Keating, John (1993) Hopfield networks, neural data structures and the nine flies problem: neural network programming projects for undergraduates. SIGCSE Bulletin, 25 (4). pp. 33-37. ISSN 0097-8418

Preview

Download (663kB) | Preview

Abstract

This paper describes two neural network programming projects suitable for undergraduate students who have already completed introductory courses in Programming and Data Structures. It briefly outlines the structure and operation of Hopfield Networks from a data structure stand-point and demonstrates how these type of neural networks may be used to solve interesting problems like Perelman's Nine Flies Problem. Although the Hopfield model is well defined mathematically, students do not have to be very familiar with the mathematics of the model in order to use it to solve problems. Students are actively encouraged to design modifications to their implementations in order to obtain faster or more accurate solutions. Additionally, students are also expected to compare the neural network's performance with traditional approaches, in order that they may appreciate the subtleties of both approaches. Sample results are provided from projects which have been completed during the last three-year period.

Item Type:	Article
Keywords:	Hopfield networks; neural data structures; nine flies problem; neural network programming projects; undergraduates;
Academic Unit:	Faculty of Science and Engineering > Computer Science
Item ID:	8675
Depositing User:	Dr. John Keating
Date Deposited:	24 Aug 2017 14:46
Journal or Publication Title:	SIGCSE Bulletin
Publisher:	ACM
Refereed:	Yes
URI:
Use Licence:	This item is available under a Creative Commons Attribution Non Commercial Share Alike Licence (CC BY-NC-SA). Details of this licence are available here

Repository Staff Only(login required)

Item control page

Downloads

Origin of downloads