Stochastic computation uses pulse streams to represent numbers. In this paper, we have studied the novel method to implement the number system which uses the ratio of the number of one(high) pulses and the number of zero(1ow) pulses in a pulse stream. With this number system, if we let P be the probability that the pulse is one in a pulse stream, then the number Y we want to deal with is defined as Y=P/(l-P). We have studied the method to implement the basic operations such as an addition, a multiplication and a division using this number system and considered the error characteristics of such operations in stochastic computation. And we introduce an averaging circuit to reduce the error which is inherent in the stochastic computation. According to the study using this number system we implement artificial neural network and represent the simulation results about the digit recognition problem.