Epistemic Autonomy: Self-supervised Learning in the Mammalian Hippocampus.

Autor: Santos-Pata D; Laboratory of Synthetic, Perceptive, Emotive and Cognitive Systems (SPECS), Institute for Bioengineering of Catalonia (IBEC), Barcelona, Spain., Amil AF; Laboratory of Synthetic, Perceptive, Emotive and Cognitive Systems (SPECS), Institute for Bioengineering of Catalonia (IBEC), Barcelona, Spain; Universitat Pompeu Fabra (UPF), Barcelona, Spain., Raikov IG; Department of Neurosurgery, Stanford University, Stanford, CA, USA., Rennó-Costa C; Digital Metropolis Institute, Federal University of Rio Grande do Norte, Natal, Rio Grande do Norte, Brazil., Mura A; Laboratory of Synthetic, Perceptive, Emotive and Cognitive Systems (SPECS), Institute for Bioengineering of Catalonia (IBEC), Barcelona, Spain., Soltesz I; Department of Neurosurgery, Stanford University, Stanford, CA, USA., Verschure PFMJ; Laboratory of Synthetic, Perceptive, Emotive and Cognitive Systems (SPECS), Institute for Bioengineering of Catalonia (IBEC), Barcelona, Spain; Catalan Institution for Research and Advanced Studies (ICREA), Barcelona, Spain. Electronic address: pverschure@ibecbarcelona.eu.
Jazyk: angličtina
Zdroj: Trends in cognitive sciences [Trends Cogn Sci] 2021 Jul; Vol. 25 (7), pp. 582-595. Date of Electronic Publication: 2021 Apr 24.
DOI: 10.1016/j.tics.2021.03.016
Abstrakt: Biological cognition is based on the ability to autonomously acquire knowledge, or epistemic autonomy. Such self-supervision is largely absent in artificial neural networks (ANN) because they depend on externally set learning criteria. Yet training ANN using error backpropagation has created the current revolution in artificial intelligence, raising the question of whether the epistemic autonomy displayed in biological cognition can be achieved with error backpropagation-based learning. We present evidence suggesting that the entorhinal-hippocampal complex combines epistemic autonomy with error backpropagation. Specifically, we propose that the hippocampus minimizes the error between its input and output signals through a modulatory counter-current inhibitory network. We further discuss the computational emulation of this principle and analyze it in the context of autonomous cognitive systems.
Competing Interests: Declaration of Interests The authors declare no conflicts of interest.
(Copyright © 2021 Elsevier Ltd. All rights reserved.)
Databáze: MEDLINE
Externí odkaz: