Combination of Multiple Neural Networks to Solve Travelling Salesman Problem using Genetic Algorithm
Anmol Aggarwal, Jasdeep Singh Bhalla · International Journal of Computer Applications · 2013
In this paper, the already recognized NP Complete problem which is Travelling Salesman Problem which is also known as TSP, is addressed and its performance is analyzed.For a large and complex data set, a particular neural network is needed to focus on a particular component of the problem, after which combining of all the networks together is required.The basic ideology behind this multiple neural network arrangement is that, n-independently different neural networks are trained separately and then their respective outputs (generated independently) are combined together to form the resultant classifier.A new combining technique (for combining outputs of multiple neural networks into one) has been proposed and utilized for evidence blend in the simulation part of the method.Its performance is analyzed on the bases of simulation and it shows some notably enhanced outcomes.