Enhancing Logic Programming Performance in Recurrent Hopfield Network
The convergence criteria for doing neuro-symbolic integration based on hopfield network can be improved by using the new modified rule known as sign constrained method. This paper shows that the performance of the hopfield network can be improved by using sign constrained by adjusting the network synaptic weights during energy relaxation looping. The memory capacity and basin of attraction performance of these networks is empirically tested by using computer simulations. In this paper, it has been proven by computer simulations that the new approach provides good solutions.