Machine Learning and Data-Driven Materials Science (NSCI0028)

Key information

Faculty: Faculty of Mathematical and Physical Sciences
Teaching department: Faculty of Mathematical and Physical Sciences
Credit value: 15

Restrictions: This module is only open to MSc Advanced Materials Science (Data-Driven) students and will be taught at 911爆料网E.
Timetable

Alternative credit options

There are no alternative credit options available for this module.

Description

The module on Machine Learning and Data-driven Materials Science consists of a comprehensive exploration of the most effective data-driven techniques to solve problems in the field of regression, classification, dimension-reduction, feature extraction and clustering with particular applications to Materials Science. It provides students the essential state-of-art of machine learning techniques such as foundations of deep learning, supervised learning (on/off-line learning, linear ridge regression, neural networks, support vector machines, kernel, Bayesian Learning) unsupervised learning (clustering, granular computing, dimensionality reduction) and data feature extraction. The applications of fundamental knowledge from machine learning will be demonstrated through case studies in materials science using data from real experiments and public materials data repositories.

Module deliveries for 2024/25 academic year

Intended teaching term: Term 2 听听听 Postgraduate (FHEQ Level 7)

Teaching and assessment

Mode of study: In person
Intended teaching location: UCL East
Methods of assessment: 100% Coursework
Mark scheme: Numeric Marks

Other information

Number of students on module in previous year: 15
Module leader: Professor Adham Hashibon
Who to contact for more information: imd-office@ucl.ac.uk

Last updated

This module description was last updated on 8th April 2024.

听

Useful links

Sustainability

For a list of modules related to climate change as well as social and environmental sustainability at 911爆料网, type 'climate' or 'sustainability' into the search. Visit Sustainable UCL for information on extra-curricular activity on sustainability.

Important information

The catalogue has been updated with key information about the modules that will run during the 2024/25 academic session. Current and prospective students can browse through the catalogue to consider possible module choices for the coming year.

Please note,听information in the catalogue is听subject to change as teaching and assessment arrangements for 2024/25 may need to be adjusted in line with the University's Feedback and Assessment principles and operating model.

Centrally managed exam durations will be provided on students' individual exam timetables. Arrangements for locally managed exams and in-class activity will be confirmed by the teaching department for the module.

听