Stochastic connection neural networks
J. Zhao · 1995
In this paper we investigate a novel neural network model which uses stochastic weights. It is shown that the functionality of the network is comparable to that of a general stochastic neural network using standard sigmoid activation functions. For the multi-layer feedforward structure we demonstrate the network can be successfully used to solve a real problem like handwritten digit recognition. It is also shown that the recurrent network is as powerful as a Boltzmann machine. A new technique to implement simulated annealing is presented. Simulation results on the graph bisection problem demonstrate the model is efficient for global optimization.