Saratha Sathasivam

Learn More
Intelligent systems are yielded from integration of a logic programming and connectionist systems. Radial basis function neural network is a commonly-used type of feedforward networks. In this paper, we proposed a method for connectionist model generation using Radial Basis Function neural network to encode higher order logic programming. We encode each(More)
Particle swarm optimization (PSO) is employed to investigate the overall performance of a pin fin.The following study will examine the effect of governing parameters on overall thermal/fluid performance associated with different fin geometries, including, rectangular plate fins as well as square, circular, and elliptical pin fins. The idea of entropy(More)
The Little-Hopfield neural network programmed with Horn clauses is studied. We argue that the energy landscape of the system, corresponding to the inconsistency function for logical interpretations of the sets of Horn clauses, has minimal ruggedness. This is supported by computer simulations. 1.INTRODUCTION Recurrent single field neural networks are(More)
In recent studies on artificial intelligence, logic program occupies a significant position because of its attractive features. Neural networks are dynamic systems in the learning and training phase of their operation and convergence is an essential feature, so it is necessary for the researchers developing the models and their learning algorithms to find a(More)
There are two ways to calculate synaptic weights for neurons in logic programming. There are by using Hebbian learning or by Wan Abdullah's method. Hebbian learning for governing events corresponding to some respective program clauses is equivalent with learning using Wan Abdullah's method for the same respective program clauses. We will evaluate(More)