A parallel computer clusters for convolutional network

Convolution neural network can gain optional solution by training dataset many times. But persons without experiments are very difficult to seek a good learning rate or a good convergence criterion. We propose a framework, which only are composed by many cheap computers, and by improved convolution network to handle this problem. In the framework, we use terminal server to dispatch initial parameter to each calculate unit (computer) and receive their final result. Single unit's collapse will not affect framework's final result, so framework has strong superiority and robustness.