A dynamic unsupervised laterally connected neural network architecture for integrative pattern discovery

Authors:
Asanka Fonseka;Damminda Alahakoon;Jayantha Rajapakse
Affiliations:
Cognitive and Connectionist Systems Lab, Faculty of Information Technology, Monash University, Clayton, Australia;Cognitive and Connectionist Systems Lab, Faculty of Information Technology, Monash University, Clayton, Australia;Cognitive and Connectionist Systems Lab, Sunway Campus, Monash University, Malaysia
Venue:
ICONIP'11 Proceedings of the 18th international conference on Neural Information Processing - Volume Part II
Year:
2011

Citing 9
Cited 0

Information Fusion in Data Mining

Information Fusion in Data Mining
Combining Pattern Classifiers: Methods and Algorithms

Combining Pattern Classifiers: Methods and Algorithms
On Clustering Multimedia Time Series Data Using K-Means and Dynamic Time Warping

MUE '07 Proceedings of the 2007 International Conference on Multimedia and Ubiquitous Engineering
2008 Special Issue: A theoretical study of multisensory integration in the superior colliculus by a neural network model

Neural Networks
Cross-modal clustering

AAAI'05 Proceedings of the 20th national conference on Artificial intelligence - Volume 2
Object localisation using laterally connected "What" and "Where" associator networks

ICANN/ICONIP'03 Proceedings of the 2003 joint international conference on Artificial neural networks and neural information processing
Perceptual binding by coupled oscillatory neural network

ICANN'05 Proceedings of the 15th international conference on Artificial Neural Networks: biological Inspirations - Volume Part I
The MPEG-7 visual standard for content description-an overview

IEEE Transactions on Circuits and Systems for Video Technology
Dynamic self-organizing maps with controlled growth for knowledge discovery

IEEE Transactions on Neural Networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

We describe an unsupervised neural network approach to build associations between neurons within cortical maps. These associations are then used to capture patterns in the input data. The cortical maps are modeled using growing self-organization maps to capture the input stimuli distribution within a two dimensional neuronal map. The associations are modeled using passive lateral connections using recognition frequency of input stimuli by a neuron. The proposed approach introduces a novel way of learning by adapting neighborhood learning rules and proximity measures according to the input stimuli structure.