Skip to Main content Skip to Navigation
Journal articles

Higher Cognitive Functions in Bio-Inspired Artificial

Frédéric Alexandre 1 Xavier Hinaut 1 Nicolas Rougier 1 Thierry Viéville 1
1 Mnemosyne - Mnemonic Synergy
LaBRI - Laboratoire Bordelais de Recherche en Informatique, Inria Bordeaux - Sud-Ouest, IMN - Institut des Maladies Neurodégénératives [Bordeaux]
Abstract : Major algorithms from artificial intelligence (AI) lack higher cognitive functions such as problem solving and reasoning. By studying how these functions operate in the brain, we can develop a biologically informed cognitive computing; transferring our knowledge about architectural and learning principles in the brain to AI. Digital techniques in artificial intelligence (AI) have been making enormous progress and offer impressive performance for the cognitive functions they model. Deep learning has been primarily developed for pattern matching, and extensions like Long Short Term Memory (LSTM) networks can identify and predict temporal sequences. Adaptations to other domains, such as deep reinforcement learning, allow complex strategies of decision-making to be learnt to optimise cumulated rewards.
Document type :
Journal articles
Complete list of metadata
Contributor : Frédéric Alexandre <>
Submitted on : Friday, April 2, 2021 - 9:59:47 PM
Last modification on : Thursday, April 8, 2021 - 3:10:07 AM


03-alexandre - final.pdf
Files produced by the author(s)


  • HAL Id : hal-03189215, version 1


Frédéric Alexandre, Xavier Hinaut, Nicolas Rougier, Thierry Viéville. Higher Cognitive Functions in Bio-Inspired Artificial. ERCIM News, ERCIM, 2021, Special topic "Brain inspired computing", 125. ⟨hal-03189215⟩



Record views


Files downloads