In certain cases, noises can improve signal transmission or signal processing. This phenomenon is the so-called stochastic resonance. In this paper, we firstly present two theorems to prove that the noisy threshold ne...In certain cases, noises can improve signal transmission or signal processing. This phenomenon is the so-called stochastic resonance. In this paper, we firstly present two theorems to prove that the noisy threshold neuron shows stochastic resonance in terms of the probability of correct reception. Secondly, we analytically discuss stochastic resonance effects and give the probability-optimal noise levels for four representative noises. Finally, we discuss the stochastic gradient ascent learning law, which can be used to find the probability-optimal noise levels. We also present our simulation results for the four representative noises. These results indicate that stochastic resonance is favorable both in biological neurons and in signal processing.展开更多
In this paper, based on a stochastic mode! for inputs and weights, and in view of the disturbance of correlative and large input and weight errors, a general algorithm to obtain the output error characteristics of a c...In this paper, based on a stochastic mode! for inputs and weights, and in view of the disturbance of correlative and large input and weight errors, a general algorithm to obtain the output error characteristics of a class of multilayered perceptrons with threshold functions is proposed by using statistical approach. Furthermore, the formula to calculate the robustness of the networks is also given. The result of computer simulation indicates the correctness of the algorithm.展开更多
文摘In certain cases, noises can improve signal transmission or signal processing. This phenomenon is the so-called stochastic resonance. In this paper, we firstly present two theorems to prove that the noisy threshold neuron shows stochastic resonance in terms of the probability of correct reception. Secondly, we analytically discuss stochastic resonance effects and give the probability-optimal noise levels for four representative noises. Finally, we discuss the stochastic gradient ascent learning law, which can be used to find the probability-optimal noise levels. We also present our simulation results for the four representative noises. These results indicate that stochastic resonance is favorable both in biological neurons and in signal processing.
基金National Science Foundation of Chinathe Doctoral Fund of the State Education Commission of China
文摘In this paper, based on a stochastic mode! for inputs and weights, and in view of the disturbance of correlative and large input and weight errors, a general algorithm to obtain the output error characteristics of a class of multilayered perceptrons with threshold functions is proposed by using statistical approach. Furthermore, the formula to calculate the robustness of the networks is also given. The result of computer simulation indicates the correctness of the algorithm.