How to apply PSO in Artificial Neural Network

Question

I have a problem to understand the concept of the Particle Swarm Algorithm. for writing the code we scatter some articles into our space and trying to find a place (for example min of a function or desire target). based on position, velocity and so on all particles finally reach the place that we wanted. now I have a problem How to apply this code into my ANN design?

How it could help the Neural Network?(it seems that PSO has strong ability to find global optimist result and Back propagation has ability to find the local, am I right?)

I would appreciate if you give me any information that help me to understand. Thanks in Advance

Answer 1

Finally I have found the answer. we should use PSO to Train the neural network and find the weights. by applying this kind of Evolutionary Algorithms the process of training could be short.having said that PSO has strong ability to find global optimist result and Back propagation has ability to find the local.

For doing so reaching the place is not important at all, just we need to check the output and base on it decide which particle is the best.

Hope I explain it properly.