CSC8111 : Machine Learning
CSC8111 : Machine Learning
- Offered for Year: 2024/25
- Module Leader(s): Dr Stephen McGough
- Lecturer: Professor Jaume Bacardit, Dr Wanqing Zhao
- Owning School: Computing
- Teaching Location: Newcastle City Campus
Semesters
Your programme is made up of credits, the total differs on programme to programme.
Semester 1 Credit Value: | 10 |
ECTS Credits: | 5.0 |
European Credit Transfer System | |
Pre-requisite
Modules you must have done previously to study this module
Pre Requisite Comment
Basic knowledge of python programming, statistics, linear algebra, and calculus
Co-Requisite
Modules you need to take at the same time
Co Requisite Comment
N/A
Aims
Machine Learning is concerned with the design of algorithms for recognising patterns in data. The field of pattern recognition represents the basis for a wide range of applications for automatic data analysis, such as computer vision, automatic speech recognition, or activity recognition – all based on sensor based observations of humans in their environment. The growth of “big data” means that such analysis techniques are now widely used for mining information from large amounts of data as they are collected in contemporary computing infrastructures, including clouds.
Conceptually, Pattern Recognition aims for the detection of instances of relevant classes that are typically associated with reappearing patterns in data streams. Examples of which are the automatic detection of faces in video streams, automatic transcription of spoken language, analysis of human movements, trend prediction in stock market data, intrusion detection in computer systems, or the analysis of social networks. The task is to find, model (or "learn") and classify those patterns, and to distinguish relevant from irrelevant events.
Machine Learning techniques represent the algorithmic foundation for such tasks, and involve both statistical modelling techniques and probabilistic reasoning approaches.
This module aims to provide a foundation in the field of Pattern Recognition and an expertise in Machine Learning techniques as a toolkit for automatically analysing (large amounts of) data – be it static data, such as images, or dynamic data, such as time series and sensor data.
Outline Of Syllabus
- Paradigms of Machine Learning
- Exploratory Data Analysis
- Experimental Design
- Standard algorithms for classification, regression and clustering
- Natural Language Processing
- Data preprocessing
- Interpretability, fairness and ethics of Machine Learning
Learning Outcomes
Intended Knowledge Outcomes
To be able to:
• Build on the algorithmic foundations of statistical pattern recognition and machine learning approaches and
their integration into practical analysis systems;
• Discern the capabilities of different modelling and analysis approaches, which allows for informed decisions
regarding the suitability of particular recognition and learning techniques;
• Exploit the potential of pattern recognition and machine learning techniques for real-world applications.
Intended Skill Outcomes
• The ability to appreciate, analyse and use the structure and algorithmic foundations of statistical pattern
recognition and machine learning systems.
• The ability to apply pattern recognition and machine learning techniques to real-world analysis problems.
Teaching Methods
Teaching Activities
Category | Activity | Number | Length | Student Hours | Comment |
---|---|---|---|---|---|
Scheduled Learning And Teaching Activities | Lecture | 12 | 1:00 | 12:00 | Lectures: Asynchronous online delivery (primarily videos) of core concepts |
Guided Independent Study | Assessment preparation and completion | 31 | 1:00 | 31:00 | Coursework |
Scheduled Learning And Teaching Activities | Practical | 16 | 1:00 | 16:00 | Practical PIP plus formative exercises |
Scheduled Learning And Teaching Activities | Small group teaching | 9 | 1:00 | 9:00 | Group problem classes to go over the lecture material. Present in person. Q&A |
Guided Independent Study | Independent study | 20 | 1:00 | 20:00 | Lecture follow up |
Guided Independent Study | Independent study | 12 | 1:00 | 12:00 | Background Reading |
Total | 100:00 |
Jointly Taught With
Code | Title |
---|---|
CSC8635 | Machine Learning with Project |
Teaching Rationale And Relationship
Pre-recorded lectures provides maximum flexibility for students learning new material. In-person small group teaching classes allow students to check their understanding and gain support for the material.
The practical classes are designed to put all concepts covered in the lectures into practice through guided practical instructions and work on the module’s coursework.
Reading Lists
Assessment Methods
The format of resits will be determined by the Board of Examiners
Other Assessment
Description | Semester | When Set | Percentage | Comment |
---|---|---|---|---|
Report | 1 | M | 100 | Extended technical Report. 2000 words. |
Formative Assessments
Formative Assessment is an assessment which develops your skills in being assessed, allows for you to receive feedback, and prepares you for being assessed. However, it does not count to your final mark.
Description | Semester | When Set | Comment |
---|---|---|---|
Prob solv exercises | 1 | M | A set of short exercises conducted during the practical sessions. |
Assessment Rationale And Relationship
The summative coursework is through an individual deliverable (Report/code), emphasising both the conceptual and applied nature of the module. Students will work on a small set of practical tasks, where they will set up and evaluate machine learning solutions that fulfils certain specified criteria.
Through the module students will complete a set of short exercises (formative assessment) conducted during the practical sessions. The student will be assessed on their understanding of machine learning as well as data processing skills, and the use of standard tools.
Timetable
- Timetable Website: www.ncl.ac.uk/timetable/
- CSC8111's Timetable
Past Exam Papers
- Exam Papers Online : www.ncl.ac.uk/exam.papers/
- CSC8111's past Exam Papers
General Notes
N/A
Welcome to Newcastle University Module Catalogue
This is where you will be able to find all key information about modules on your programme of study. It will help you make an informed decision on the options available to you within your programme.
You may have some queries about the modules available to you. Your school office will be able to signpost you to someone who will support you with any queries.
Disclaimer
The information contained within the Module Catalogue relates to the 2024 academic year.
In accordance with University Terms and Conditions, the University makes all reasonable efforts to deliver the modules as described.
Modules may be amended on an annual basis to take account of changing staff expertise, developments in the discipline, the requirements of external bodies and partners, and student feedback. Module information for the 2025/26 entry will be published here in early-April 2025. Queries about information in the Module Catalogue should in the first instance be addressed to your School Office.