Robust Character Recognition Using a Hierarchical Bayesian Network

File Size Format
40684.pdf 119Kb Adobe PDF View
Title Robust Character Recognition Using a Hierarchical Bayesian Network
Author Thornton, John; Gustafsson, Torbjorn Emil Karl; Blumenstein, Michael Myer; Hine, Trevor John
Publication Title AI 2006: Advances in Artificial Intelligence
Editor Abdul Sattar and Byeong-Ho Kang
Year Published 2006
Place of publication Berlin
Publisher Springer-Verlag
Abstract There is increasing evidence to suggest that the neocortex of the mammalian brain does not consist of a collection of specialised and dedicated cortical architectures, but instead possesses a fairly uniform, hierarchically organised structure. As Mountcastle has observed [1], this uniformity implies that the same general computational processes are performed across the entire neocortex, even though different regions are known to play different functional roles. Building on this evidence, Hawkins has proposed a top-down model of neocortical operation [2], taking it to be a kind of pattern recognition machine, storing invariant representations of neural input sequences in hierarchical memory structures that both predict sensory input and control behaviour. The first partial proof of concept of Hawkins' model was recently developed using a hierarchically organised Bayesian network that was tested on a simple pattern recognition problem [3]. In the current study we extend Hawkins' work by comparing the performance of a backpropagation neural network with our own implementation of a hierarchical Bayesian network in the well-studied domain of character recognition. The results show that even a simplistic implementation of Hawkins' model can produce recognition rates that exceed a standard neural network approach. Such results create a strong case for the further investigation and development of Hawkins' neocortically-inspired approach to building intelligent systems.
Peer Reviewed Yes
Published Yes
Publisher URI
Alternative URI
Copyright Statement Copyright 2006 Springer. This is the author-manuscript version of this paper. Reproduced in accordance with the copyright policy of the publisher. The original publication is available at
ISBN 978-3-540-49787-5
Conference name 19th Australian Joint Conference on Artificial Intelligence
Location Hobart
Date From 2006-12-04
Date To 2006-12-08
Date Accessioned 2007-03-09
Language en_AU
Research Centre Menzies Health Institute Qld; Behavioural Basis of Health; Institute for Integrated and Intelligent Systems
Faculty Faculty of Engineering and Information Technology
Subject PRE2009-Pattern Recognition
Publication Type Conference Publications (Full Written Paper - Refereed)
Publication Type Code e1

Show simple item record

Griffith University copyright notice