Show simple item record

dc.contributor.author
Di Stefano, Francesco
dc.contributor.supervisor
Hofmann, Thomas
dc.contributor.supervisor
Rahimi, A.
dc.contributor.supervisor
Hersche, Michael
dc.date.accessioned
2023-11-09T06:55:41Z
dc.date.available
2023-09-04T14:23:43Z
dc.date.available
2023-09-05T07:14:27Z
dc.date.available
2023-11-05T13:57:31Z
dc.date.available
2023-11-06T09:23:57Z
dc.date.available
2023-11-06T09:25:23Z
dc.date.available
2023-11-08T18:15:14Z
dc.date.available
2023-11-09T06:55:41Z
dc.date.issued
2023
dc.identifier.uri
http://hdl.handle.net/20.500.11850/629701
dc.identifier.doi
10.3929/ethz-b-000629701
dc.description.abstract
The capacity for abstract reasoning is a cornerstone of human intelligence, and replicating this in machine learning models presents a complex challenge. This study focuses on the RAVEN dataset, a standard for assessing abstract reasoning abilities. Building upon the foundational work of Hersche et al., which employed Vector Symbolic Architectures (VSA) for reasoning, we delve deeper into making the reasoning mechanism learnable. Central to our exploration is the introduction of the AxR-Learners Framework, which incorporates the Learnable Formula. This innovative model is designed to autonomously adapt, allowing for a more flexible and tailored approach to abstract reasoning tasks. Our findings highlight the efficacy of the Learnable Formula in enhancing machine reasoning, suggesting a promising avenue for the evolution of more sophisticated artificial intelligence systems.
en_US
dc.format
application/pdf
en_US
dc.language.iso
en
en_US
dc.publisher
ETH Zurich
en_US
dc.rights.uri
http://rightsstatements.org/page/InC-NC/1.0/
dc.title
Exploring Abstract Reasoning Methods Working with Disentangled Visual Attributes
en_US
dc.type
Master Thesis
dc.rights.license
In Copyright - Non-Commercial Use Permitted
ethz.size
62 p.
en_US
ethz.publication.place
Zurich
en_US
ethz.publication.status
published
en_US
ethz.leitzahl
ETH Zürich::00002 - ETH Zürich::00012 - Lehre und Forschung::00007 - Departemente::02150 - Dep. Informatik / Dep. of Computer Science::02661 - Institut für Maschinelles Lernen / Institute for Machine Learning::09462 - Hofmann, Thomas / Hofmann, Thomas
en_US
ethz.date.deposited
2023-09-04T14:23:43Z
ethz.source
FORM
ethz.eth
yes
en_US
ethz.availability
Open access
en_US
ethz.rosetta.installDate
2023-09-05T07:14:28Z
ethz.rosetta.lastUpdated
2024-02-03T06:05:56Z
ethz.rosetta.versionExported
true
ethz.COinS
ctx_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.atitle=Exploring%20Abstract%20Reasoning%20Methods%20Working%20with%20Disentangled%20Visual%20Attributes&rft.date=2023&rft.au=Di%20Stefano,%20Francesco&rft.genre=unknown&rft.btitle=Exploring%20Abstract%20Reasoning%20Methods%20Working%20with%20Disentangled%20Visual%20Attributes
 Search print copy at ETH Library

Files in this item

Thumbnail
Thumbnail

Publication type

Show simple item record