Simultaneous perturbation stochastic approximation （SPSA） belongs to the class of gradient-free optimization methods that extract gradient information from successive objective function evaluation. This paper descri...Simultaneous perturbation stochastic approximation （SPSA） belongs to the class of gradient-free optimization methods that extract gradient information from successive objective function evaluation. This paper describes an improved SPSA algorithm, which entails fuzzy adaptive gain sequences, gradient smoothing, and a step rejection procedure to enhance convergence and stability. The proposed fuzzy adaptive simultaneous perturbation approximation （FASPA） algorithm is particularly well suited to problems involving a large number of parameters such as those encountered in nonlinear system identification using neural networks （NNs）. Accordingly, a multilayer perceptron （MLP） network with popular training algorithms was used to predicate the system response. We found that an MLP trained by FASPSA had the desired accuracy that was comparable to results obtained by traditional system identification algorithms. Simulation results for typical nonlinear systems demonstrate that the proposed NN architecture trained with FASPSA yields improved system identification as measured by reduced time of convergence and a smaller identification error.展开更多
With the continuous optimization of mobile intelligent mode,the internet has gradually entered the era of visualization.This paper briefly summarizes the reasons and current situation of the rapid development of mains...With the continuous optimization of mobile intelligent mode,the internet has gradually entered the era of visualization.This paper briefly summarizes the reasons and current situation of the rapid development of mainstream media short films,analyzes the composition and functions of mainstream media short video online reviews,and probes into the rules of mainstream media short video online reviews.展开更多
文摘Simultaneous perturbation stochastic approximation （SPSA） belongs to the class of gradient-free optimization methods that extract gradient information from successive objective function evaluation. This paper describes an improved SPSA algorithm, which entails fuzzy adaptive gain sequences, gradient smoothing, and a step rejection procedure to enhance convergence and stability. The proposed fuzzy adaptive simultaneous perturbation approximation （FASPA） algorithm is particularly well suited to problems involving a large number of parameters such as those encountered in nonlinear system identification using neural networks （NNs）. Accordingly, a multilayer perceptron （MLP） network with popular training algorithms was used to predicate the system response. We found that an MLP trained by FASPSA had the desired accuracy that was comparable to results obtained by traditional system identification algorithms. Simulation results for typical nonlinear systems demonstrate that the proposed NN architecture trained with FASPSA yields improved system identification as measured by reduced time of convergence and a smaller identification error.
基金Research on media short videos’impact on public opinions(Project No.:2018wtscx235)--A characteristic innovation project of colleges and universities in Guangdong province in 2018.
文摘With the continuous optimization of mobile intelligent mode,the internet has gradually entered the era of visualization.This paper briefly summarizes the reasons and current situation of the rapid development of mainstream media short films,analyzes the composition and functions of mainstream media short video online reviews,and probes into the rules of mainstream media short video online reviews.
