Computational advantages of higher order neural networks

C. L. Giles; R. D. Griffin; T. Maxwell

doi:10.1016/0893-6080(88)90134-7

Computational advantages of higher order neural networks

C. L. Giles, R. D. Griffin, T. Maxwell

Research output: Contribution to journal › Conference article › peer-review

Abstract

This paper discusses recent research in higher order neural networks (HONNs) with a particular emphasis on geometric invariances. Motivation for the HONN model is that it is a natural extension of first order neural nets (power series expansion) and offers increased computational power for an artificial neuron. Though there are many ways to increase the computational power of the neuron, the HONN representation is a straight-forward one.

Original language	English (US)
Pages (from-to)	95
Number of pages	1
Journal	Neural Networks
Volume	1
Issue number	1 SUPPL
DOIs	https://doi.org/10.1016/0893-6080(88)90134-7
State	Published - 1988
Event	International Neural Network Society 1988 First Annual Meeting - Boston, MA, USA Duration: Sep 6 1988 → Sep 10 1988

All Science Journal Classification (ASJC) codes

Cognitive Neuroscience
Artificial Intelligence

Access to Document

10.1016/0893-6080(88)90134-7

Cite this

@article{cb21eaabe6f94623a42ba411f6957d7e,

title = "Computational advantages of higher order neural networks",

abstract = "This paper discusses recent research in higher order neural networks (HONNs) with a particular emphasis on geometric invariances. Motivation for the HONN model is that it is a natural extension of first order neural nets (power series expansion) and offers increased computational power for an artificial neuron. Though there are many ways to increase the computational power of the neuron, the HONN representation is a straight-forward one.",

author = "Giles, {C. L.} and Griffin, {R. D.} and T. Maxwell",

note = "Funding Information: This work was financially supported by National Natural Science Foundation of China (51972070 and 52062004), Guizhou Provincial Science and Technology Projects (QKHJC[2020]1Z042), Cultivation Project of Guizhou University (GDPY[2019]01), Guizhou Provincial Science and Technology Projects (QKHZC[2021]YB317), Graduate Innovation Research Fund of Guizhou Province (YJSCXJH[2020]028)，and Guizhou Provincial High Level Innovative Talents Project (QKHPTRC-GCC[2022]013-1).; International Neural Network Society 1988 First Annual Meeting ; Conference date: 06-09-1988 Through 10-09-1988",

year = "1988",

doi = "10.1016/0893-6080(88)90134-7",

language = "English (US)",

volume = "1",

pages = "95",

journal = "Neural Networks",

issn = "0893-6080",

publisher = "Elsevier Limited",

number = "1 SUPPL",

}

TY - JOUR

T1 - Computational advantages of higher order neural networks

AU - Giles, C. L.

AU - Griffin, R. D.

AU - Maxwell, T.

N1 - Funding Information: This work was financially supported by National Natural Science Foundation of China (51972070 and 52062004), Guizhou Provincial Science and Technology Projects (QKHJC[2020]1Z042), Cultivation Project of Guizhou University (GDPY[2019]01), Guizhou Provincial Science and Technology Projects (QKHZC[2021]YB317), Graduate Innovation Research Fund of Guizhou Province (YJSCXJH[2020]028)，and Guizhou Provincial High Level Innovative Talents Project (QKHPTRC-GCC[2022]013-1).

PY - 1988

Y1 - 1988

N2 - This paper discusses recent research in higher order neural networks (HONNs) with a particular emphasis on geometric invariances. Motivation for the HONN model is that it is a natural extension of first order neural nets (power series expansion) and offers increased computational power for an artificial neuron. Though there are many ways to increase the computational power of the neuron, the HONN representation is a straight-forward one.

AB - This paper discusses recent research in higher order neural networks (HONNs) with a particular emphasis on geometric invariances. Motivation for the HONN model is that it is a natural extension of first order neural nets (power series expansion) and offers increased computational power for an artificial neuron. Though there are many ways to increase the computational power of the neuron, the HONN representation is a straight-forward one.

UR - http://www.scopus.com/inward/record.url?scp=0024174421&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0024174421&partnerID=8YFLogxK

U2 - 10.1016/0893-6080(88)90134-7

DO - 10.1016/0893-6080(88)90134-7

M3 - Conference article

AN - SCOPUS:0024174421

SN - 0893-6080

VL - 1

SP - 95

JO - Neural Networks

JF - Neural Networks

IS - 1 SUPPL

T2 - International Neural Network Society 1988 First Annual Meeting

Y2 - 6 September 1988 through 10 September 1988

ER -

Computational advantages of higher order neural networks

Abstract

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this