Machine intelligence using hierarchical memory networks

Research output: Chapter in Book/Report/Conference proceedingChapter

1 Citation (Scopus)

Abstract

This chapter presents the fundamentals of a hardware based memory network that can perform complex cognitive tasks. The network is designed to provide space dimensionality reduction, which enables desired functionality in a random environment. Complex network functionality is achieved by simple network cells that minimize the needed chip area for hardware implementation. Functionality of this network is demonstrated by automatic character recognition with various input deformations. In the character recognition, the network is trained to recognize characters deformed by random noise, rotation, scaling, and shifting. This example demonstrates how cognitive functionality of a hardware network can be achieved through an evolutionary process, as distinct from design based on mathematical formalism.

Original languageEnglish
Title of host publicationHandbook of Research on Computational Intelligence for Engineering, Science, and Business
PublisherIGI Global
Pages62-73
Number of pages12
ISBN (Print)9781466625181
DOIs
Publication statusPublished - Dec 1 2012
Externally publishedYes

Fingerprint

Character recognition
Hardware
Data storage equipment
Complex networks
Computer hardware

ASJC Scopus subject areas

  • Computer Science(all)

Cite this

James, A. P. (2012). Machine intelligence using hierarchical memory networks. In Handbook of Research on Computational Intelligence for Engineering, Science, and Business (pp. 62-73). IGI Global. https://doi.org/10.4018/978-1-46662-518-1.ch003

Machine intelligence using hierarchical memory networks. / James, A. P.

Handbook of Research on Computational Intelligence for Engineering, Science, and Business. IGI Global, 2012. p. 62-73.

Research output: Chapter in Book/Report/Conference proceedingChapter

James, AP 2012, Machine intelligence using hierarchical memory networks. in Handbook of Research on Computational Intelligence for Engineering, Science, and Business. IGI Global, pp. 62-73. https://doi.org/10.4018/978-1-46662-518-1.ch003
James AP. Machine intelligence using hierarchical memory networks. In Handbook of Research on Computational Intelligence for Engineering, Science, and Business. IGI Global. 2012. p. 62-73 https://doi.org/10.4018/978-1-46662-518-1.ch003
James, A. P. / Machine intelligence using hierarchical memory networks. Handbook of Research on Computational Intelligence for Engineering, Science, and Business. IGI Global, 2012. pp. 62-73
@inbook{2c5c713a73834a63b712c87d7011f163,
title = "Machine intelligence using hierarchical memory networks",
abstract = "This chapter presents the fundamentals of a hardware based memory network that can perform complex cognitive tasks. The network is designed to provide space dimensionality reduction, which enables desired functionality in a random environment. Complex network functionality is achieved by simple network cells that minimize the needed chip area for hardware implementation. Functionality of this network is demonstrated by automatic character recognition with various input deformations. In the character recognition, the network is trained to recognize characters deformed by random noise, rotation, scaling, and shifting. This example demonstrates how cognitive functionality of a hardware network can be achieved through an evolutionary process, as distinct from design based on mathematical formalism.",
author = "James, {A. P.}",
year = "2012",
month = "12",
day = "1",
doi = "10.4018/978-1-46662-518-1.ch003",
language = "English",
isbn = "9781466625181",
pages = "62--73",
booktitle = "Handbook of Research on Computational Intelligence for Engineering, Science, and Business",
publisher = "IGI Global",

}

TY - CHAP

T1 - Machine intelligence using hierarchical memory networks

AU - James, A. P.

PY - 2012/12/1

Y1 - 2012/12/1

N2 - This chapter presents the fundamentals of a hardware based memory network that can perform complex cognitive tasks. The network is designed to provide space dimensionality reduction, which enables desired functionality in a random environment. Complex network functionality is achieved by simple network cells that minimize the needed chip area for hardware implementation. Functionality of this network is demonstrated by automatic character recognition with various input deformations. In the character recognition, the network is trained to recognize characters deformed by random noise, rotation, scaling, and shifting. This example demonstrates how cognitive functionality of a hardware network can be achieved through an evolutionary process, as distinct from design based on mathematical formalism.

AB - This chapter presents the fundamentals of a hardware based memory network that can perform complex cognitive tasks. The network is designed to provide space dimensionality reduction, which enables desired functionality in a random environment. Complex network functionality is achieved by simple network cells that minimize the needed chip area for hardware implementation. Functionality of this network is demonstrated by automatic character recognition with various input deformations. In the character recognition, the network is trained to recognize characters deformed by random noise, rotation, scaling, and shifting. This example demonstrates how cognitive functionality of a hardware network can be achieved through an evolutionary process, as distinct from design based on mathematical formalism.

UR - http://www.scopus.com/inward/record.url?scp=84898519177&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84898519177&partnerID=8YFLogxK

U2 - 10.4018/978-1-46662-518-1.ch003

DO - 10.4018/978-1-46662-518-1.ch003

M3 - Chapter

AN - SCOPUS:84898519177

SN - 9781466625181

SP - 62

EP - 73

BT - Handbook of Research on Computational Intelligence for Engineering, Science, and Business

PB - IGI Global

ER -