Loading…
Temporal pattern recognition via temporal networks of temporal neurons
We show that real valued continuous functions can be recognized in a reliable way, with good generalization ability using an adapted version of the Liquid State Machine (LSM) that receives direct real valued input. Furthermore this system works without the necessity of preliminary extraction of sign...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Conference Proceeding |
| Language: | English |
| Subjects: | |
| Online Access: | Request full text |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| cited_by | |
|---|---|
| cites | |
| container_end_page | 4 |
| container_issue | |
| container_start_page | 1 |
| container_title | |
| container_volume | |
| creator | Frid, Alex Hazan, H. Manevitz, L. |
| description | We show that real valued continuous functions can be recognized in a reliable way, with good generalization ability using an adapted version of the Liquid State Machine (LSM) that receives direct real valued input. Furthermore this system works without the necessity of preliminary extraction of signal processing features. This avoids the necessity of discretization and encoding that has plagued earlier attempts on this process. We show this is effective on a simulated signal designed to have the properties of a physical trace of human speech. The main changes to the basic liquid state machine paradigm are (i) external stimulation to neurons by normalized real values and (ii) adaptation of the integrate and fire neurons in the liquid to have a history dependent sliding threshold (iii) topological constraints on the network connectivity. |
| doi_str_mv | 10.1109/EEEI.2012.6377010 |
| format | conference_proceeding |
| fullrecord | <record><control><sourceid>ieee_6IE</sourceid><recordid>TN_cdi_ieee_primary_6377010</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>6377010</ieee_id><sourcerecordid>6377010</sourcerecordid><originalsourceid>FETCH-LOGICAL-i90t-ca9397429c56714ef134329c96a8068d59670a693233d4c62d735c37b0a1c7763</originalsourceid><addsrcrecordid>eNpNT1FLwzAYjMhAnf0B4kv_QOuXfGm-5lFG5wYDX_o-YpqO6NaUNCr-ewtu4NNxx91xx9gDh5Jz0E9N02xLAVyUComAwxW741IRSlWDuGaZpvrCRXXDsml6B4A5q2rUt2zdutMYojnmo0nJxSGPzobD4JMPQ_7lTZ4uhsGl7xA_pjz0_8XPGIbpni16c5xcdsYla9dNu9oUu9eX7ep5V3gNqbBGoyYptK0Ucel6jhJnppWp5z1dpRWBURoFYietEh1hZZHewHBLpHDJHv9qvXNuP0Z_MvFnf36Ov8m1S98</addsrcrecordid><sourcetype>Publisher</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>Temporal pattern recognition via temporal networks of temporal neurons</title><source>IEEE Electronic Library (IEL) Conference Proceedings</source><creator>Frid, Alex ; Hazan, H. ; Manevitz, L.</creator><creatorcontrib>Frid, Alex ; Hazan, H. ; Manevitz, L.</creatorcontrib><description>We show that real valued continuous functions can be recognized in a reliable way, with good generalization ability using an adapted version of the Liquid State Machine (LSM) that receives direct real valued input. Furthermore this system works without the necessity of preliminary extraction of signal processing features. This avoids the necessity of discretization and encoding that has plagued earlier attempts on this process. We show this is effective on a simulated signal designed to have the properties of a physical trace of human speech. The main changes to the basic liquid state machine paradigm are (i) external stimulation to neurons by normalized real values and (ii) adaptation of the integrate and fire neurons in the liquid to have a history dependent sliding threshold (iii) topological constraints on the network connectivity.</description><identifier>ISBN: 9781467346825</identifier><identifier>ISBN: 1467346829</identifier><identifier>EISBN: 1467346802</identifier><identifier>EISBN: 9781467346801</identifier><identifier>EISBN: 9781467346818</identifier><identifier>EISBN: 1467346810</identifier><identifier>DOI: 10.1109/EEEI.2012.6377010</identifier><language>eng</language><publisher>IEEE</publisher><subject>Classification ; Classification algorithms ; Encoding ; Feature extraction ; Fires ; Firing ; Liquid State Machine (LSM) ; Liquids ; Neurons ; Signal Processing ; Temporal Networks</subject><ispartof>2012 IEEE 27th Convention of Electrical and Electronics Engineers in Israel, 2012, p.1-4</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/6377010$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>309,310,780,784,789,790,2057,27924,54919</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/6377010$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Frid, Alex</creatorcontrib><creatorcontrib>Hazan, H.</creatorcontrib><creatorcontrib>Manevitz, L.</creatorcontrib><title>Temporal pattern recognition via temporal networks of temporal neurons</title><title>2012 IEEE 27th Convention of Electrical and Electronics Engineers in Israel</title><addtitle>EEEI</addtitle><description>We show that real valued continuous functions can be recognized in a reliable way, with good generalization ability using an adapted version of the Liquid State Machine (LSM) that receives direct real valued input. Furthermore this system works without the necessity of preliminary extraction of signal processing features. This avoids the necessity of discretization and encoding that has plagued earlier attempts on this process. We show this is effective on a simulated signal designed to have the properties of a physical trace of human speech. The main changes to the basic liquid state machine paradigm are (i) external stimulation to neurons by normalized real values and (ii) adaptation of the integrate and fire neurons in the liquid to have a history dependent sliding threshold (iii) topological constraints on the network connectivity.</description><subject>Classification</subject><subject>Classification algorithms</subject><subject>Encoding</subject><subject>Feature extraction</subject><subject>Fires</subject><subject>Firing</subject><subject>Liquid State Machine (LSM)</subject><subject>Liquids</subject><subject>Neurons</subject><subject>Signal Processing</subject><subject>Temporal Networks</subject><isbn>9781467346825</isbn><isbn>1467346829</isbn><isbn>1467346802</isbn><isbn>9781467346801</isbn><isbn>9781467346818</isbn><isbn>1467346810</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>2012</creationdate><recordtype>conference_proceeding</recordtype><sourceid>6IE</sourceid><recordid>eNpNT1FLwzAYjMhAnf0B4kv_QOuXfGm-5lFG5wYDX_o-YpqO6NaUNCr-ewtu4NNxx91xx9gDh5Jz0E9N02xLAVyUComAwxW741IRSlWDuGaZpvrCRXXDsml6B4A5q2rUt2zdutMYojnmo0nJxSGPzobD4JMPQ_7lTZ4uhsGl7xA_pjz0_8XPGIbpni16c5xcdsYla9dNu9oUu9eX7ep5V3gNqbBGoyYptK0Ucel6jhJnppWp5z1dpRWBURoFYietEh1hZZHewHBLpHDJHv9qvXNuP0Z_MvFnf36Ov8m1S98</recordid><startdate>201211</startdate><enddate>201211</enddate><creator>Frid, Alex</creator><creator>Hazan, H.</creator><creator>Manevitz, L.</creator><general>IEEE</general><scope>6IE</scope><scope>6IL</scope><scope>CBEJK</scope><scope>RIE</scope><scope>RIL</scope></search><sort><creationdate>201211</creationdate><title>Temporal pattern recognition via temporal networks of temporal neurons</title><author>Frid, Alex ; Hazan, H. ; Manevitz, L.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-i90t-ca9397429c56714ef134329c96a8068d59670a693233d4c62d735c37b0a1c7763</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>2012</creationdate><topic>Classification</topic><topic>Classification algorithms</topic><topic>Encoding</topic><topic>Feature extraction</topic><topic>Fires</topic><topic>Firing</topic><topic>Liquid State Machine (LSM)</topic><topic>Liquids</topic><topic>Neurons</topic><topic>Signal Processing</topic><topic>Temporal Networks</topic><toplevel>online_resources</toplevel><creatorcontrib>Frid, Alex</creatorcontrib><creatorcontrib>Hazan, H.</creatorcontrib><creatorcontrib>Manevitz, L.</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/IET 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>Frid, Alex</au><au>Hazan, H.</au><au>Manevitz, L.</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>Temporal pattern recognition via temporal networks of temporal neurons</atitle><btitle>2012 IEEE 27th Convention of Electrical and Electronics Engineers in Israel</btitle><stitle>EEEI</stitle><date>2012-11</date><risdate>2012</risdate><spage>1</spage><epage>4</epage><pages>1-4</pages><isbn>9781467346825</isbn><isbn>1467346829</isbn><eisbn>1467346802</eisbn><eisbn>9781467346801</eisbn><eisbn>9781467346818</eisbn><eisbn>1467346810</eisbn><abstract>We show that real valued continuous functions can be recognized in a reliable way, with good generalization ability using an adapted version of the Liquid State Machine (LSM) that receives direct real valued input. Furthermore this system works without the necessity of preliminary extraction of signal processing features. This avoids the necessity of discretization and encoding that has plagued earlier attempts on this process. We show this is effective on a simulated signal designed to have the properties of a physical trace of human speech. The main changes to the basic liquid state machine paradigm are (i) external stimulation to neurons by normalized real values and (ii) adaptation of the integrate and fire neurons in the liquid to have a history dependent sliding threshold (iii) topological constraints on the network connectivity.</abstract><pub>IEEE</pub><doi>10.1109/EEEI.2012.6377010</doi><tpages>4</tpages></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | ISBN: 9781467346825 |
| ispartof | 2012 IEEE 27th Convention of Electrical and Electronics Engineers in Israel, 2012, p.1-4 |
| issn | |
| language | eng |
| recordid | cdi_ieee_primary_6377010 |
| source | IEEE Electronic Library (IEL) Conference Proceedings |
| subjects | Classification Classification algorithms Encoding Feature extraction Fires Firing Liquid State Machine (LSM) Liquids Neurons Signal Processing Temporal Networks |
| title | Temporal pattern recognition via temporal networks of temporal neurons |
| url | http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-08T23%3A54%3A58IST&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=Temporal%20pattern%20recognition%20via%20temporal%20networks%20of%20temporal%20neurons&rft.btitle=2012%20IEEE%2027th%20Convention%20of%20Electrical%20and%20Electronics%20Engineers%20in%20Israel&rft.au=Frid,%20Alex&rft.date=2012-11&rft.spage=1&rft.epage=4&rft.pages=1-4&rft.isbn=9781467346825&rft.isbn_list=1467346829&rft_id=info:doi/10.1109/EEEI.2012.6377010&rft.eisbn=1467346802&rft.eisbn_list=9781467346801&rft.eisbn_list=9781467346818&rft.eisbn_list=1467346810&rft_dat=%3Cieee_6IE%3E6377010%3C/ieee_6IE%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-i90t-ca9397429c56714ef134329c96a8068d59670a693233d4c62d735c37b0a1c7763%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=6377010&rfr_iscdi=true |