MODEL BIAS DETECTION
Aspects of the present disclosure provide techniques for detecting latent bias in machine learning models. Embodiments include receiving a data set comprising features of a plurality of individuals. Embodiments include receiving identifying information for each individual of the plurality of individ...
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Patent |
| Sprache: | eng |
| Schlagworte: | |
| 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 | HORESH, Yair MEIR LADOR, Shir DE SHETLER, Natalie Grace BEN ARIE, Aviv MISHRAKY, Elhanan |
| description | Aspects of the present disclosure provide techniques for detecting latent bias in machine learning models. Embodiments include receiving a data set comprising features of a plurality of individuals. Embodiments include receiving identifying information for each individual of the plurality of individuals. Embodiments include predicting, for each respective individual of the plurality of individuals, a probability that the respective individual belongs to a given class based on the identifying information for the given individual. Embodiments include providing, as inputs to a machine learning model, the features of the plurality of individuals from the data set. Embodiments include receiving outputs from the machine learning model in response to the inputs. Embodiments include determining whether the machine learning model is biased against the given class based on the outputs and the probability that each respective individual of the plurality of individuals belongs to the given class. |
| format | Patent |
| fullrecord | <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_US2022351068A1</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>US2022351068A1</sourcerecordid><originalsourceid>FETCH-epo_espacenet_US2022351068A13</originalsourceid><addsrcrecordid>eNrjZBDx9Xdx9VFw8nQMVnBxDXF1DvH09-NhYE1LzClO5YXS3AzKbq4hzh66qQX58anFBYnJqXmpJfGhwUYGRkbGpoYGZhaOhsbEqQIA4G4fWA</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>MODEL BIAS DETECTION</title><source>esp@cenet</source><creator>HORESH, Yair ; MEIR LADOR, Shir ; DE SHETLER, Natalie Grace ; BEN ARIE, Aviv ; MISHRAKY, Elhanan</creator><creatorcontrib>HORESH, Yair ; MEIR LADOR, Shir ; DE SHETLER, Natalie Grace ; BEN ARIE, Aviv ; MISHRAKY, Elhanan</creatorcontrib><description>Aspects of the present disclosure provide techniques for detecting latent bias in machine learning models. Embodiments include receiving a data set comprising features of a plurality of individuals. Embodiments include receiving identifying information for each individual of the plurality of individuals. Embodiments include predicting, for each respective individual of the plurality of individuals, a probability that the respective individual belongs to a given class based on the identifying information for the given individual. Embodiments include providing, as inputs to a machine learning model, the features of the plurality of individuals from the data set. Embodiments include receiving outputs from the machine learning model in response to the inputs. Embodiments include determining whether the machine learning model is biased against the given class based on the outputs and the probability that each respective individual of the plurality of individuals belongs to the given class.</description><language>eng</language><subject>CALCULATING ; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS ; COMPUTING ; COUNTING ; PHYSICS</subject><creationdate>2022</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&date=20221103&DB=EPODOC&CC=US&NR=2022351068A1$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,776,881,25542,76289</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20221103&DB=EPODOC&CC=US&NR=2022351068A1$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>HORESH, Yair</creatorcontrib><creatorcontrib>MEIR LADOR, Shir</creatorcontrib><creatorcontrib>DE SHETLER, Natalie Grace</creatorcontrib><creatorcontrib>BEN ARIE, Aviv</creatorcontrib><creatorcontrib>MISHRAKY, Elhanan</creatorcontrib><title>MODEL BIAS DETECTION</title><description>Aspects of the present disclosure provide techniques for detecting latent bias in machine learning models. Embodiments include receiving a data set comprising features of a plurality of individuals. Embodiments include receiving identifying information for each individual of the plurality of individuals. Embodiments include predicting, for each respective individual of the plurality of individuals, a probability that the respective individual belongs to a given class based on the identifying information for the given individual. Embodiments include providing, as inputs to a machine learning model, the features of the plurality of individuals from the data set. Embodiments include receiving outputs from the machine learning model in response to the inputs. Embodiments include determining whether the machine learning model is biased against the given class based on the outputs and the probability that each respective individual of the plurality of individuals belongs to the given class.</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>2022</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNrjZBDx9Xdx9VFw8nQMVnBxDXF1DvH09-NhYE1LzClO5YXS3AzKbq4hzh66qQX58anFBYnJqXmpJfGhwUYGRkbGpoYGZhaOhsbEqQIA4G4fWA</recordid><startdate>20221103</startdate><enddate>20221103</enddate><creator>HORESH, Yair</creator><creator>MEIR LADOR, Shir</creator><creator>DE SHETLER, Natalie Grace</creator><creator>BEN ARIE, Aviv</creator><creator>MISHRAKY, Elhanan</creator><scope>EVB</scope></search><sort><creationdate>20221103</creationdate><title>MODEL BIAS DETECTION</title><author>HORESH, Yair ; MEIR LADOR, Shir ; DE SHETLER, Natalie Grace ; BEN ARIE, Aviv ; MISHRAKY, Elhanan</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_US2022351068A13</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>eng</language><creationdate>2022</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>HORESH, Yair</creatorcontrib><creatorcontrib>MEIR LADOR, Shir</creatorcontrib><creatorcontrib>DE SHETLER, Natalie Grace</creatorcontrib><creatorcontrib>BEN ARIE, Aviv</creatorcontrib><creatorcontrib>MISHRAKY, Elhanan</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>HORESH, Yair</au><au>MEIR LADOR, Shir</au><au>DE SHETLER, Natalie Grace</au><au>BEN ARIE, Aviv</au><au>MISHRAKY, Elhanan</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>MODEL BIAS DETECTION</title><date>2022-11-03</date><risdate>2022</risdate><abstract>Aspects of the present disclosure provide techniques for detecting latent bias in machine learning models. Embodiments include receiving a data set comprising features of a plurality of individuals. Embodiments include receiving identifying information for each individual of the plurality of individuals. Embodiments include predicting, for each respective individual of the plurality of individuals, a probability that the respective individual belongs to a given class based on the identifying information for the given individual. Embodiments include providing, as inputs to a machine learning model, the features of the plurality of individuals from the data set. Embodiments include receiving outputs from the machine learning model in response to the inputs. Embodiments include determining whether the machine learning model is biased against the given class based on the outputs and the probability that each respective individual of the plurality of individuals belongs to the given class.</abstract><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | |
| ispartof | |
| issn | |
| language | eng |
| recordid | cdi_epo_espacenet_US2022351068A1 |
| source | esp@cenet |
| subjects | CALCULATING COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS COMPUTING COUNTING PHYSICS |
| title | MODEL BIAS DETECTION |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-05T11%3A06%3A33IST&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=HORESH,%20Yair&rft.date=2022-11-03&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3EUS2022351068A1%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 |