Higher Cognitive Functions in Bio-Inspired Artificial Intelligence - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Journal Articles ERCIM News Year : 2021

Higher Cognitive Functions in Bio-Inspired Artificial Intelligence

Frédéric Alexandre
Xavier Hinaut
Nicolas P. Rougier
Thierry Viéville

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.
Fichier principal
Vignette du fichier
03-alexandre - final.pdf (166.42 Ko) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

hal-03189215 , version 1 (02-04-2021)

Identifiers

  • HAL Id : hal-03189215 , version 1

Cite

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

Share

Gmail Mastodon Facebook X LinkedIn More