Back to results

University of Windsor

Optical photoreceptors for CMOS neural circuitry.

Abstract

dc:description.abstract

The work described in this thesis relates to the design of photoreceptors fabricated in Northern Telecom's 3μ CMOS process. The photoreceptor consists of a vertical BJT whose output current is fed to four diode connected MOSFETs. Results of the experiments used to characterize the device both optically and electronically are given. Shortcomings of the device are identified and a modified photoreceptive device has been designed. These photoreceptive devices will be used to provide optical inputs to a neural network. By using optical connections to provide inputs to the chip, data can be sent directly to individual locations on the chip from above. This approach may eventually be used to solve the problems of an analog storage device and of pin-limitations usually associated with the VLSI implementation of neural networks. An architecture for making optimal use of the photoreceptors characteristics is given. This current mode architecture uses the current from the photoreceptor as the input to the network as well as the weights. Source: Masters Abstracts International, Volume: 31-03, page: 1315. Thesis (M.A.Sc.)--University of Windsor (Canada), 1991.

Degree

thesis:*
Name thesis:degree_name
M.A.Sc.
Level thesis:degree_level
Masters
Discipline thesis:degree_discipline
Electrical and Computer Engineering
Grantor
University of Windsor
Year dc:date.issued
1991

Author and committee

dc:creator, dc:contributor.*
Author dc:creator
  • Bewtra, Naveen.

Rights

dc:rights
Language dc:language.iso
en_CA

Identifiers

dc:identifier.*
Handle dc:identifier.uri
https://hdl.handle.net/20.500.14776/2573
OAI identifier oai:identifier
oai:uwindsor.scholaris.ca:20.500.14776/2573

Chain of custody

source
Harvested from
University of Windsor
Base URL
uwindsor.scholaris.ca/server/oai/request
Last updated
2026-07-27
Source record
OAI-PMH GetRecord
related terms
citation

Bewtra, Naveen.. Optical photoreceptors for CMOS neural circuitry.. Masters thesis, University of Windsor, 1991. https://hdl.handle.net/20.500.14776/2573