self-certification | |
---|---|---|---|
Lab Assessments | 60% | No | |
Programming assignments / in-class tests |
|||
Group Project | 40% | No |
Feedback on assessment
- Support through advice and feedback hours.
- Written feedback on individual projects
- Written feedback on group projects
- Cohort feedback in lectures on coursework performance
Each of the component must be passed (>=30%) in order to pass the module
Pre-requisites
To take this module, you must have passed:
Courses
This module is Core for:
- Year 3 of UESA-HH35 BEng Systems Engineering
- Year 4 of UESA-HH34 BEng Systems Engineering with Intercalated Year
-
UESA-HH31 MEng Systems Engineering
- Year 3 of HH31 Systems Engineering
- Year 3 of HH35 Systems Engineering
This module is Core optional for:
- Year 3 of UESA-H115 MEng Engineering with Intercalated Year
- Year 4 of UESA-HH32 MEng Systems Engineering with Intercalated Year
This module is Optional for:
- Year 3 of UESA-H113 BEng Engineering
- Year 3 of UESA-H114 MEng Engineering
- Year 4 of UESA-H115 MEng Engineering with Intercalated Year
This module is Option list A for:
- Year 4 of UESA-H111 BEng Engineering with Intercalated Year
- Year 3 of UESA-H112 BSc Engineering
This module is Option list B for:
- Year 3 of UCSA-G406 Undergraduate Computer Systems Engineering
- Year 3 of UCSA-G408 Undergraduate Computer Systems Engineering
- Year 4 of UCSA-G407 Undergraduate Computer Systems Engineering (with Intercalated Year)
- Year 4 of UCSA-G409 Undergraduate Computer Systems Engineering (with Intercalated Year)