Analysis and synthesis of neural networks Public Deposited

http://ir.library.oregonstate.edu/concern/graduate_thesis_or_dissertations/db78tf46c

Descriptions

Attribute NameValues
Creator
Abstract or Summary
  • The brain has long attracted the interest of researchers. Some tasks, such as pattern recognition and optimization, have proven to be exceptionally difficult for conventional computing systems to perform, but are executed by the brain almost effortlessly. Due to the large number of neurons and interconnections, it has proven impossible to model the brain's architecture exactly. Researchers have instead created modest networks of artificial neural elements which can perform some interesting functions, such as generalization, pattern recognition, and the solution of certain optimization problems. These artificial neural networks do not work in exactly the same manner as the brain but they are proving useful in numerous practical applications. In this thesis the analysis, design, and hardware implementation of an artificial neural network is presented. In order to fully appreciate the architecture of the neural network described, a discussion of the properties of biological neurons and a brief history of neural network research is included. This is followed by a detailed discussion of the design, implementation, and testing of the network. The network under consideration is a general purpose time-multiplexed neural network suitable for VLSI implementation. A non-multiplexed neural network implementation generally requires full connectivity of the neural elements. This approach consumes too much chip area. The multiplexed approach taken in this thesis offers substantial area savings over the non-multiplexed approach.
Resource Type
Date Available
Date Copyright
Date Issued
Degree Level
Degree Name
Degree Field
Degree Grantor
Commencement Year
Advisor
Committee Member
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 : Made available in DSpace on 2013-06-27T22:13:07Z (GMT). No. of bitstreams: 1 SkeltonJeanetteK1989.pdf: 724366 bytes, checksum: bb95ea7cb9b40678e52919ffb21b3177 (MD5) Previous issue date: 1989-04-27
  • description.provenance : Submitted by Kaylee Patterson (kdpscanner@gmail.com) on 2013-05-16T19:31:12Z No. of bitstreams: 1 SkeltonJeanetteK1989.pdf: 724366 bytes, checksum: bb95ea7cb9b40678e52919ffb21b3177 (MD5)
  • description.provenance : Approved for entry into archive by Patricia Black(patricia.black@oregonstate.edu) on 2013-06-27T22:13:07Z (GMT) No. of bitstreams: 1 SkeltonJeanetteK1989.pdf: 724366 bytes, checksum: bb95ea7cb9b40678e52919ffb21b3177 (MD5)
  • description.provenance : Approved for entry into archive by Patricia Black(patricia.black@oregonstate.edu) on 2013-05-24T17:13:52Z (GMT) No. of bitstreams: 1 SkeltonJeanetteK1989.pdf: 724366 bytes, checksum: bb95ea7cb9b40678e52919ffb21b3177 (MD5)

Relationships

Parents:

This work has no parents.

Last modified

Downloadable Content

Download PDF

Items