Modeling Mechanisms of Cognition-emotion Interaction in Artificial Neural Networks, since 1981

AbstractThe paper describes modeling of cognition-emotion interaction implemented in a neural network named Crossbar Adaptive Array in 1981. The architecture was proposed to meet two challenges: solving the delayed reinforcement learning problem for neural networks, and building a self-learning system (no advice and no reinforcement from environment) based on a neural network. The architecture introduced computation of feelings, and their interaction with learning and decision making mechanisms. It also introduced genetic environment as provider of initial emotions to the neural network. Receiving initial emotions from the genetic environment, the architecture learns using the proposed emotion backpropagation mechanism. Some developments after 1981 are also discussed