Photonic neurocomputers and learning machines

Author

Farhat, Nabil H.

Author_Institution

Dept. of Electr. Eng., Pennsylvania Univ., Philadelphia, PA, USA

fYear

1990

fDate

1-3 May 1990

Firstpage

696

Abstract

Efforts and progress made towards achieving desirable attributes in analog photonic (optoelectronic and/or electron optical) hardware that utilizes primarily incoherent light are reviewed. A hardware implementation of a stochastic Boltzmann learning machine is used as a vehicle for identifying generic issues and clarifying research and development areas for further advancement of the field. The development of architectures and methodologies for learning in self-organizing networks that employ a type of quasi-nonvolatile storage medium called electron trapping material is discussed

Keywords

integrated optoelectronics; learning systems; neural nets; optical information processing; analogue photonic hardware; architectures; biological neural networks; electron trapping material; electronoptical hardware; incoherent light; optoelectronic hardware; photonic neurocomputers; quasi-nonvolatile storage medium; self-organizing networks; stochastic Boltzmann learning machine; Analog computers; Computer networks; Frequency; High performance computing; High speed optical techniques; Machine learning; Neural networks; Neurons; Optical computing; Physics computing;

fLanguage

English

Publisher

ieee

Conference_Titel

Circuits and Systems, 1990., IEEE International Symposium on

Conference_Location

New Orleans, LA

Type

conf

DOI

10.1109/ISCAS.1990.112174

Filename

112174