Learning Dynamics of Cognitive Parallel Processing Based on a Collective Evaluation - Archive ouverte HAL Access content directly
Journal Articles IEEE Computer Society Year : 2019

Learning Dynamics of Cognitive Parallel Processing Based on a Collective Evaluation

Abstract

Learning dynamics at cognitive process level is difficult to study and emulate because of the complexity of intricate psychological and neuronal mechanisms and dynamics. When considering the parallel processing of a task, the difficulty relies on the execution concurrency making the process contributions indistinguishable. We present here a metric for rewarding increasingly the right parallel cognitive processes with respect to the wrong ones through learning steps. The metric, based on the symmetric difference between task parallel processes, proves to correctly achieve collective and individual credit assignment of the processes.
Fichier principal
Vignette du fichier
Sabri & Muzy. IEEE ICCICC'19-Proceedings.pdf (428.8 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-02277010 , version 1 (03-09-2019)

Identifiers

  • HAL Id : hal-02277010 , version 1

Cite

Oussama Sabri, Alexandre Muzy. Learning Dynamics of Cognitive Parallel Processing Based on a Collective Evaluation. IEEE Computer Society, 2019, Proceedings of The 18th IEEE International Conference on Cognitive Informatics & Cognitive Computing. ⟨hal-02277010⟩
205 View
159 Download

Share

Gmail Facebook X LinkedIn More