MSc in Information Processing and Neural Networks -- Neural Computing

King's College London MSc in Information Processing and Neural Networks
(updated 10 Sept 2002 by PKS)

Departmental enrolment is on Thu 19 Sept 2002

The programme for the day is available in Postscript or PDF format.

Note: College enrolment is separate and will take place on Mon 16 Sept 2002. You should have received the relevant information from the School Office for Physical Sciences and Engineering; if you haven't, contact them directly.

Introduction

There have been numerous significant advances in the last twenty years in our understanding of information processing in living and artificial systems. These developments have been both at a software/hardware level and (especially since about 1990) at a theoretical/mathematical level. Students wishing to enter this rapidly expanding field after a first degree, however, will often not be adequately prepared by their undergraduate training.

The purpose of the M.Sc. programme in Information Processing and Neural Networks is to teach students

(i) the definitions and properties of the most commonly used neural information processing systems and algorithms, addressing both their potential and their restrictions.

(ii) the mathematical techniques required to analyse the operation of these systems and algorithms (e.g. Bayesian statistics, information theory, statistical mechanics).

(iii) how to use these techniques for quantifying the operation of neural information processing systems, for improving upon present ones and for designing new ones, and for making quantitative predictions on their performance and reliability.

(iv) where and how neural information processing systems are used in information technology and engineering, and how they compare to more standard approaches.

(v) how to obtain and maintain access to the most recent research results in the academic community.

Upon successfully completing this degree the student should be able to contribute to research and development in an academic, industrial or business environment. This EPSRC supported course was accepted as an MSc course of the University of London by the separate Boards of Physics, Engineering and Mathematics in 1989, and was formally approved in 1990 by the Senate of King's College London as a course leading to the award of an MSc degree in the Faculty of Science (presently: the School of Physical Sciences and Engineering, which includes the Departments of Mathematics, Physics, Engineering and Computer Science). In the 1998 subject review of the Quality Assurance Agency for Higher Education the programme was described as follows: `The MSc in Information Processing and Neural Networks is a well designed, innovative research led programme which includes a substantial project. It is highly praised by students, external examiners and employers.'

A succesful study will lead to one of the following awards: pass, pass with merit, or pass with distinction. The detailed criteria to be met in order to obtain these awards are found by following the link `awards' below. The full programme regulations can be downloaded in postscript or PDF format.

Programme Structure 2001/2002

The MSc programme is based on course work and a project and requires either one year of full-time study, or may be taken part-time over two years.

All candidates follow two core lecture courses as well as a selection of six further lecture courses , chosen in consultation with their tutor, and taken from a list of options. For a detailed description of the present programme of core and optional lecture courses follow the relevant link at the right (this list can be subject to minor changes, dependent on the availablity of lecturers in a given session).

Each candidate must complete a research project in some area of Information Processing and Neural Networks at the postgraduate level, after passing the written examinations (in the months June-August). This project can also be carried out and supervised in academic or industrial institutions outside KCL. For an indication of the range of possible projects see e.g. the overview of past IPNN projects by following the relevant link at the right.

The third requirement is participation of the students in the neural networks seminar series. This allows the students to find out which is the state of the art in the field, and where are the present foci of academic and industrial research.

Semester I (Oct, Nov, Dec):	Neural Networks (core) + three selected lecture courses from Communication Theory Applied Probability and Statistics Basic Time Series Digital Signal Processing Introduction to Derivatives Pricing Numerical Analysis
Semester II (Jan, Feb, Mar):	Advanced Neural Networks (core) + three selected lecture courses from Information Theory in Neural Networks Statistical Mechanics of Neural Networks Theory of Algorithms Chaotic Dynamics/ Non-linear Dynamics
Examinations (May):	Written examinations in most subjects (a small number is examined in January)
Research Project (June-July-Aug):	Three month research project, concluded with project report to be examined early Sept

[Return to KCL Mathematics]