A signal processing neural network resembling the simple cells of the visual cortex

A single-layer neural network that mimics the quadratic phase relationship between the adjacent simple cells in the visual cortex is described. The input nodes of the network use neurons that have multiple output synapses. The resulting system, called the orthonormal neural network, can approximate...

Full description

Saved in:
Bibliographic Details
Main Author: Ulug, M.E.
Format: Conference Proceeding
Language:English
Subjects:
Backpropagation
Band pass filters
Fourier series
Frequency
Intelligent networks
Neural networks
Neurons
Signal processing
Testing
Transfer functions
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by
cites
container_end_page 989 vol.2
container_issue
container_start_page 978
container_title
container_volume
creator Ulug, M.E.
description A single-layer neural network that mimics the quadratic phase relationship between the adjacent simple cells in the visual cortex is described. The input nodes of the network use neurons that have multiple output synapses. The resulting system, called the orthonormal neural network, can approximate any L/sub 2/ mapping function between the input and output vectors without using hidden layers or the backpropagation rule. It is also free from the problems of local minima. Because the transfer functions of the input nodes are the terms of the Fourier series, the synaptic link values between the input and output layers represent the frequency spectrum of the signals of the output nodes. As a result by auto-associatively training the network with all the synaptic links and testing it with certain selected ones, it is quite easy to build a nonlinear bandpass filter. Several systems built with this new network are discussed.< >
doi_str_mv 10.1109/RNNS.1992.268533
format conference_proceeding
fullrecord <record><control><sourceid>ieee_6IE</sourceid><recordid>TN_cdi_ieee_primary_268533</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>268533</ieee_id><sourcerecordid>268533</sourcerecordid><originalsourceid>FETCH-LOGICAL-i89t-37c0cf873cc52c9a335d8f57c7133f75ff9523e093837806d2a49313794dd37e3</originalsourceid><addsrcrecordid>eNotj1tLAzEQhQMiqLXv4lP-wK5JZrNJHkvxBqWC7XtZs5MazV5Itl7-vdE6LwPfmTOcQ8gVZyXnzNw8r9ebkhsjSlFrCXBCLpjSDJhmBs7IPKU3lqcCBaI-J5sFTX7fN4GOcbCYku_3tMdDzKTH6XOI7zRiwu4l_CrTK-b7bgxILYaQ6OD-2IdPh-ywQ5zw65KcuiYknP_vGdne3W6XD8Xq6f5xuVgVXpupAGWZdVqBtVJY0wDIVjuprOIATknnjBSAObWGXKBuRVMZ4KBM1bagEGbk-vjWI-JujL5r4vfu2Bp-ANTlTas</addsrcrecordid><sourcetype>Publisher</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>A signal processing neural network resembling the simple cells of the visual cortex</title><source>IEEE Electronic Library (IEL) Conference Proceedings</source><creator>Ulug, M.E.</creator><creatorcontrib>Ulug, M.E.</creatorcontrib><description>A single-layer neural network that mimics the quadratic phase relationship between the adjacent simple cells in the visual cortex is described. The input nodes of the network use neurons that have multiple output synapses. The resulting system, called the orthonormal neural network, can approximate any L/sub 2/ mapping function between the input and output vectors without using hidden layers or the backpropagation rule. It is also free from the problems of local minima. Because the transfer functions of the input nodes are the terms of the Fourier series, the synaptic link values between the input and output layers represent the frequency spectrum of the signals of the output nodes. As a result by auto-associatively training the network with all the synaptic links and testing it with certain selected ones, it is quite easy to build a nonlinear bandpass filter. Several systems built with this new network are discussed.&lt; &gt;</description><identifier>ISBN: 0780308093</identifier><identifier>ISBN: 9780780308091</identifier><identifier>DOI: 10.1109/RNNS.1992.268533</identifier><language>eng</language><publisher>IEEE</publisher><subject>Backpropagation ; Band pass filters ; Fourier series ; Frequency ; Intelligent networks ; Neural networks ; Neurons ; Signal processing ; Testing ; Transfer functions</subject><ispartof>[Proceedings] 1992 RNNS/IEEE Symposium on Neuroinformatics and Neurocomputers, 1992, p.978-989 vol.2</ispartof><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/268533$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>309,310,780,784,789,790,2058,4050,4051,27925,54920</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/268533$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Ulug, M.E.</creatorcontrib><title>A signal processing neural network resembling the simple cells of the visual cortex</title><title>[Proceedings] 1992 RNNS/IEEE Symposium on Neuroinformatics and Neurocomputers</title><addtitle>RNNS</addtitle><description>A single-layer neural network that mimics the quadratic phase relationship between the adjacent simple cells in the visual cortex is described. The input nodes of the network use neurons that have multiple output synapses. The resulting system, called the orthonormal neural network, can approximate any L/sub 2/ mapping function between the input and output vectors without using hidden layers or the backpropagation rule. It is also free from the problems of local minima. Because the transfer functions of the input nodes are the terms of the Fourier series, the synaptic link values between the input and output layers represent the frequency spectrum of the signals of the output nodes. As a result by auto-associatively training the network with all the synaptic links and testing it with certain selected ones, it is quite easy to build a nonlinear bandpass filter. Several systems built with this new network are discussed.&lt; &gt;</description><subject>Backpropagation</subject><subject>Band pass filters</subject><subject>Fourier series</subject><subject>Frequency</subject><subject>Intelligent networks</subject><subject>Neural networks</subject><subject>Neurons</subject><subject>Signal processing</subject><subject>Testing</subject><subject>Transfer functions</subject><isbn>0780308093</isbn><isbn>9780780308091</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>1992</creationdate><recordtype>conference_proceeding</recordtype><sourceid>6IE</sourceid><recordid>eNotj1tLAzEQhQMiqLXv4lP-wK5JZrNJHkvxBqWC7XtZs5MazV5Itl7-vdE6LwPfmTOcQ8gVZyXnzNw8r9ebkhsjSlFrCXBCLpjSDJhmBs7IPKU3lqcCBaI-J5sFTX7fN4GOcbCYku_3tMdDzKTH6XOI7zRiwu4l_CrTK-b7bgxILYaQ6OD-2IdPh-ywQ5zw65KcuiYknP_vGdne3W6XD8Xq6f5xuVgVXpupAGWZdVqBtVJY0wDIVjuprOIATknnjBSAObWGXKBuRVMZ4KBM1bagEGbk-vjWI-JujL5r4vfu2Bp-ANTlTas</recordid><startdate>1992</startdate><enddate>1992</enddate><creator>Ulug, M.E.</creator><general>IEEE</general><scope>6IE</scope><scope>6IL</scope><scope>CBEJK</scope><scope>RIE</scope><scope>RIL</scope></search><sort><creationdate>1992</creationdate><title>A signal processing neural network resembling the simple cells of the visual cortex</title><author>Ulug, M.E.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-i89t-37c0cf873cc52c9a335d8f57c7133f75ff9523e093837806d2a49313794dd37e3</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>1992</creationdate><topic>Backpropagation</topic><topic>Band pass filters</topic><topic>Fourier series</topic><topic>Frequency</topic><topic>Intelligent networks</topic><topic>Neural networks</topic><topic>Neurons</topic><topic>Signal processing</topic><topic>Testing</topic><topic>Transfer functions</topic><toplevel>online_resources</toplevel><creatorcontrib>Ulug, M.E.</creatorcontrib><collection>IEEE Electronic Library (IEL) Conference Proceedings</collection><collection>IEEE Proceedings Order Plan All Online (POP All Online) 1998-present by volume</collection><collection>IEEE Xplore All Conference Proceedings</collection><collection>IEEE Electronic Library (IEL)</collection><collection>IEEE Proceedings Order Plans (POP All) 1998-Present</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Ulug, M.E.</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>A signal processing neural network resembling the simple cells of the visual cortex</atitle><btitle>[Proceedings] 1992 RNNS/IEEE Symposium on Neuroinformatics and Neurocomputers</btitle><stitle>RNNS</stitle><date>1992</date><risdate>1992</risdate><spage>978</spage><epage>989 vol.2</epage><pages>978-989 vol.2</pages><isbn>0780308093</isbn><isbn>9780780308091</isbn><abstract>A single-layer neural network that mimics the quadratic phase relationship between the adjacent simple cells in the visual cortex is described. The input nodes of the network use neurons that have multiple output synapses. The resulting system, called the orthonormal neural network, can approximate any L/sub 2/ mapping function between the input and output vectors without using hidden layers or the backpropagation rule. It is also free from the problems of local minima. Because the transfer functions of the input nodes are the terms of the Fourier series, the synaptic link values between the input and output layers represent the frequency spectrum of the signals of the output nodes. As a result by auto-associatively training the network with all the synaptic links and testing it with certain selected ones, it is quite easy to build a nonlinear bandpass filter. Several systems built with this new network are discussed.&lt; &gt;</abstract><pub>IEEE</pub><doi>10.1109/RNNS.1992.268533</doi></addata></record>
fulltext fulltext_linktorsrc
identifier ISBN: 0780308093
ispartof [Proceedings] 1992 RNNS/IEEE Symposium on Neuroinformatics and Neurocomputers, 1992, p.978-989 vol.2
issn
language eng
recordid cdi_ieee_primary_268533
source IEEE Electronic Library (IEL) Conference Proceedings
subjects Backpropagation
Band pass filters
Fourier series
Frequency
Intelligent networks
Neural networks
Neurons
Signal processing
Testing
Transfer functions
title A signal processing neural network resembling the simple cells of the visual cortex
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-29T17%3A15%3A56IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-ieee_6IE&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=proceeding&rft.atitle=A%20signal%20processing%20neural%20network%20resembling%20the%20simple%20cells%20of%20the%20visual%20cortex&rft.btitle=%5BProceedings%5D%201992%20RNNS/IEEE%20Symposium%20on%20Neuroinformatics%20and%20Neurocomputers&rft.au=Ulug,%20M.E.&rft.date=1992&rft.spage=978&rft.epage=989%20vol.2&rft.pages=978-989%20vol.2&rft.isbn=0780308093&rft.isbn_list=9780780308091&rft_id=info:doi/10.1109/RNNS.1992.268533&rft_dat=%3Cieee_6IE%3E268533%3C/ieee_6IE%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-i89t-37c0cf873cc52c9a335d8f57c7133f75ff9523e093837806d2a49313794dd37e3%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_id=info:pmid/&rft_ieee_id=268533&rfr_iscdi=true