NEURAL NETWORK SYSTEM

NEURAL NETWORK SYSTEM

The present invention relates to a neural network system (300), having a first electronic computation module (301-1) for computing an output from a first neuron by means of an activation function in a data format having a first bit range for indicating that the value of the activation function is ze...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
1. Verfasser: GUNTORO, Andre
Format: Patent
Sprache:eng ; fre ; ger
Schlagworte:
CALCULATING
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
COMPUTING
COUNTING
PHYSICS
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title
container_volume
creator GUNTORO, Andre
description The present invention relates to a neural network system (300), having a first electronic computation module (301-1) for computing an output from a first neuron by means of an activation function in a data format having a first bit range for indicating that the value of the activation function is zero and a second bit range for coding a positive value of the activation function; and a second computation module (301-2) for computing the output from a second neuron on the basis of the output from the first neuron by omitting multiplication and accumulation of the output from the first neuron if the data format indicates that the value of the activation function is zero.
format Patent
fullrecord <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_EP3590078A1</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>EP3590078A1</sourcerecordid><originalsourceid>FETCH-epo_espacenet_EP3590078A13</originalsourceid><addsrcrecordid>eNrjZBD1cw0NcvRR8HMNCfcP8lYIjgwOcfXlYWBNS8wpTuWF0twMCm6uIc4euqkF-fGpxQWJyal5qSXxrgHGppYGBuYWjobGRCgBAHFCHro</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>NEURAL NETWORK SYSTEM</title><source>esp@cenet</source><creator>GUNTORO, Andre</creator><creatorcontrib>GUNTORO, Andre</creatorcontrib><description>The present invention relates to a neural network system (300), having a first electronic computation module (301-1) for computing an output from a first neuron by means of an activation function in a data format having a first bit range for indicating that the value of the activation function is zero and a second bit range for coding a positive value of the activation function; and a second computation module (301-2) for computing the output from a second neuron on the basis of the output from the first neuron by omitting multiplication and accumulation of the output from the first neuron if the data format indicates that the value of the activation function is zero.</description><language>eng ; fre ; ger</language><subject>CALCULATING ; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS ; COMPUTING ; COUNTING ; PHYSICS</subject><creationdate>2020</creationdate><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&amp;date=20200108&amp;DB=EPODOC&amp;CC=EP&amp;NR=3590078A1$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,776,881,25542,76516</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&amp;date=20200108&amp;DB=EPODOC&amp;CC=EP&amp;NR=3590078A1$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>GUNTORO, Andre</creatorcontrib><title>NEURAL NETWORK SYSTEM</title><description>The present invention relates to a neural network system (300), having a first electronic computation module (301-1) for computing an output from a first neuron by means of an activation function in a data format having a first bit range for indicating that the value of the activation function is zero and a second bit range for coding a positive value of the activation function; and a second computation module (301-2) for computing the output from a second neuron on the basis of the output from the first neuron by omitting multiplication and accumulation of the output from the first neuron if the data format indicates that the value of the activation function is zero.</description><subject>CALCULATING</subject><subject>COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS</subject><subject>COMPUTING</subject><subject>COUNTING</subject><subject>PHYSICS</subject><fulltext>true</fulltext><rsrctype>patent</rsrctype><creationdate>2020</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNrjZBD1cw0NcvRR8HMNCfcP8lYIjgwOcfXlYWBNS8wpTuWF0twMCm6uIc4euqkF-fGpxQWJyal5qSXxrgHGppYGBuYWjobGRCgBAHFCHro</recordid><startdate>20200108</startdate><enddate>20200108</enddate><creator>GUNTORO, Andre</creator><scope>EVB</scope></search><sort><creationdate>20200108</creationdate><title>NEURAL NETWORK SYSTEM</title><author>GUNTORO, Andre</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_EP3590078A13</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>eng ; fre ; ger</language><creationdate>2020</creationdate><topic>CALCULATING</topic><topic>COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS</topic><topic>COMPUTING</topic><topic>COUNTING</topic><topic>PHYSICS</topic><toplevel>online_resources</toplevel><creatorcontrib>GUNTORO, Andre</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>GUNTORO, Andre</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>NEURAL NETWORK SYSTEM</title><date>2020-01-08</date><risdate>2020</risdate><abstract>The present invention relates to a neural network system (300), having a first electronic computation module (301-1) for computing an output from a first neuron by means of an activation function in a data format having a first bit range for indicating that the value of the activation function is zero and a second bit range for coding a positive value of the activation function; and a second computation module (301-2) for computing the output from a second neuron on the basis of the output from the first neuron by omitting multiplication and accumulation of the output from the first neuron if the data format indicates that the value of the activation function is zero.</abstract><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier
ispartof
issn
language eng ; fre ; ger
recordid cdi_epo_espacenet_EP3590078A1
source esp@cenet
subjects CALCULATING
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
COMPUTING
COUNTING
PHYSICS
title NEURAL NETWORK SYSTEM
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-13T13%3A48%3A59IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-epo_EVB&rft_val_fmt=info:ofi/fmt:kev:mtx:patent&rft.genre=patent&rft.au=GUNTORO,%20Andre&rft.date=2020-01-08&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3EEP3590078A1%3C/epo_EVB%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true