Graduate Thesis Or Dissertation
 

Training and pattern recognition in layered automata

Public Deposited

Downloadable Content

Download PDF
https://ir.library.oregonstate.edu/concern/graduate_thesis_or_dissertations/5h73pz52b

Descriptions

Attribute NameValues
Creator
Abstract
  • The project herein described, presents the results of an investigation in the relatively new and expanding field of computer stimulated learning machines for use in pattern recognition. A learning machine, one that benefits from its past experience was devised in computer program form. It may be described as a Piecewise-Linear, layer, learning machine, Efforts were made to ascertain the major parameters, properties, requirements and so on, that determine its behavior. Once a feeling for the idiosyncracies of the machine had been developed, a second. goal was to devise an effective training procedure and obtain an estimate as to the accuracy that may be obtained in pattern classification and extrapolation problems. We denote "training" as that phase during which one attempts to develop the machine's ability to differentiate between various examples of pattern categories by some means of an interactive error correction procedure; and the "decision" or "extrapolation" phase as that during which unknown, uncategorized patterns are presented to the machine for judgement.
Resource Type
Date Available
Date Issued
Degree Level
Degree Name
Degree Field
Degree Grantor
Commencement Year
Advisor
Academic Affiliation
Non-Academic Affiliation
Subject
Rights Statement
Publisher
Peer Reviewed
Language
Digitization Specifications
  • File scanned at 300 ppi (Monochrome) using Capture Perfect 3.0 on a Canon DR-9050C in PDF format. CVista PdfCompressor 4.0 was used for pdf compression and textual OCR.
Replaces

Relationships

Parents:

This work has no parents.

In Collection:

Items

Thumbnail Title Date Uploaded Visibility Actions
file details SchmidtDietger1973.pdf 2017-08-07 Public Download