Convergence for fuzzy δ rules in a special stochastic input sample
Mingchen Yao · Journal of Natural Science of Heilongjiang University · 2013
Convergence for fuzzy δ rules in a special stochastic input sample is presented under the fuzzily separable condition.Here special stochastic order means that the samples supplied to the network is cycle by cycle,and in each cycle samples is stochastically chosen.Weights sequence is proved to be monotonous decrease in the training process and learning rates are provided to guarantee its convergence.