Training of recurrent internal symmetry networks by backpropagation

Authors:
Alan Blair;Guanzhong Li
Affiliations:
School of Computer Science and Engineering, University of New South Wales, Sydney, Australia;School of Computer Science and Engineering, University of New South Wales, Sydney, Australia
Venue:
IJCNN'09 Proceedings of the 2009 international joint conference on Neural Networks
Year:
2009

Citing 4
Cited 0

A Computational Approach to Edge Detection

IEEE Transactions on Pattern Analysis and Machine Intelligence
The Induction of Dynamical Recognizers

Machine Learning - Connectionist approaches to language learning
Cellular neural networks and visual computing: foundations and applications

Cellular neural networks and visual computing: foundations and applications
Backpropagation applied to handwritten zip code recognition

Neural Computation

Quantified Score

Hi-index	0.00

Visualization

Abstract

Internal Symmetry Networks are a recently developed class of Cellular Neural Network inspired by the phenomenon of internal symmetry in quantum physics. Their hidden unit activations are acted on non-trivially by the dihedral group of symmetries of the square. Here, we extend Internal Symmetry Networks to include recurrent connections, and train them by backpropagation to perform two simple image processing tasks.