典型文献
Hyperparameter on-line learning of stochastic resonance based threshold networks
文献摘要：
Aiming at training the feed-forward threshold neural network consisting of nondifferentiable activation functions,the approach of noise injection forms a stochastic resonance based threshold network that can be optimized by various gradient-based optimizers.The introduction of injected noise extends the noise level into the parameter space of the designed threshold network,but leads to a highly non-convex optimization landscape of the loss function.Thus,the hyperparameter on-line learning procedure with respective to network weights and noise levels becomes of challenge.It is shown that the Adam optimizer,as an adaptive variant of stochastic gradient descent,manifests its superior learning ability in training the stochastic resonance based threshold network effectively.Experimental results demonstrate the significant improvement of performance of the designed threshold network trained by the Adam optimizer for function approximation and image classification.
文献关键词：
中图分类号：
作者姓名：
Weijin Li;Yuhao Ren;Fabing Duan
作者机构：
College of Automation,Qingdao University,Qingdao 266071,China
文献出处：
引用格式：
[1]Weijin Li;Yuhao Ren;Fabing Duan-.Hyperparameter on-line learning of stochastic resonance based threshold networks)[J].中国物理B（英文版）,2022(08):322-328
A类：
Hyperparameter,nondifferentiable,hyperparameter
B类：
line,learning,stochastic,resonance,threshold,networks,Aiming,training,feed,forward,neural,consisting,activation,functions,approach,noise,injection,forms,that,optimized,by,various,gradient,optimizers,introduction,injected,extends,into,space,designed,but,leads,highly,convex,optimization,landscape,loss,Thus,procedure,respective,weights,levels,becomes,challenge,It,shown,Adam,adaptive,variant,descent,manifests,its,superior,ability,effectively,Experimental,results,demonstrate,significant,improvement,performance,trained,approximation,image,classification
AB值：
0.525472
相似文献
机标中图分类号，由域田数据科技根据网络公开资料自动分析生成，仅供学习研究参考。
