Grounded HyperSymbolic Representations Learned through Gradient-Based Optimization

Uproszczony widok
dc.contributor.authorŁuczak, Piotr
dc.contributor.authorŚlot, Krzysztof
dc.contributor.authorKucharski, Jacek
dc.date.accessioned2023-09-25T05:50:01Z
dc.date.available2023-09-25T05:50:01Z
dc.date.issued2023
dc.description.abstractHyperdimensional computing is a novel paradigm, capable of processing complex data structures with simple operations. Its main limitations lie in the conversion of real world data onto hyperdimensional space, which due to lack of a universal translation scheme, oftentimes requires application-specific methods. This work presents a novel method for unsupervised hyperdimensional conversion of arbitrary image data. Additionally, this method is augmented by the ability of creating HyperSymbols, or class prototypes, provided that such class labels are available. The proposed method achieves promising performance on MNIST dataset, both in translating individual samples as well as producing HyperSymbols for downstream classification task.en_EN
dc.identifier.citationŁuczak P., Ślot K., Kucharski J., Grounded HyperSymbolic Representations Learned through Gradient-Based Optimization. W: Progress in Polish Artificial Intelligence Research 4, Wojciechowski A. (Ed.), Lipiński P. (Ed.)., Seria: Monografie Politechniki Łódzkiej Nr. 2437, Wydawnictwo Politechniki Łódzkiej, Łódź 2023, s. 319-324, ISBN 978-83-66741-92-8, doi: 10.34658/9788366741928.51.
dc.identifier.doi10.34658/9788366741928.51
dc.identifier.isbn978-83-66741-92-8
dc.identifier.urihttp://hdl.handle.net/11652/4827
dc.identifier.urihttps://doi.org/10.34658/9788366741928.51
dc.language.isoenen_EN
dc.page.numbers. 319-324
dc.publisherWydawnictwo Politechniki Łódzkiejpl_PL
dc.publisherLodz University of Technology Pressen_EN
dc.relation.ispartofWojciechowski A. (Ed.), Lipiński P. (Ed.)., Progress in Polish Artificial Intelligence Research 4, Seria: Monografie Politechniki Łódzkiej Nr. 2437, Wydawnictwo Politechniki Łódzkiej, Łódź 2023, ISBN 978-83-66741-92-8, doi: 10.34658/9788366741928.
dc.rightsDla wszystkich w zakresie dozwolonego użytkupl_PL
dc.rightsFair use conditionen_EN
dc.rights.licenseLicencja PŁpl_PL
dc.rights.licenseLUT Licenseen_EN
dc.subjectartificial intelligenceen_EN
dc.subjecthyperdimensional computingen_EN
dc.subjectrepresentation extractionen_EN
dc.subjectneuromorphic architecturesen_EN
dc.subjectsztuczna inteligencjapl_PL
dc.subjectobliczenia hiperwymiarowepl_PL
dc.subjectekstrakcja reprezentacjipl_PL
dc.subjectarchitektury neuromorficznepl_PL
dc.titleGrounded HyperSymbolic Representations Learned through Gradient-Based Optimizationen_EN
dc.typeRozdział - monografiapl_PL
dc.typeChapter - monographen_EN

Pliki

Oryginalne pliki
Teraz wyświetlane 1 - 1 z 1
Brak miniatury
Nazwa:
51. Grounded_hypersymbolic_representat_Luczak_Slot_2023.pdf
Rozmiar:
450.49 KB
Format:
Adobe Portable Document Format
Opis:
Pobierz
Licencja
Teraz wyświetlane 1 - 1 z 1
Brak miniatury
Nazwa:
license.txt
Rozmiar:
1.71 KB
Format:
Item-specific license agreed upon to submission
Opis:
Pobierz

Kolekcje

Rozdziały
Książki, monografie, podręczniki, rozdziały (WEEIiA)