Reducing the number of multiplies in backpropagation

There have been many algorithms to speed up the learning time of backpropagation. However, most of them do not take into consideration the amount of hardware required to implement the algorithm. Without suitable hardware implementation, the real promise of neural network applications will be difficult to achieve. Since multiply dominates computation and is expensive in hardware, this paper proposes a method to reduce the number of multiplies in the backward path of backpropagation algorithm by setting some neuron errors to zero. It proves the convergence theorem by the general Robbins-Monro process, a stochastic approximation process