An Optical Adaptive Resonance Neural Network Utilizing Phase Conjugation

Donald C. Wunsch; D. J. Morris; T. P. Caudell; R. A. Falk

doi:10.1109/RNNS.1992.268572

An Optical Adaptive Resonance Neural Network Utilizing Phase Conjugation

Donald C. Wunsch
, D. J. Morris
, T. P. Caudell
, R. A. Falk

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

Abstract

An adaptive resonance (ART) device has been conceived that is fully optical in the input-output processing path. It is based on holographic information processing in a phase-conjugating crystal. This sets up an associative pattern retrieval in a resonating loop utilizing angle-multiplexed reference beams for pattern classification. A reset mechanism is used to reject any given beam, allowing an ART search strategy. The design is similar to an existing nonlearning optical associative memory, but it does allow learning and makes use of information the other device discards. This device is expected to offer higher information storage density than alternative ART implementations.

Original language	American English
Journal	Proceedings of the RNNS/IEEE Symposium on Neuroinformatics and Neurocomputers, 1992
DOIs	https://doi.org/10.1109/RNNS.1992.268572
State	Published - Jan 1 1992

Keywords

Adaptive Optics
Angle-Multiplexed Reference Beams
Associative Pattern Retrieval
Holographic Information Processing
Holographic Storage
Optical Adaptive Resonance Neural Network
Optical Neural Nets
Optical Phase Conjugation
Pattern Classification
Pattern Recognition
Phase Conjugation
Phase-Conjugating Crystal
Reset Mechanism

Disciplines

Electrical and Computer Engineering

Access to Document

10.1109/RNNS.1992.268572License: Unspecified

An Optical Adaptive Resonance Neural Network Utilizing Phase ConjFinal published version, 466 KBLicense: Unspecified

Cite this

@article{e9ce9ed600a04e768741fea818e794ed,

title = "An Optical Adaptive Resonance Neural Network Utilizing Phase Conjugation",

abstract = " An adaptive resonance (ART) device has been conceived that is fully optical in the input-output processing path. It is based on holographic information processing in a phase-conjugating crystal. This sets up an associative pattern retrieval in a resonating loop utilizing angle-multiplexed reference beams for pattern classification. A reset mechanism is used to reject any given beam, allowing an ART search strategy. The design is similar to an existing nonlearning optical associative memory, but it does allow learning and makes use of information the other device discards. This device is expected to offer higher information storage density than alternative ART implementations.",

keywords = "Adaptive Optics, Angle-Multiplexed Reference Beams, Associative Pattern Retrieval, Holographic Information Processing, Holographic Storage, Optical Adaptive Resonance Neural Network, Optical Neural Nets, Optical Phase Conjugation, Pattern Classification, Pattern Recognition, Phase Conjugation, Phase-Conjugating Crystal, Reset Mechanism",

author = "Wunsch, \{Donald C.\} and Morris, \{D. J.\} and Caudell, \{T. P.\} and Falk, \{R. A.\}",

year = "1992",

month = jan,

day = "1",

doi = "10.1109/RNNS.1992.268572",

language = "American English",

journal = "Proceedings of the RNNS/IEEE Symposium on Neuroinformatics and Neurocomputers, 1992",

}

TY - JOUR

T1 - An Optical Adaptive Resonance Neural Network Utilizing Phase Conjugation

AU - Wunsch, Donald C.

AU - Morris, D. J.

AU - Caudell, T. P.

AU - Falk, R. A.

PY - 1992/1/1

Y1 - 1992/1/1

N2 - An adaptive resonance (ART) device has been conceived that is fully optical in the input-output processing path. It is based on holographic information processing in a phase-conjugating crystal. This sets up an associative pattern retrieval in a resonating loop utilizing angle-multiplexed reference beams for pattern classification. A reset mechanism is used to reject any given beam, allowing an ART search strategy. The design is similar to an existing nonlearning optical associative memory, but it does allow learning and makes use of information the other device discards. This device is expected to offer higher information storage density than alternative ART implementations.

AB - An adaptive resonance (ART) device has been conceived that is fully optical in the input-output processing path. It is based on holographic information processing in a phase-conjugating crystal. This sets up an associative pattern retrieval in a resonating loop utilizing angle-multiplexed reference beams for pattern classification. A reset mechanism is used to reject any given beam, allowing an ART search strategy. The design is similar to an existing nonlearning optical associative memory, but it does allow learning and makes use of information the other device discards. This device is expected to offer higher information storage density than alternative ART implementations.

KW - Adaptive Optics

KW - Angle-Multiplexed Reference Beams

KW - Associative Pattern Retrieval

KW - Holographic Information Processing

KW - Holographic Storage

KW - Optical Adaptive Resonance Neural Network

KW - Optical Neural Nets

KW - Optical Phase Conjugation

KW - Pattern Classification

KW - Pattern Recognition

KW - Phase Conjugation

KW - Phase-Conjugating Crystal

KW - Reset Mechanism

UR - https://scholarsmine.mst.edu/ele_comeng_facwork/1443

U2 - 10.1109/RNNS.1992.268572

DO - 10.1109/RNNS.1992.268572

M3 - Article

JO - Proceedings of the RNNS/IEEE Symposium on Neuroinformatics and Neurocomputers, 1992

JF - Proceedings of the RNNS/IEEE Symposium on Neuroinformatics and Neurocomputers, 1992

ER -

An Optical Adaptive Resonance Neural Network Utilizing Phase Conjugation

Abstract

Keywords

Disciplines

Access to Document

Other files and links

Fingerprint

Cite this