Sign In With Google
Course Description
-
Course Name
Neural Networks
-
Host University
University of Reading
-
Location
Reading, England
-
Area of Study
Computer Engineering, Computer Science
-
Language Level
Taught In English
-
Course Level Recommendations
Upper
ISA offers course level recommendations in an effort to facilitate the determination of course levels by credential evaluators.We advice each institution to have their own credentials evaluator make the final decision regrading course levels.
-
ECTS Credits
5 -
Recommended U.S. Semester Credits3
-
Recommended U.S. Quarter Units4
Hours & Credits
-
Overview
Module Provider: School of Mathematical and Physical Sciences
Number of credits: 10 [5 ECTS credits]
Level:5
Terms in which taught: Autumn / Spring term module
Pre-requisites: SE1PR11 Programming SE1FA15 Fundamentals and Applications of Computing
Non-modular pre-requisites:
Co-requisites:
Modules excluded:
Module version for: 2016/7Summary module description:
This module covers the theory and implementation of a few types of artificial neural network. In addition, one network is used as a case study for object oriented programming. Students are expected to implement a neural network and apply it to real world problems.Aims:
The module aims to describe in detail a mode of computation inspired by such biological functionality, namely artificial neural networks. The module also demonstrates how such a network can be programmed using object orientation.Assessable learning outcomes:
By the end of the module the student should be able to apply various neural network techniques to 'real-world' problems; and to program a simple neural network using the object oriented paradigm.Additional outcomes:
EA2 topics: Neural Network Programming and Report WritingOutline content:
Various neural network techniques are described, for some their implementation is provided, and suitable applications discussed. Networks and techniques examined include data processing; Single and Multi- Layer Perceptrons and associated learning methods; Radial Basis Function networksm Weightless Neural Networks; Genetic Algorithms; Stochastic Diffusion Search.
Associated with the lectures is an assignment whereby students use the object oriented paradigm to design and implement a neural network and then apply that network to a suitable problem.
Brief description of teaching and learning methods:
The module comprises 1 lecture per week, three lab practicals and an associated assignment.Contact hours:
Lectures- 10
Practicals classes and workshops- 9
Guided independent study- 25%
Total hours by term- 44Summative Assessment Methods:
Sex exercise- 100%Other information on summative assessment:
Formative assessment methods:Length of examination:
NoneRequirements for a pass:
A mark of 40% overallReassessment arrangements:
Examination only.
One 2-hour examination paper in August/September.
Course Disclaimer
Courses and course hours of instruction are subject to change.
Some courses may require additional fees.
Credits earned vary according to the policies of the students' home institutions. According to ISA policy and possible visa requirements, students must maintain full-time enrollment status, as determined by their home institutions, for the duration of the program.
ECTS (European Credit Transfer and Accumulation System) credits are converted to semester credits/quarter units differently among U.S. universities. Students should confirm the conversion scale used at their home university when determining credit transfer.
Please reference fall and spring course lists as not all courses are taught during both semesters.
Please note that some courses with locals have recommended prerequisite courses. It is the student's responsibility to consult any recommended prerequisites prior to enrolling in their course.