A Neural Architecture for Unsupervised Learning with Shift, Scale and Rotation Invariance, Efficient Software Simulation Heuristics, and Optoelectronic Implementation

Donald C. Wunsch; D. S. Newman; T. P. Caudell; R. A. Falk; C. David Capps

doi:10.1109/HICSS.1991.183898

A Neural Architecture for Unsupervised Learning with Shift, Scale and Rotation Invariance, Efficient Software Simulation Heuristics, and Optoelectronic Implementation

Donald C. Wunsch
, D. S. Newman
, T. P. Caudell
, R. A. Falk
, C. David Capps

Research output: Contribution to journal › Article › peer-review

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

Original language	American English
Journal	Proceedings of the 24th Annual Hawaii International Conference on System Sciences, 1991
DOIs	https://doi.org/10.1109/HICSS.1991.183898
State	Published - Jan 1 1991

Keywords

Adaptive Resonance Theory
Fourier-Mellin Transform
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
Van Der Lugt Optical Correlator

Disciplines

Electrical and Computer Engineering

Access to Document

10.1109/HICSS.1991.183898License: Unspecified

A Neural Architecture for Unsupervised Learning with Shift ScaleFinal published version, 532 KBLicense: Unspecified

Cite this

Wunsch, D. C., Newman, D. S., Caudell, T. P., Falk, R. A., & Capps, C. D. (1991). 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. https://doi.org/10.1109/HICSS.1991.183898

A Neural Architecture for Unsupervised Learning with Shift, Scale and Rotation Invariance, Efficient Software Simulation Heuristics, and Optoelectronic Implementation. / Wunsch, Donald C.; Newman, D. S.; Caudell, T. P. et al.
In: Proceedings of the 24th Annual Hawaii International Conference on System Sciences, 1991, 01.01.1991.

Research output: Contribution to journal › Article › peer-review

@article{713729efa03a44b2aee70ddc522a45fc,

title = "A Neural Architecture for Unsupervised Learning with Shift, Scale and Rotation Invariance, Efficient Software Simulation Heuristics, and Optoelectronic Implementation",

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",

keywords = "Adaptive Resonance Theory, Fourier-Mellin Transform, 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, Van Der Lugt Optical Correlator",

author = "Wunsch, \{Donald C.\} and Newman, \{D. S.\} and Caudell, \{T. P.\} and Falk, \{R. A.\} and Capps, \{C. David\}",

year = "1991",

month = jan,

day = "1",

doi = "10.1109/HICSS.1991.183898",

language = "American English",

journal = "Proceedings of the 24th Annual Hawaii International Conference on System Sciences, 1991",

}

TY - JOUR

T1 - A Neural Architecture for Unsupervised Learning with Shift, Scale and Rotation Invariance, Efficient Software Simulation Heuristics, and Optoelectronic Implementation

AU - Wunsch, Donald C.

AU - Newman, D. S.

AU - Caudell, T. P.

AU - Falk, R. A.

AU - Capps, C. David

PY - 1991/1/1

Y1 - 1991/1/1

N2 - 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

AB - 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

KW - Adaptive Resonance Theory

KW - Fourier-Mellin Transform

KW - Hardwired Interconnects

KW - Learning Systems

KW - Neural Architecture

KW - Neural Nets

KW - Neural Network

KW - Optical Information Processing

KW - Optoelectronic Devices

KW - Optoelectronic Hardware

KW - Optoelectronic Implementation

KW - Rotation Invariance

KW - Scale Invariance

KW - Shift Invariance

KW - Software Simulation Heuristics

KW - Unsupervised Learning

KW - Van Der Lugt Optical Correlator

UR - https://scholarsmine.mst.edu/ele_comeng_facwork/1377

U2 - 10.1109/HICSS.1991.183898

DO - 10.1109/HICSS.1991.183898

M3 - Article

JO - Proceedings of the 24th Annual Hawaii International Conference on System Sciences, 1991

JF - Proceedings of the 24th Annual Hawaii International Conference on System Sciences, 1991

ER -

A Neural Architecture for Unsupervised Learning with Shift, Scale and Rotation Invariance, Efficient Software Simulation Heuristics, and Optoelectronic Implementation

Abstract

Keywords

Disciplines

Access to Document

Other files and links

Fingerprint

Cite this