Activation Functions in Neuro Symbolic Integration Using Agent Based Modelling

Logic program and neural networks are two important aspects in artificial intelligence. This paper is part of an endeavour towards neural networks and logic programming integration. The goal in performing logic programming based on the energy minimization scheme is to achieve the best ratio of global minimum. However, there is no guarantee to find the best minimum in the network. To achieve this, activations functions are modified to accelerate the neuro symbolic integration. These activation functions will reduced the complexity of doing logic programming in Hopfield Neural Network (HNN).The activations functions discussed in this paper are new learning rule, Mc Culloch Pitts function and Hyperbolic Tangent Activation function. This paper also focused on agent based modelling for presenting performance of doing logic programming in Hopfield network using various activation functions. The effects of the activation function are analyzed mathematically and compared with the existing method. Computer simulations are carried out by using NETLOGO to validate the effectiveness on the new activation function. The resuls obtained showed that the Hyperbolic Tangent Activation function outperform other activation functions in doing logic programming in Hopfield network. The models developed by agent based modelling also support this theory