Title :
How Emotional Mechanism Learn and Helps Other Types of Learning in a Cognitive Agent
Author :
Faghihi, Usef ; Poirier, Pierre ; Dubois, Daniel ; Nkambou, Roger
Author_Institution :
Dept. of Comput. Sci., Univ. of Quebec in Montreal, Montreal, QC
Abstract :
Research in human neurobiology sustains the idea that emotions play a role, sometimes crucial, in most decisions and actions taken. Every input from perceptual mechanism passes through the amygdala before affecting action selection, sometimes temporarily bypassing detailed cortical interpretation. We describe our reproduction of these emotional mechanisms in our cognitive autonomous agent, CTS (Conscious Tutoring System), and hint at repercussions on its tutoring behaviors. The model replicates the amygdalapsilas emotional influence over different parts of the system as a means of preparing the system for action, biasing action selection, and improving the agent´s self-resilience in an unknown or changing environment. It all sums up to a way of improving the agentpsilas fitness and autonomy.
Keywords :
cognitive systems; learning (artificial intelligence); cognitive agent; conscious tutoring system; emotional mechanism; self-resilience; Autonomous agents; Brain; Cognition; Emotion recognition; Humans; Intelligent agent; Leg; Legged locomotion; Mediation; Neuroscience; Tutoring System; cognitive agent; consciousness; emotional mechanisms;
Conference_Titel :
Web Intelligence and Intelligent Agent Technology, 2008. WI-IAT '08. IEEE/WIC/ACM International Conference on
Conference_Location :
Sydney, NSW
Print_ISBN :
978-0-7695-3496-1
DOI :
10.1109/WIIAT.2008.59