A1 Alkuperäisartikkeli tieteellisessä aikakauslehdessä
Neural Networks with Disabilities : An Introduction to Complementary Artificial Intelligence (2022)
Terziyan, V., & Kaikova, O. (2022). Neural Networks with Disabilities : An Introduction to Complementary Artificial Intelligence. Neural Computation, 34(1), 255-290. https://doi.org/10.1162/neco_a_01449
JYU-tekijät tai -toimittajat
Julkaisun tiedot
Julkaisun kaikki tekijät tai toimittajat: Terziyan, Vagan; Kaikova, Olena
Lehti tai sarja: Neural Computation
ISSN: 0899-7667
eISSN: 1530-888X
Julkaisuvuosi: 2022
Ilmestymispäivä: 19.10.2021
Volyymi: 34
Lehden numero: 1
Artikkelin sivunumerot: 255–290
Kustantaja: MIT Press
Julkaisumaa: Yhdysvallat (USA)
Julkaisun kieli: englanti
DOI: https://doi.org/10.1162/neco_a_01449
Julkaisun avoin saatavuus: Ei avoin
Julkaisukanavan avoin saatavuus:
Julkaisu on rinnakkaistallennettu (JYX): https://jyx.jyu.fi/handle/123456789/85058
Tiivistelmä
Machine learning is a good tool to simulate human cognitive skills as it is about mapping perceived information to various labels or action choices, aiming at optimal behavior policies for a human or an artificial agent operating in the environment. Regarding autonomous systems, objects and situations are perceived by some receptors as divided between sensors. Reactions to the input (e.g., actions) are distributed among the particular capability providers or actuators. Cognitive models can be trained as, for example, neural networks. We suggest training such models for cases of potential disabilities. Disability can be either the absence of one or more cognitive sensors or actuators at different levels of cognitive model. We adapt several neural network architectures to simulate various cognitive disabilities. The idea has been triggered by the “coolability” (enhanced capability) paradox, according to which a person with some disability can be more efficient in using other capabilities. Therefore, an autonomous system (human or artificial) pretrained with simulated disabilities will be more efficient when acting in adversarial conditions. We consider these coolabilities as complementary artificial intelligence and argue on the usefulness if this concept for various applications.
YSO-asiasanat: koneoppiminen; neuroverkot; kognitiiviset taidot; toimintarajoitteet; simulointi
Liittyvät organisaatiot
OKM-raportointi: Kyllä
Raportointivuosi: 2021
JUFO-taso: 3
