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.     

Toward Fuzzy Optimization without Mathematical Ambiguity

Fuzzy programming has been discussed widely in literature and applied in such various disciplines as operations research, economic management, business administration, and engineering. The main purpose of this paper is to present a brief review on fuzzy programming models, and classify them into three broad classes: expected value model, chance-constrained programming and dependent-chance programming. In order to solve general fuzzy programming models, a hybrid intelligent algorithm is also documented. Finally, some related topics are discussed.     

模糊对向传播网络数据融合目标识别方法

重点研究了模糊对向传播网络 (FCPN)模型。针对数据融合和目标识别的特点 ,提出了基于模糊对向传播网络的融合目标识别方法和改进的模糊对向传播网络 (MFCPN)融合结构。利用仿真数据对网络的训练算法和融合结构进行了实验研究。结果表明 ,模糊对向传播网络较误差后向传播网络 (BPN)能够有效地实现融合识别 ;改进的模糊对向传播网络融合结构是可行的。同时还对FCPN和MFCPN应用于前视红外 (FLIR)和可见光摄像机目标跟踪系统进行了应用研究。     

Time Series Prediction Based on Chaotic Attractor

A new prediction technique is proposed for chaotic time series. The usefulness of the technique is thatit can kick off some false neighbor points which are not suitable for the local estimation of the dynamics systems. Atime-delayed embedding is used to reconstruct the underlying attractor, and the prediction model is based on the timeevolution of the topological neighboring in the phase space. We use a feedforward neural network to approximate thelocal dominant Lyapunov exponent, and choose the spatial neighbors by the Lyapunov exponent. The model is testedfor the Mackey-Glass equation and the convection amplitude of lorenz systems. The results indicate that this predictiontechnique can improve the prediction of chaotic time series.     

带惩罚项与随机输入的BP神经网络在线梯度学习算法的收敛性

本文对三层BP神经网络中带有惩罚项的在线梯度学习算法的收敛性问题进行了研究,在网络训练每一轮开始执行之前,对训练样本随机进行重排,以使网络学习更容易跳出局部极小,文中给出了误差函数的单调性定理以及该算法的弱收敛和强收敛性定理。     

基于进化人工神经网络的组合系统滤波技术

在组合系统运用Kalman滤波器技术时,准确的系统模型和可靠的观测数据是保证其性能的重要因素,否则将大大降低Kalman滤波器的估计精度,甚至导致滤波器发散.为解决上述Kalman应用中的实际问题,提出了一种新颖的基于进化人工神经网络技术的自适应Kalman滤波器.仿真试验表明该算法可以在系统模型不准确时、甚至外部观测数据短暂中断时,仍能保证Kalman滤波器的性能.     

农户信用评估系统的设计与运用研究

农户信用评估的研究对推动农村消费信用的发展，促进农村经济良好运行十分重要。本在构造农户信用评估的指标体系的基础上，提出了农户信用评估神经网络模型的算法，利用实际搜集到的农户资料进一步建立了农户信用评估模型，继而构造了农户信用评估系统，并举例说明了该系统的实际运用，以期能为农村经济发展中的农户信用评价及相关研究提供一丝基础性启发。     

基于径向基函数神经网络的Lorenz混沌系统滑模控制

针对受参数不确定和外扰影响的混沌Lorenz系统，提出一种基于径向基函数（RBF）神经网 络的滑模控制方法.基于被控系统在不稳定平衡点处状态误差的可控规范形，设计滑模切换 面并将其作为神经网络的唯一输入.单入单出形式的RBF控制器隐层只需7个径向基函数，网 络的权值则依滑模趋近条件在线确定.仿真表明该控制器对系统参数突变和外部干扰具有鲁棒性，同时抑制了抖振. 关键词： 混沌控制 滑模 径向基函数神经网络 Lorenz系统     

神经网络法计算镉（Ⅱ）,羟基及碳酸根三元体系的形态分布

采用前馈线笥网络ＢＰ算法，计算了Ｃｄ６２＋－ＯＨ＾－ＣＯ＾２－３三元体系的累积稳定常数。用Ｈｏｐｆｉｅｌｄ反馈网络研究了体系中络合物的形态分布。溶液中溶解的ＣＯ２对ｌｇβ１的计算结果有重要影响，对ｌｇβ２，ｌｇβ３，ｌｇβ４的结果影响不大。     

Max—min神经网络的一种有效学习算法

本文在Ａ．Ｂｌａｎｃｏ等人的算法的基础上，提出了ｍａｘ－ｍｉｎ神经网络的一种改进了的反馈学习算法，严格证明了该算法的迭代收敛性，理论分析及实例计算结果均表明，本文算法具有算法简单，收敛速度快，输出误差小等显著特点。