Search Results - "Neville, R.S"
-
1
Applying Evolutionary Computing to Complex Systems Design
Published in IEEE transactions on systems, man and cybernetics. Part A, Systems and humans (01-09-2007)“…Development of an evolutionary computing tool for requirements analysis and optimization of component-based systems is described. The tool assesses scenarios…”
Get full text
Journal Article -
2
Transformations of sigma–pi nets: obtaining reflected functions by reflecting weight matrices
Published in Neural networks (01-04-2002)“…This paper presents a methodology that reflected functions by reflecting the weight matrices of an artificial neural network. One of the major problems with…”
Get full text
Journal Article -
3
Performing basic mathematics with neurons/nets. I
Published in Proceedings of the 2002 International Joint Conference on Neural Networks. IJCNN'02 (Cat. No.02CH37290) (2002)“…We introduce a way of performing basic mathematics or symbolic algebra with neurons. The method is novel because we enable knowledge encapsulated in trained…”
Get full text
Conference Proceeding
-
4
Performing mathematics with neurons or neural networks trained to represent non-linear functions. II
Published in Proceedings of the 2002 International Joint Conference on Neural Networks. IJCNN'02 (Cat. No.02CH37290) (2002)“…For part I see IEEE WCCI-2002 World Congress Computational Intelligence. The article introduces a way of performing mathematics with neurons trained to map…”
Get full text
Conference Proceeding -
5
Partially pre-calculated weights for the backpropagation learning regime and high accuracy function mapping using continuous input RAM-based sigma–pi nets
Published in Neural networks (2000)“…In this article we present a methodology that partially pre-calculates the weight updates of the backpropagation learning regime and obtains high accuracy…”
Get full text
Journal Article -
6
Learning Boolean functions without training
Published in 1998 IEEE International Joint Conference on Neural Networks Proceedings. IEEE World Congress on Computational Intelligence (Cat. No.98CH36227) (1998)“…This paper presents a new theory that enables one to obtain a set of Boolean functions from one learnt Boolean function. We do this by transposition of the…”
Get full text
Conference Proceeding -
7
Toward second-order generalisation
Published in 1998 IEEE International Joint Conference on Neural Networks Proceedings. IEEE World Congress on Computational Intelligence (Cat. No.98CH36227) (1998)“…Generalisation in artificial neural networks may be cast into two basic categories, 'standard' and 'higher-order'. We view 'standard' generalisation as a means…”
Get full text
Conference Proceeding -
8
Introduction to adaptive weight lattice neural networks
Published in 1998 IEEE International Joint Conference on Neural Networks Proceedings. IEEE World Congress on Computational Intelligence (Cat. No.98CH36227) (1998)“…Research into RAM-based neural networks has now been in progress for approximately two decades. In this paper we introduce a novel way to visualise RAM-based…”
Get full text
Conference Proceeding -
9
Inheritance of information in multi-layer sigma-pi neural networks
Published in Proceedings of the International Joint Conference on Neural Networks, 2003 (2003)“…This article shows that prior knowledge may be incorporated into a neural network by using the knowledge in a trained net to prescribe the weights for a new…”
Get full text
Conference Proceeding -
10
Third-order generalization and a new approach to systematically categorizing higher-order generalization
Published in Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005 (2005)“…Higher-order generalization is a means of categorizing different types of generalization. The paper presents a framework within which higher-order…”
Get full text
Conference Proceeding -
11
Information reuse and integration in artificial neural networks
Published in IRI -2005 IEEE International Conference on Information Reuse and Integration, Conf, 2005 (2005)“…The need to reuse information is urgent, and a shift is required in the development (understanding - research) of methodologies, with a more reuse-centric view…”
Get full text
Conference Proceeding -
12
Second-order generalization
Published in 2004 IEEE International Joint Conference on Neural Networks (IEEE Cat. No.04CH37541) (2004)“…Second-order generalization is usually of a more abstract nature than standard generalization, as unseen stimuli may be classified by some higher order rule…”
Get full text
Conference Proceeding -
13
RAM-based Sigma-pi nets for high accuracy function mapping
Published in Fifth International Conference on Artificial Neural Networks (1997)“…We investigate the use of digital "Higher Order" Sigma-pi nodes and study continuous input RAM-based Sigma-pi units trained with the backpropagation training…”
Get full text
Conference Proceeding -
14
Evaluation of training and mapping Sigma-pi networks to a massively parallel processor
Published in Proceedings of ICNN'95 - International Conference on Neural Networks (1995)“…This paper presents a methodology for training and mapping Sigma-pi networks on to a massively parallel processing (MPP) system. The implementation uses a…”
Get full text
Conference Proceeding