I'm developing a program to recognize a character from a image using OCR techniques. Up till now I have used a method that scanned the image, but now I have to use neural networks. Please explain what is a single layer perceptron and how to use it to train the network.
I typed a portion of your question into Google: http://en.wikipedia.org/wiki/Feedforward_neural_network
You might also use this CodeProject article, Creating Optical Character Recognition (OCR) applications using Neural Networks, as a starting point.
Sounds like a basic explanation on Perceptron / Artificial Neural Network may help you. I wrote an article "An Intuitive Example of Artificial Neural Network (Perceptron) Detecting Cars / Pedestrians from a Self-driven Car"
You can check. Hopefully you will find it useful.