Building Practical Classifiers Using Cerebellar Model Associative Memory Neural Networks

David Cornforth

Building Practical Classifiers Using Cerebellar Model Associative Memory Neural Networks

David Cornforth

Research output: Book chapter/Published conference paper › Conference paper › peer-review

Abstract

How can cerebellar model neural networks be successfully applied to automated classification? Simple modifications and a new training scheme are applied to the Cerebellar Model Articulation Controller (CMAC). This results in a classifier with fast training time, guaranteed convergence and a small number of parameters. How can model parameters be set to achieve optimum classifier accuracy, without lengthy empirical trials? A consideration of the most significant sources of classification error results in a simple method for estimating the optimum range for the parameters. The method is tested using empirical trials, and shown to be reliable. This makes the modified CMAC a desirable choice for automated classification in the context of pattern recognition and data mining.

Original language	English
Title of host publication	Artificial Neural Networks and Expert Systems
Editors	Nikola Kasabov, Brendon Woodford
Place of Publication	Dunedin, New Zealand
Publisher	University of Otago
Pages	1-6
Number of pages	6
ISBN (Electronic)	1877139408
Publication status	Published - 2001
Event	Conference on Artificial Neural Networks and Expert systems - Dunedin, New Zealand, New Zealand Duration: 22 Nov 2001 → 24 Nov 2001

Conference

Conference	Conference on Artificial Neural Networks and Expert systems
Country	New Zealand
Period	22/11/01 → 24/11/01

Fingerprint Dive into the research topics of 'Building Practical Classifiers Using Cerebellar Model Associative Memory Neural Networks'. Together they form a unique fingerprint.

Cite this

@inproceedings{e6ea2afe236d4aa193776b9217efc1b9,

title = "Building Practical Classifiers Using Cerebellar Model Associative Memory Neural Networks",

abstract = "How can cerebellar model neural networks be successfully applied to automated classification? Simple modifications and a new training scheme are applied to the Cerebellar Model Articulation Controller (CMAC). This results in a classifier with fast training time, guaranteed convergence and a small number of parameters. How can model parameters be set to achieve optimum classifier accuracy, without lengthy empirical trials? A consideration of the most significant sources of classification error results in a simple method for estimating the optimum range for the parameters. The method is tested using empirical trials, and shown to be reliable. This makes the modified CMAC a desirable choice for automated classification in the context of pattern recognition and data mining.",

author = "David Cornforth",

note = "Imported on 03 May 2017 - DigiTool details were: publisher = Dunedin, New Zealand: University of Otago, 2001. editor/s (773b) = Kasabov, Nikola & Woodford, Brendon; Event dates (773o) = 22-24 November 2001; Parent title (773t) = Conference on Artificial Neural Networks and Expert systems.; Conference on Artificial Neural Networks and Expert systems ; Conference date: 22-11-2001 Through 24-11-2001",

year = "2001",

language = "English",

pages = "1--6",

editor = "Nikola Kasabov and Brendon Woodford",

booktitle = "Artificial Neural Networks and Expert Systems",

publisher = "University of Otago",

}

TY - GEN

T1 - Building Practical Classifiers Using Cerebellar Model Associative Memory Neural Networks

AU - Cornforth, David

N1 - Imported on 03 May 2017 - DigiTool details were: publisher = Dunedin, New Zealand: University of Otago, 2001. editor/s (773b) = Kasabov, Nikola & Woodford, Brendon; Event dates (773o) = 22-24 November 2001; Parent title (773t) = Conference on Artificial Neural Networks and Expert systems.

PY - 2001

Y1 - 2001

N2 - How can cerebellar model neural networks be successfully applied to automated classification? Simple modifications and a new training scheme are applied to the Cerebellar Model Articulation Controller (CMAC). This results in a classifier with fast training time, guaranteed convergence and a small number of parameters. How can model parameters be set to achieve optimum classifier accuracy, without lengthy empirical trials? A consideration of the most significant sources of classification error results in a simple method for estimating the optimum range for the parameters. The method is tested using empirical trials, and shown to be reliable. This makes the modified CMAC a desirable choice for automated classification in the context of pattern recognition and data mining.

AB - How can cerebellar model neural networks be successfully applied to automated classification? Simple modifications and a new training scheme are applied to the Cerebellar Model Articulation Controller (CMAC). This results in a classifier with fast training time, guaranteed convergence and a small number of parameters. How can model parameters be set to achieve optimum classifier accuracy, without lengthy empirical trials? A consideration of the most significant sources of classification error results in a simple method for estimating the optimum range for the parameters. The method is tested using empirical trials, and shown to be reliable. This makes the modified CMAC a desirable choice for automated classification in the context of pattern recognition and data mining.

M3 - Conference paper

SP - 1

EP - 6

BT - Artificial Neural Networks and Expert Systems

A2 - Kasabov, Nikola

A2 - Woodford, Brendon

PB - University of Otago

CY - Dunedin, New Zealand

T2 - Conference on Artificial Neural Networks and Expert systems

Y2 - 22 November 2001 through 24 November 2001

ER -