A1 Journal article (refereed)
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 authors or editors

Publication details

All authors or editors: Terziyan, Vagan; Kaikova, Olena

Journal or series: Neural Computation

ISSN: 0899-7667

eISSN: 1530-888X

Publication year: 2022

Publication date: 19/10/2021

Volume: 34

Issue number: 1

Pages range: 255–290

Publisher: MIT Press

Publication country: United States

Publication language: English

DOI: https://doi.org/10.1162/neco_a_01449

Publication open access: Not open

Publication channel open access:

Publication is parallel published (JYX): https://jyx.jyu.fi/handle/123456789/85058

Abstract

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.

Keywords: machine learning; neural networks (information technology); cognitive skills; disabilities; simulation

Contributing organizations

Ministry reporting: Yes

Reporting Year: 2021

JUFO rating: 3