Abstract
A simple modification of the adaptive resonance theory (ART) neural network allows shift, scale and rotation invariant learning. The authors point out that this can be accomplished as a neural architecture by modifying the standard ART with hardwired interconnects that perform a Fourier-Mellin transform, and show how to modify the heuristics for efficient simulation of ART architectures to accomplish the additional innovation. Finally, they discuss the implementation of this in optoelectronic hardware, using a modification of the Van der Lugt optical correlator
Recommended Citation
D. C. Wunsch et al., "A Neural Architecture for Unsupervised Learning with Shift, Scale and Rotation Invariance, Efficient Software Simulation Heuristics, and Optoelectronic Implementation," Proceedings of the 24th Annual Hawaii International Conference on System Sciences, 1991, Institute of Electrical and Electronics Engineers (IEEE), Jan 1991.
The definitive version is available at https://doi.org/10.1109/HICSS.1991.183898
Meeting Name
24th Annual Hawaii International Conference on System Sciences, 1991
Department(s)
Electrical and Computer Engineering
Keywords and Phrases
Fourier-Mellin Transform; Van Der Lugt Optical Correlator; Adaptive Resonance Theory; Hardwired Interconnects; Learning Systems; Neural Architecture; Neural Nets; Neural Network; Optical Information Processing; Optoelectronic Devices; Optoelectronic Hardware; Optoelectronic Implementation; Rotation Invariance; Scale Invariance; Shift Invariance; Software Simulation Heuristics; Unsupervised Learning
Document Type
Article - Conference proceedings
Document Version
Final Version
File Type
text
Language(s)
English
Rights
© 1991 Institute of Electrical and Electronics Engineers (IEEE), All rights reserved.
Publication Date
01 Jan 1991
