Skip to main content

CS331 Neural Computing

CS331 15 CATS (7.5 ECTS) Term 2

Availability

Option - CS, CSE, CBS and DM

Prerequisites

CS131 Mathematics for Computer Scientists II or equivalent

Academic Aims

This module provides an introduction to the theory and implementation of neural networks, both biological and artificial. It aims to give students sufficient knowledge to enable employment or postgraduate study involving neural networks.

Learning Outcomes

Students completing the module should be able to demonstrate:

  • an understanding of the principles of Neural Networks and a knowledge of their main areas of application;
  • the ability to design, implement and analyse the behaviour of simple neural networks.

Content

  • Introduction: history of neural computing; relationship to Artificial Intelligence.
  • Neurons: structure and behaviour of biological neurons; simple models of neurons; nonlinear and dynamical models.
  • Networks of Neurons: how neuronal networks are arranged in the brain; common architectures for artificial networks.
  • Coding and Representation: how information is represented in neural networks; place coding; distributed representations.
  • Learning and Memory: plasticity in biological neurons; theories of memory; learning in artificial networks.
  • Vision: structure of the human visual system; function of the retina, LGN and cortical processing; artificial network models for vision.

Books

  • Haykin S, Neural Networks: a Comprehensive Foundation, Macmillan, 2009.
  • Schalkoff R J, Artificial Neural Networks, New York, McGraw-Hill, 1997.

Assessment

Three-hour examination (80%) Assessed work (20%)

Teaching

30 one-hour lectures plus 5 revision classes