SwePub
Sök i LIBRIS databas

  Utökad sökning

WFRF:(Higuera Nelson)
 

Sökning: WFRF:(Higuera Nelson) > A Neuro-Symbolic AS...

LIBRIS Formathandbok  (Information om MARC21)
FältnamnIndikatorerMetadata
00003548naa a2200517 4500
001oai:DiVA.org:hj-63556
003SwePub
008240216s2022 | |||||||||||000 ||eng|
024a https://urn.kb.se/resolve?urn=urn:nbn:se:hj:diva-635562 URI
024a https://doi.org/10.1017/S14710684220002292 DOI
040 a (SwePub)hj
041 a engb eng
042 9 SwePub
072 7a ref2 swepub-contenttype
072 7a art2 swepub-publicationtype
100a Eiter, Thomasu Institute of Logic and Computation, Vienna University of Technology (TU Wien), Austria4 aut
2451 0a A Neuro-Symbolic ASP Pipeline for Visual Question Answering
264 1b Cambridge University Press,c 2022
338 a print2 rdacarrier
520 a We present a neuro-symbolic visual question answering (VQA) pipeline for CLEVR, which is a well-known dataset that consists of pictures showing scenes with objects and questions related to them. Our pipeline covers (i) training neural networks for object classification and bounding-box prediction of the CLEVR scenes, (ii) statistical analysis on the distribution of prediction values of the neural networks to determine a threshold for high-confidence predictions, and (iii) a translation of CLEVR questions and network predictions that pass confidence thresholds into logic programmes so that we can compute the answers using an answer-set programming solver. By exploiting choice rules, we consider deterministic and non-deterministic scene encodings. Our experiments show that the non-deterministic scene encoding achieves good results even if the neural networks are trained rather poorly in comparison with the deterministic approach. This is important for building robust VQA systems if network predictions are less-than perfect. Furthermore, we show that restricting non-determinism to reasonable choices allows for more efficient implementations in comparison with related neuro-symbolic approaches without losing much accuracy.
650 7a NATURVETENSKAPx Data- och informationsvetenskapx Datavetenskap0 (SwePub)102012 hsv//swe
650 7a NATURAL SCIENCESx Computer and Information Sciencesx Computer Sciences0 (SwePub)102012 hsv//eng
653 a answer-set programming
653 a neuro-symbolic computation
653 a visual question answering
653 a Computation theory
653 a Encoding (symbols)
653 a Forecasting
653 a Logic programming
653 a Program translators
653 a Answer set programming
653 a Deterministics
653 a Encodings
653 a Network prediction
653 a Neural-networks
653 a Object classification
653 a Question Answering
653 a Symbolic computation
653 a Pipelines
700a Higuera, Nelsonu Institute of Logic and Computation, Vienna University of Technology (TU Wien), Austria4 aut
700a Oetsch, Johannesu Institute of Logic and Computation, Vienna University of Technology (TU Wien), Austria4 aut0 (Swepub:hj)oetjoh
700a Pritz, Michaelu Institute of Logic and Computation, Vienna University of Technology (TU Wien), Austria4 aut
710a Institute of Logic and Computation, Vienna University of Technology (TU Wien), Austria4 org
773t Theory and Practice of Logic Programmingd : Cambridge University Pressg 22:5, s. 739-754q 22:5<739-754x 1471-0684x 1475-3081
8564 8u https://urn.kb.se/resolve?urn=urn:nbn:se:hj:diva-63556
8564 8u https://doi.org/10.1017/S1471068422000229

Hitta via bibliotek

Till lärosätets databas

Hitta mer i SwePub

Av författaren/redakt...
Eiter, Thomas
Higuera, Nelson
Oetsch, Johannes
Pritz, Michael
Om ämnet
NATURVETENSKAP
NATURVETENSKAP
och Data och informa ...
och Datavetenskap
Artiklar i publikationen
Theory and Pract ...
Av lärosätet
Jönköping University

Sök utanför SwePub

Kungliga biblioteket hanterar dina personuppgifter i enlighet med EU:s dataskyddsförordning (2018), GDPR. Läs mer om hur det funkar här.
Så här hanterar KB dina uppgifter vid användning av denna tjänst.

 
pil uppåt Stäng

Kopiera och spara länken för att återkomma till aktuell vy