Studying at York
Machine Learning - ELE00144M
- Department: Electronic Engineering
- Credit value: 20 credits
- Credit level: M
- Academic year of delivery: 2023-24
- See module specification for other years: 2024-25
Module summary
Artificial Intelligence and Machine Learning is one of the most important and influential research field of the modern world. This module introduces you to the theory of a range of biologically inspired machine learning and computational intelligence methods for processing information. This module will introduce the theory of a range of machine learning and computational intelligence methods including Artificial Neural Networks, supervised and unsupervised learning algorithms, swarm intelligence principles, and probabilistic inference. You will develop practical skills in relevant software tools and systems, and explore their application through real-world practical examples. The implications for information searching and management, robotics, and major international networks are enormous. You will understand how perceptions work, and gain experience in the structure and operation of a wide variety of techniques in machine learning.
Module will run
| Occurrence | Teaching period |
|---|---|
| A | Semester 2 2023-24 |
Module aims
Subject content aims:
-
Introduce the fields and theory behind of Neural Networks, supervised and unsupervised learning algorithms, swarm intelligence principles, and probabilistic inference
-
Explain the implementation and use of machine learning and computational intelligence methods in practical applications
Graduate skills aims:
-
Understand the different types of neural network technologies, machine learning methodologies, and application areas
-
Develop practical skills in relevant software tools and systems
-
Application through real-world practical examples
Module learning outcomes
Subject content learning outcomes:
After successful completion of this module, students will:
-
Be able to discuss the principles of contemporary machine learning technologies including reinforcement learning, supervised and unsupervised learning methods, and probabilistic learning
-
Be able to explain the structure and function of a neural computing unit and types of artificial neural networks including Perceptron, Multilayer perceptron, Deep, Associative, Hebbian, Competitive and Boltzmann networks, and basic Spiking Neural Networks
-
Be able to describe the range of learning rules applied to these networks, including: Widrow-Hoff, Back-propagation, Hebbian, Oja, Sanger, Competitive, Kohonen and Boltzmann rules, and be able to calculate and use the Widrow-Hoff delta rule for Perceptron networks and the Hopfield energy function for associative networks
-
Be able to explain probabilistic learning and inference systems based on probabilistic models and Bayesian networks, including swarm intelligence algorithms, naive Bayes inference, Kalman filters, and Hidden Markov Models
-
Be able to implement machine learning systems to accomplish basic tasks
Graduate skills learning outcomes:
After successful completion of this module, students will be able to:
-
Communicate understanding and design choices through written content.
-
Implement and apply a range of machine learning algorithms
-
Apply theoretical knowledge to solve problems.
-
Use relevant software tools and systems
-
Perform problem solving and inference using tools and systems applied to real-world problems/applications
Module content
-
Introduction to machine learning methods including neural, statistical, and swarm intelligent methodologies
-
Supervised learning systems, e.g. neural networks, decision trees, genetic programming
-
Unsupervised learning systems. e.g. K-means, autoencoders and other clustering approaches
-
Reinforcement learning including Q-learning and reward-based mechanisms
-
Probabilistic learning including Bayesian networks, Kalman filters, and Hidden Markov Models
-
Future methods
Indicative assessment
| Task | % of module mark |
|---|---|
| Essay/coursework | 100 |
Special assessment rules
None
Indicative reassessment
| Task | % of module mark |
|---|---|
| Essay/coursework | 100 |
Module feedback
'Feedback’ at a university level can be understood as any part of the learning process which is designed to guide your progress through your degree programme. We aim to help you reflect on your own learning and help you feel more clear about your progress through clarifying what is expected of you in both formative and summative assessments. A comprehensive guide to feedback and to forms of feedback is available in the Guide to Assessment Standards, Marking and Feedback.
The School of PET aims to provide some form of feedback on all formative and summative assessments that are carried out during the degree programme. In general, feedback on any written work/assignments undertaken will be sufficient so as to indicate the nature of the changes needed in order to improve the work. The School will endeavour to return all exam feedback within the timescale set out in the University's Policy on Assessment Feedback Turnaround Time. The School would normally expect to adhere to the times given, however, it is possible that exceptional circumstances may delay feedback. The School will endeavour to keep such delays to a minimum. Please note that any marks released are subject to ratification by the Board of Examiners and Senate. Meetings at the start/end of each term provide you with an opportunity to discuss and reflect with your supervisor on your overall performance to date.
Indicative reading
TBC