Training of recurrent Internal Symmetry Networks by backpropagation

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 netwo...

Full description

Saved in:
Bibliographic Details
Published in2009 International Joint Conference on Neural Networks pp. 353 - 358
Main Authors Blair, A., Guanzhong Li
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.06.2009
Subjects
Backpropagation
Cellular networks
Cellular neural networks
group representations
Image processing
internal symmetry
Lattices
Neural networks
Performance evaluation
Physics
recurrent dynamics
Recurrent neural networks
Testing
Online AccessGet full text

Cover

More Information
Summary: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.
ISBN:142443548X
9781424435487
ISSN:2161-4393
2161-4407
DOI:10.1109/IJCNN.2009.5178870