Learning Dynamics of Cognitive Parallel Processing Based on a Collective Evaluation

Oussama Sabri (1, 2) , Alexandre Muzy (3, 2)

1 I3S - Laboratoire d'Informatique, Signaux, et Systèmes de Sophia Antipolis
2 COMUE UCA - COMUE Université Côte d'Azur (2015-2019)
3 CNRS - Centre National de la Recherche Scientifique

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.

Mots clés: Learning dynamics; Cognitive task; Parallel processing; Collective credit assignment

Domaines: Informatique; Intelligence artificielle [cs.AI]

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⟩