M-P神经元模型的几何意义及其应用

给出M-P神经元模型的几何意义,这个几何的铨释,给神经元一个非常直观的理解,利用这个直观的理解,给出两个颇为有趣的应用:(1)用此法给出三层前向神经网络的学习能力的基本定理的新的证明;(2)给出前向网络的拓扑结构设计的新方法.     

An MLP-based representation of neural tensor networks for the RDF data models

In this paper, a new representation of neural tensor networks is presented. Recently, state-of-the-art neural tensor networks have been introduced to complete RDF knowledge bases. However, mathematical model representation of these networks is still a challenging problem, due to tensor parameters. To solve this problem, it is proposed that these networks can be represented as two-layer perceptron network. To complete the network topology, the traditional gradient based learning rule is then developed. It should be mentioned that for tensor networks there have been developed some learning rules which are complex in nature due to the complexity of the objective function used. Indeed, this paper is aimed to show that the tensor network can be viewed and represented by the two-layer feedforward neural network in its traditional form. The simulation results presented in the paper easily verify this claim.

     

多层前向小世界神经网络及其函数逼近

借鉴复杂网络的研究成果, 探讨一种在结构上处于规则和随机连接型神经网络之间的网络模型—-多层前向小世界神经网络. 首先对多层前向规则神经网络中的连接依重连概率p进行重连, 构建新的网络模型, 对其特征参数的分析表明, 当0 < p < 1时, 该网络在聚类系数上不同于Watts-Strogatz 模型; 其次用六元组模型对网络进行描述; 最后, 将不同p值下的小世界神经网络用于函数逼近, 仿真结果表明, 当p = 0:1时, 网络具有最优的逼近性能, 收敛性能对比试验也表明, 此时网络在收敛性能、逼近速度等指标上要优于同规模的规则网络和随机网络.     

Architecture and statistical model of a pulse-mode digitalmultilayer neural network

A new architecture and a statistical model for a pulse-mode digital multilayer neural network (DMNN) are presented. Algebraic neural operations are replaced by stochastic processes using pseudo-random pulse sequences. Synaptic weights and neuron states are represented as probabilities and estimated as average rates of pulse occurrences in corresponding pulse sequences. A statistical model of error (or noise) is developed to estimate relative accuracy associated with stochastic computing in terms of mean and variance. The stochastic computing technique is implemented with simple logic gates as basic computing elements leading to a high neuron-density on a chip. Furthermore, the use of simple logic gates for neural operations, the pulse-mode signal representation, and the modular design techniques lead to a massively parallel yet compact and flexible network architecture, well suited for VLSI implementation. Any size of a feedforward network can be configured where processing speed is independent of the network size. Multilayer feedforward networks are modeled and applied to pattern classification problems such as encoding and character recognition.     

基于隐层生长策略的前馈神经网络隐层性能评测

针对最佳平方逼近三层前馈神经网络模型,讨论了以逐一增加隐单元方式构建隐层时隐层性能的评测方法。分析了影响前馈神经网络性能的相关空间,引入了表示空间、误差空间、目标空间和耗损空间的概念,研究了每个隐单元的误差补偿性能,提出了网络隐层性能的评测参数,并通过对传统BP算法和正交化算法的考查验证了其合理性与有效性。     

基于子空间信息量准则的前向神经网络设计理论与方法研究

从理论上提出了子空间信息量(SIQ)及其准则(SIQC)的概念；在此基础上阐述了基于上述准则的前向神经网络设计的相关理论，包括前向神经网络隐含层信息量(HLIQ)、存在性和逼近定理，给出了选择隐含层神经元数、权值向量集和隐含层激励函数的指导方向；提出了基于上述理论的一种可行的次优网络设计算法；最后，详细分析了网络性能指标及其影响因素，上述理论和方法完全克服了传统学习算法的各种弊端，丰富了前向神经网络设计领域的理论依据，具有较大的理论指导和实际应用价值，文中通过具体实例验证了上述理论和方法的可行性和优越性．     

一种新型随机二进制神经网络

二进制数据表示具有简洁高效的特点,随机噪声有助于系统摆脱局部极小.新型的随 机神经网络模型采用随机加权联接,内部数据表示为随机二进制序列形式,实现十分高效.文中 分别就前馈型网络和反馈型网络进行了深入的讨论,给出了前馈型网络的梯度下降学习算法, 为反馈型网络设计了快速有效的模拟退火算法和渐进式Boltzmann学习算法.通过对PARITY 问题的测试,发现了新模型的一些有趣特征,实验结果表明梯度下降学习效果显著.利用渐进式 Boltzmann学习,反馈型网络被成功地用于带噪声人脸识别.     

Analysis and synthesis of feedforward neural networks usingdiscrete affine wavelet transformations

A representation of a class of feedforward neural networks in terms of discrete affine wavelet transforms is developed. It is shown that by appropriate grouping of terms, feedforward neural networks with sigmoidal activation functions can be viewed as architectures which implement affine wavelet decompositions of mappings. It is shown that the wavelet transform formalism provides a mathematical framework within which it is possible to perform both analysis and synthesis of feedforward networks. For the purpose of analysis, the wavelet formulation characterizes a class of mappings which can be implemented by feedforward networks as well as reveals an exact implementation of a given mapping in this class. Spatio-spectral localization properties of wavelets can be exploited in synthesizing a feedforward network to perform a given approximation task. Two synthesis procedures based on spatio-spectral localization that reduce the training problem to one of convex optimization are outlined.     

Neural network synthesis for thermal processes

Neural networks are relatively new and highly attractive tools for modelling complex systems. The main feature of neural networks is their inherent plasticity which enables them to fit virtually any nonlinear function provided they have a sufficient number of parameters. Neural networks are a general class of nonlinear systems. Neural models can be used advantageously to model the dynamic behaviour of physical processes. In this paper, feedforward neural networks are used for modelling of dynamic thermal processes. The synthesis of neural networks is directly associated with the minimization of an objective function normally defined as the square of the difference between the output of the process being modelled and the output predicted by the network. Learning schemes are used for the evaluation of the connection weights of the feedforward neural network. In this paper, the dynamic modelling of several thermal processes using feedforward neural networks is presented. In one example, the identified neural model of the inverse of the plant is used as a controller.     

基于输出误差与偏导数误差信息融合的神经网络训练

文章首先提出了表示前向神经网的泛化能力的一种度量,分析了提高网络泛化能力的主要途径,进而提出了基于网络输出误差与输出对输入偏导数误差信息融合的网络训练策略,给出了两者信息融合的有效方法和相应网络训练算法。具体应用结果表明所提出算法可显著提高网络的泛化能力。