Computational Model Of Social Intelligence Based On Emotional Learning In The Amygdala

Abstract

Today, neural systems are being applied as a powerful tool to solve a host of problems. The more computational model of the presented neural system and the neural system of animals look alike, the more powerful the computational model would be. The brain emotional learning algorithm in the Amygdala inspired by Limbic of mammalian brains was put forward originally by Mor´en. A combination of some Limbic systems as some living creatures will be applied in this paper. The gathering of these living creatures and output summation of each Limbic system in accordance with the relevant applied coefficient will result in social intelligence. The proposed model has been compared with feed-forward back propagation network, Elman back propagation network, and a computational model of emotional learning in the Amygdala to forecast Mackey-Glass Chaotic Time Series. The results of the above mentioned comparison concludes that in forecasting Mackey-Glass Chaotic Time Series, the computational model of social intelligence based on the emotional learning in the Amygdala has shown fewer errors in not only training patterns but also testing patterns.