Hyperparameter on-line learning of stochastic resonance based threshold networks

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.     

非同分布φ混合序列加权和的强极限收敛性

利用φ混合序列矩不等式和截尾的处理方法,研究非同分布φ混合序列加权和强极限收敛性质的问题,得到了若干新结果,推广并改进了独立同分布情形下的相应结果.     

Recent Progress in the $L_p$ Theory for Elliptic and Parabolic Equations with Discontinuous Coefficients

In this paper, we review some results over the last 10-15 years on elliptic and parabolic equations with discontinuous coefficients. We begin with an approach given by N. V. Krylov to parabolic equations in the whole space with $\rm{VMO}_x$ coefficients. We then discuss some subsequent development including elliptic and parabolic equations with coefficients which are allowed to be merely measurable in one or two space directions, weighted $L_p$estimates with Muckenhoupt ($A_p$) weights, non-local elliptic and parabolic equations, as well as fully nonlinear elliptic and parabolic equations.     

An Improved Composite Multiscale Fuzzy Entropy for Feature Extraction of MI-EEG

Motor Imagery Electroencephalography (MI-EEG) has shown good prospects in neurorehabilitation, and the entropy-based nonlinear dynamic methods have been successfully applied to feature extraction of MI-EEG. Especially based on Multiscale Fuzzy Entropy (MFE), the fuzzy entropies of the τ coarse-grained sequences in τ scale are calculated and averaged to develop the Composite MFE (CMFE) with more feature information. However, the coarse-grained process fails to match the nonstationary characteristic of MI-EEG by a mean filtering algorithm. In this paper, CMFE is improved by assigning the different weight factors to the different sample points in the coarse-grained process, i.e., using the weighted mean filters instead of the original mean filters, which is conductive to signal filtering and feature extraction, and the resulting personalized Weighted CMFE (WCMFE) is more suitable to represent the nonstationary MI-EEG for different subjects. All the WCMFEs of multi-channel MI-EEG are fused in serial to construct the feature vector, which is evaluated by a back-propagation neural network. Based on a public dataset, extensive experiments are conducted, yielding a relatively higher classification accuracy by WCMFE, and the statistical significance is examined by two-sample t-test. The results suggest that WCMFE is superior to the other entropy-based and traditional feature extraction methods.     

基于多变量希尔伯特频域模型的癫痫发作预测

癫痫发作具有突发性和反复性,对患者生命安全构成巨大威胁.为了对癫痫发作进行有效地预测,提出了多变量希尔伯特频域模型的癫痫发作预测方法.将希尔伯特边际谱、希尔伯特边际谱的变化方向和希尔伯特加权频率组成一个三维特征向量作为多变量希尔伯特频域模型,输入到支持相量机中,实现癫痫的发作预测,最后采用癫痫发作预测特征方法对预测结果进行评估.实验结果表明:采用多变量希尔伯特频域模型分析方法预测δ波和θ波的癫痫发作,癫痫预测范围在30~45 min,患者有足够的时间采取措施应对;癫痫发作周期在5~10 min,缩短患者等待时间,降低焦虑程度;与多种相关方法进行比较,该方法具有较低的错误预报率和较高的预测敏感度.     

惯性导航系统水平阻尼网络的自适应控制

当海况变化较大时，惯性导航系统(INS)的误差振荡幅度较大．为了减小系统误差的振荡幅度，提出了一种新的设计思想，采用自适应控制方法，根据实际的海况变化情况，实时校正阻尼参数，使由舰船的机动性造成的系统误差最小．结果表明，与传统方法相比，水平误差角振荡幅度减小了约50％，速度误差振荡幅度减小了约30％．经度、纬度和航向误差振荡幅度也有明显改善；水平阻尼网络的自适应控制有效地改善了INS的动态性能．     

NA列加权乘积和的完全收敛性

本文讨论了NA和几类加权部分和及加权乘积和的完全收敛性，其中部分结果要优于iid列的已知结论。     

用自适应脉冲微扰引导混沌系统到周期解

用自适应脉冲微扰方法控制的系统的某个系统变量作为驱动,设计了一种自适应控制器方法对两个或多个响应混沌系统进行脉冲微扰,引导这些系统从混沌运动到低周期运动,实现同时控制多个混沌系统到不同的周期态. 当选择相同的自适应控制器输入变量实施脉冲微扰时,还可控制两个或多个混沌系统达到不同的周期态同步. 通过对R?ssler混沌系统的仿真研究证实了方法的有效性. 关键词： 混沌控制 系统参量 自适应控制器 脉冲微扰 周期态同步