Module code: MTH767P
Credits: 15.0
Semester: SEM2
Contact: Dr Masanori Hanada
Prerequisite: Before taking this module you must take MTH786P
This module introduces you to several state-of-the-art methodologies for machine learning with neural networks (NNs). After discussing the basic theory of constructing and calibrating NNs, we consider various types of NN suitable for different purposes, such as recurrent NNs, autoencoders and transformers. This module includes a wide range of practical applications; you will implement each type of network using Python (and PyTorch) for your weekly coursework assignments, and will calibrate these networks to real datasets.
Connected course(s): UDF DATA
Assessment: 50.0% Examination, 50.0% Practical
Level: 7
