Different learning architectures contribute to value prediction in human cognition

Frédéric Alexandre 1
1 Mnemosyne - Mnemonic Synergy
LaBRI - Laboratoire Bordelais de Recherche en Informatique, Inria Bordeaux - Sud-Ouest, IMN - Institut des Maladies Neurodégénératives [Bordeaux]
Abstract : Pavlovian conditioning plays a fundamental role in our cog-nitive architecture, by its capacity to bind values to stimuli. Due to the multifarious characteristics of this learning mode, many approaches in machine learning have been proposed to implement it in artificial intelligence models. Considering the complementary properties of these models and inspired by biological evidences, we propose not to select the best model but rather to combine them, thereby forming a cognitive architecture. From a functional point of view, we report the good properties and performances of this architecture. From a methodological point of view, this work highlights the interest of defining a cognitive function at the algorithmic level, binding its general properties to its implementation details. It is also proposed that it is a fruitful approach to decipher and organize many information extracted by modern approaches in neu-roscience, towards the definition of a global cognitive architecture.
Document type :
Conference papers
Liste complète des métadonnées

https://hal.inria.fr/hal-01931492
Contributor : Frédéric Alexandre <>
Submitted on : Thursday, November 22, 2018 - 7:49:16 PM
Last modification on : Saturday, November 24, 2018 - 1:23:59 AM
Document(s) archivé(s) le : Saturday, February 23, 2019 - 3:31:11 PM

File

AlexandreAIC_2018.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01931492, version 1

Citation

Frédéric Alexandre. Different learning architectures contribute to value prediction in human cognition. AIC 2018 : 6th International Workshop on Artificial Intelligence and Cognition, Jul 2018, Palermo, Italy. ⟨hal-01931492⟩

Share

Metrics

Record views

28

Files downloads

33