International Journal of Engineering and Techniques - Volume 3 Issue 4, July-Aug 2017 ISSN: 2395-1303 http://www.ijetjournal.org Page 86 Neural Networks for Shortest Path Computation and Routing in Computer Networks R.Karthikeyan 1 , Dr.T.Geetha 2 , Thamaraiselvi V 3 , Tharani V 4 1,2 Asst.Prof, Dept of MCA, Gnanamani college of Technology, Namakkal, INDIA. 3.4 P.G.Scholar, Dept of MCA, Gnanamani college of Technology, Namakkal, INDIA. I.INTRODUCTION Mobile ad hoc network (MANET) is a self- organizing and self-configuring multihop wireless network, which is collected of a set of Mobile Hosts (MHs) that can move around freely and cooperate in spreading packets on behalf of one another. MANET supports robust and proficient operations by combining the routing functionality into MHs. In MANETs, the unicast routing establishes a multihop forwarding path for two nodes beyond the direct wireless communiqué range. Routing protocols also maintain connectivity when links on these paths break due to personal property such as node movement, battery drainage, radio proliferation, and wireless interference. In multihop networks, routing is one of the most important issues that have a significant impact on the presentation of networks. So far, there are mainly two types of routing protocols in MANETs, namely, topological routing and geographic routing. In the topological routing, mobile nodes utilize the topological information to construct routing tables or search routes directly. In the geographic routing, each node knows its own position and makes routing decisions based on the position of the destination and the positions of its local neighbors. Here, I adapt and considerquite a few genetic algorithms (GAs) that are developed to deal with general DOPs to solve the DSPRP in MANETs. First, I design the constituents of the standard GA (SGA) specifically for the DSPRP. Then, I integrate several refugees and memory schemes and their combination into the GA to enhance its searching capacity for the SPs in dynamic environments. Once the topology is changed, new immigrants or the useful information stored in the memory can help guide the search of good solutions in the new environment. Our second part details about literature survey. Our third part details about system architecture. Our forth part details about critical analysis. Our fifth part details about conclusion. Our sixth part details about reference. II.LITERATURE SURVEY: [1]A near-optimal routing algorithm employing a modified Hopfield neural network (HNN) is presented. Since it uses every piece of information that is available at the peripheral neurons, in addition to the highly correlated information that is available at the local neuron, faster coming together and better route optimality is achieved than with existing algorithms that employ the HNN. Besides, all the results are reasonably independent of network topology for almost all source-destination pairs. [2] This paper presents a new neural network to solve comparisons with similar techniques from literature, for static and dynamic environment, prove that mmEA technique is promising. RESEARCH ARTICLE OPEN ACCESS Abstract: Many intellectual optimization performances like Artificial Neural Networks (ANN),Genetic Algorithms (GAs), etc., were being planned to find the stagnant shortest path. Rapid expansions in the wireless communication predominantly in the field of mobile networks havematerialized as two major fields namely Mobile Ad hoc Networks (MANETs) and Wireless Sensor Networks (WSN). Topology elusiveness is the top most challenge in the mobile wireless network field i.e., the network topology changes over time due to energy conservancy or node mobility. In order to find the shortest path (SP) with in this network becomes a dynamic optimization problem due to nodes mobility. Nodes usually die due to low energy or it may move, this scenario makes the network to be more complex for finding shortest path. In this paper we propose a novel method of using Genetic Algorithms (GAs) to solve the dynamic shortest path discovery and routing in MANETs. MANETs is one of the faster growing new-generation wireless networks. The tentative results indicate that this GA based algorithm can quick adapt to environmental change (i.e. the network topology change) and create high quality solutions after each change.