Using a new brain-like artificial neural network to realize fear learning and classical conditioning

Subjects: Psychology >> Physiological Psychology Subjects: Computer Science >> Other Disciplines of Computer Science submitted time 2020-08-07

位东涛 王国清

Abstract： Neuroscience have great inspiration for artificial intelligence. By drawing on the research results of these disciplines, we designed a new artificial neural network to simulate the amygdala in human brain. The neural network consists of two parts, a long-term memory network and a activation network. The memory network records the neurons sending and receiving signals and the weight between them, while the activation network records the neurons sending and receiving signals and the time point when the signals were sent. The activation network retains only a short time memory of the event and modifies the weights in the long-term memory network according to the set rules. Using this approach, we have successfully endows the agent the ability of fear emotion learning and classical conditioning learning, which is very similar to the ability of amygdala".

Peer Review Status:Awaiting Review

 Hits 8603  Downloads 1689  Comment 2