2017 IEEE International Conference on Wireless Communications, Signal Processing and Networking (WiSPNET 2017)

166 / 2016-11-10 11:53:58

DEVELOPING AGENT BASED MODELLING FOR ACCELARATING NEURO-SYMBOLIC INTEGRATION WITH NEW ACTIVATION FUNCTION

This paper shows on developing agent based modelling for represent the performance of doing logic programming in Hopfield network by using a new activation function. The effects of the activation function on the performance of the neuro-symbolic integration are analyzed mathematically and compared eith the existing method. Computer simulations are carried out to validate the effectiveness on the new activation function.