Stochastic neural computation II: Soft competitive learning

An investigation has been made into the use of stochastic arithmetic to imp lement an artificial neural network solution to a typical pattern recogniti on application. Optical character recognition is performed on very noisy ch aracters in the E-13B MICR font. The artificial neural network is composed of two layers, the first layer being a set of soft competitive learning sub networks and the second a set of fully connected linear output neurons. The observed number of clock cycles in the stochastic case represents an order of magnitude improvement over the floating-point implementation assuming c lock frequency parity. Network generalization capabilities were also compar ed based on the network squared error as a function of the amount of noise added to the input patterns. The stochastic network maintains a squared err or within 10 percent of that of the floating-point implementation for a wid e range of noise levels.