一种新的双权值前向神经网络学习算法

提出了一种新的基于遗传算法和误差反向传播的双权值神经网络学习算法,同时确定核心权值、方向权值以及幂参数、学习率等参数,通过适当地调节这些参数,可以实现尽可能多种不同超曲面的特性以及起到加快收敛的效果。并通过对实际的模式分类问题的仿真,将文中的方法与带动量项BP算法、CSFN等算法进行了比较,验证了其有效性。实验结果表明所提出的方法具有分类准确率高、收敛速度快的优点。     

Hybrid Feedforward Neural Networks for Solving Classification Problems

A novel multistage feedforward network is proposed for efficient solving of difficult classification tasks. The standard Radial Basis Functions (RBF) architecture is modified in order to alleviate two potential drawbacks, namely the curse of dimensionality and the limited discriminatory capacity of the linear output layer. The first goal is accomplished by feeding the hidden layer output to the input of a module performing Principal Component Analysis (PCA). The second one is met by substituting the simple linear combiner in the standard architecture by a Multilayer Perceptron (MLP). Simulation results for the 2-spirals problem and Peterson-Barney vowel classification are reported, showing high classification accuracy using less parameters than existing solutions.     

前馈神经网络的新算法及其收敛性

从一般前馈神经网络模型出发，构造出一组关于权重的非线性方程组，给出不同于传统ＢＰ算法的新型神经元算法。理论证明了该算法的收敛性，从而避免了ＢＰ算法的局限性。     

前馈神经网隐层节点的动态删除法

本文首先针对ＢＰ算法中存在的缺陷对误差函数作了简单的修改，使网络的收敛速度比原来的大大提高，此外本文提提出了一种基于线性回归分析算法来确定隐层节点数。当已训练好的网络具有过多的隐层单元，可以用这种算法来计算隐层节点输出之间的线性相关性，并估计多余隐层单元数目，然后删除这部分多余的节点，就能获得一个合适的网络结构。     

零代价函数的前馈神经网络新算法

文章提出一种全新的三层前馈神经网络算法,它比BP算法优越得多.新算法不再采用误差反向传播原理,而是选择一层自由权,通过求解线性方程组求得另一层待求权.新算法选择很广一类的隐层神经元函数,可以直接求得全局最小点,不存在BP算法的局部极小、收敛速度慢等问题.新算法较BP算法快得多.     

一种训练前馈神经网络的局部线性化最小二乘算法

提出了一种新的训练前馈神经网络的局部线性化最小二乘算法。新算法将整个网络的权值训练看作非线性系统的参数识别，并将非线性系统的全局参数识别转化为一系列局部子系统的参数识别，最终将局部子系统的参数识别转化为线性化的最小二乘问题。     

基于粗糙集理论的RBF神经网络剪枝算法

分析了满足给定学习误差要求的最小结构神经网络的各种实现方法.把粗糙集理论引入神经网络的结构构造中;提出了一种基于粗糙集理论的RBF神经网络剪枝算法,并将这种算法与现有剪枝算法相比较.最后将该算法应用于热工过程中过热气温动态特性建模.仿真结果表明基于该算法的神经网络模型具有较高的建模精度以及泛化能力.     

Optimizing Deep Feedforward Neural Network Architecture: A Tabu Search Based Approach

Neural Processing Letters - The optimal architecture of a deep feedforward neural network (DFNN) is essential for its better accuracy and faster convergence. Also, the training of DFNN becomes...     

Political Optimizer Based Feedforward Neural Network for Classification and Function Approximation

Neural Processing Letters - Political optimizer (PO) is a recently proposed human-behavior inspired meta-heuristic, which has shown tremendous performance on complex multimodal functions as well as...     

A Hybrid Training Algorithm for Feedforward Neural Networks

Feedforward neural networks (FNN) have been proposed to solve complex problems in pattern recognition, classification and function approximation. Despite the general success of learning methods for FNN, such as the backpropagation (BP) algorithm, second-order algorithms, long learning time for convergence remains a problem to be overcome. In this paper, we propose a new hybrid algorithm for a FNN that combines unsupervised training for the hidden neurons (Kohonen algorithm) and supervised training for the output neurons (gradient descent method). Simulation results show the effectiveness of the proposed algorithm compared with other well-known learning methods.     

一种新型拉格朗日神经网络解决非光滑优化问题

针对函数是非光滑的问题以及采用固定惩罚项的弊端,利用 Clarke广义梯度的理论和lagrange乘子法的思想,建立了一个微分包含的神经网络模型。此模型是采用罚函数的方法,有效避免了固定项的缺陷。理论证明了网络是有全局解的,并且收敛到原问题的关键点集,对于凸问题来说网络收敛的平衡点就是问题的最优点。最后通过仿真实验验证了理论结果的正确性。     

A Simple Neural Network Pruning Algorithm with Application to Filter Synthesis

This paper describes an approach to synthesizing desired filters using a multilayer neural network (NN). In order to acquire the right function of the object filter, a simple method for reducing the structures of both the input and the hidden layers of the NN is proposed. In the proposed method, the units are removed from the NN on the basis of the influence of removing each unit on the error, and the NN is retrained to recover the damage of the removal. Each process is performed alternately, and then the structure is reduced. Experiments to synthesize a known filter were performed. By the analysis of the NN obtained by the proposed method, it has been shown that it acquires the right function of the object filter. By the experiment to synthesize the filter for solving real signal processing tasks, it has been shown that the NN obtained by the proposed method is superior to that obtained by the conventional method in terms of the filter performance and the computational cost.     

实数编码遗传算法的前向神经网络优化设计

提出一种综合控制策略的实数编码遗传算法,用该算法实现对前向网络结构及权值的同时优化设计。用非线性函数的逼近问题作仿真实验。结果表明,该算法能快速有效地确定网络结构及权值。     

基于DMDE算法的前向神经网络设计

针对神经网络结构与参数并行优化问题,提出一种基于动态多群体差分进化算法的前向神经网络设计方法。采用分层递阶结构原理构造算法个体,根据控制基因信息将个体分成不同的动态群体。通过对个体进行重构,实现进化过程中个体信息的充分交换与共享。设计基于群体适应度的控制基因更新方法来优化网络拓扑结构,克服结构优化的盲目与低效问题。将所设计的神经网络应用于大包线飞行控制律参数拟合中。仿真结果表明,该算法能快速有效地确定神经网络的结构和权值,所优化的网络在调参控制中具有较好的泛化能力。     

基于Kalman滤波的神经网络学习算法及其应用

针对传统神经网络学习算法速度慢、容易陷入局部最优解的缺点,将卡尔曼滤波应用于人工神经网络的训练算法中。同时,在卡尔曼滤波计算中,将奇异值分解应用于卡尔曼滤波的递推公式中,提高了协方差阵计算的数值稳定性。最后,本文通过将神经网络的卡尔曼滤波算法应用于电力系统短期负荷预测中,验证了该方法不仅具有理论意义,同时也有实用价值。     

A Neural Network Parallel Algorithm for Meeting Schedule Problems

A parallel algorithm for solving meeting schedule problems is presented in this paper where the problem is NP-complete. The proposed system is composed of two maximum neural networks which interact with each other. One is an M × S neural network to assign meetings to available time slots on a timetable where M andS are the number of meetings and the number of time slots, respectively. The other is an M × P neural network to assign persons to the meetings where P is the number of persons. The simulation results show that the state of the system always converges to one of the solutions. Our empirical study shows that the solution quality of the proposed algorithm does not degrade with the problem size.     

多层前向神经网络的新型二阶学习算法

提出了多层前向神经网络的新型二阶递推学习算法。该算法不仅能使用网络各层误差而且使二阶导数信息因子反向传播。证明了新算法等价于Ｎｅｗｔｏｎ迭代法并且有二阶收敛速度。它实现了Ｎｅｗｔｏｎ搜索方向和Ｈｅｓｓｉａｎ阵逆的递推运算,其计算量几乎与普通递推最小二乘法相当。由算法性能分析证明新算法优于Ｋａｒａｙｉａｎｎｉｓ等人的二阶学习算法。     

基于免疫遗传算法的前向神经网络设计

针对传统BP算法训练速度慢、易陷入局部最优等缺点,该文提出了一种采用免疫遗传算法设计前向神经网络的方法。为解决神经网络权值随机初始化带来的问题,介绍了一种基于免疫的多样性模拟退火法(SAND算法)来进行神经网络权值初始化。仿真结果表明,该算法比混合遗传算法有更高的性能。     

一种多层前馈网参数可分离学习算法

目前大部分神经网络学习算法都是对网络所有的参数同时进行学习.当网络规模较大时,这种做法常常很耗时.由于许多网络,例如感知器、径向基函数网络、概率广义回归网络以及模糊神经网络,都是一种多层前馈型网络,它们的输入输出映射都可以表示为一组可变基的线性组合.网络的参数也表现为二类:可变基中的参数是非线性的,组合系数是线性的.为此,提出了一个将这二类参数进行分离学习的算法.仿真结果表明,这个学习算法加快了学习过程,提高了网络的逼近性能.