Shortest Path Using Neural Network

Shortest path problem is solved by using the famous Dijkstra's algorithm, which would quickly provide a global optimization solution in most instances. But when the weight is not given, this method does not work. This research paper examines and analyzes the use of neural networks for finding the weights. A neural network is an artificial representation of human brain that tries to simulate the learning process. It is also called a simulated neural network (SNN) or commonly just neural networks (NN), which are massively parallel models, can solve this question easily. A neural-net-inspired non-von-Neumann architecture which implements Dijkstra's dynamic programming algorithm to find the shortest path between two given nodes in a graph is presented.