The architecture and design of a neural network classifier Public Deposited

http://ir.library.oregonstate.edu/concern/graduate_thesis_or_dissertations/nk322h502

Descriptions

Attribute NameValues
Creator
Abstract or Summary
  • The objective of this thesis is to present the architecture and design of a neural network-based pattern classifier. The classifier detects textual characters which have been translated, rotated, and corrupted by noise. This form of pattern classifier differs significantly from traditional pattern classifiers. The neural network architecture used in implementing this classifier incorporates massive parallelism, distributed memory, fault tolerance, and is capable of learning. Traditional classifiers rarely incorporate all these features. The classifier's neural network topology, interconnect structure, learning algorithms, test methodology, and test results are presented in the thesis.
Resource Type
Date Available
Date Copyright
Date Issued
Degree Level
Degree Name
Degree Field
Degree Grantor
Commencement Year
Advisor
Academic Affiliation
Non-Academic Affiliation
Subject
Rights Statement
Peer Reviewed
Language
Digitization Specifications
  • File scanned at 300 ppi (Monochrome) using ScandAll PRO 1.8.1 on a Fi-6770A in PDF format. CVista PdfCompressor 5.0 was used for pdf compression and textual OCR.
Replaces
Additional Information
  • description.provenance : Approved for entry into archive by Patricia Black(patricia.black@oregonstate.edu) on 2013-06-28T15:24:28Z (GMT) No. of bitstreams: 1 JiangJin1990.pdf: 899429 bytes, checksum: 1939e997a8f31a885df46d1f923c6ec2 (MD5)
  • description.provenance : Submitted by Kaylee Patterson (kdpscanner@gmail.com) on 2013-05-06T19:38:54Z No. of bitstreams: 1 JiangJin1990.pdf: 899429 bytes, checksum: 1939e997a8f31a885df46d1f923c6ec2 (MD5)
  • description.provenance : Made available in DSpace on 2013-06-28T15:24:28Z (GMT). No. of bitstreams: 1 JiangJin1990.pdf: 899429 bytes, checksum: 1939e997a8f31a885df46d1f923c6ec2 (MD5) Previous issue date: 1990-03-02
  • description.provenance : Approved for entry into archive by Patricia Black(patricia.black@oregonstate.edu) on 2013-05-08T15:32:51Z (GMT) No. of bitstreams: 1 JiangJin1990.pdf: 899429 bytes, checksum: 1939e997a8f31a885df46d1f923c6ec2 (MD5)

Relationships

Parents:

This work has no parents.

Last modified

Downloadable Content

Download PDF

Items