Boole函数的线性可分性(Ⅰ)——n-维超立方体的基本理论

Boole函数的线性可分性是前向人工神经网络理论中的一个比较困难的问题之一。目前仅对变量数n≤7的某些问题给予讨论。当n≥8时,尚无判别Boole函数线性可分的一般准则,更无线性可分Boole函数的计数公式。基于此,本文详细地研究了与Boole函数线性可分性有关的n-维超立方体的基本理论,包括n-维超立方体的基本性质、超立方体中的平行线、子超立方体的计数等,并给出了构造n-维超立方体图的一种新方法。     

A Neural Network Approach for Signal Detection in Digital Communications

In this paper, we propose a new approach for signal detection in wireless digital communications based on the neural network with transient chaos and time-varying gain (NNTCTG), and give a concrete model of the signal detector after appropriate transformations and mappings. It is well known that the problem of the maximum likelihood signal detection can be described as a complex optimization problem that has so many local optima that conventional Hopfield-type neural networks fail to solve. By refraining from the serious local optima problem of Hopfield-type neural networks, the NNTCTG makes use of the time-varying parameters of the recurrent neural network to control the evolving behavior of the network so that the network undergoes the transition from chaotic behavior to gradient convergence. It has richer and more flexible dynamics rather than conventional neural networks only with point attractors, so that it can be expected to have much ability to search for globally optimal or near-optimal solutions. After going through a transiently inverse-bifurcation process, the NNTCTG can approach the global optimum or the neighborhood of global optimum of our problem. Simulation experiments have been performed to show the effectiveness and validation of the proposed neural network based method for the signal detection in digital communications.     

Artificial neural networks for coordination and control: The portability of experiential representations

It is time to locate connectionist representation theory in the new wave of robotics research. The utility of representations developed in artificial neural networks (ANNs) during learning has been demonstrated in cognitive science research since the 1980s. The research reported here puts learned representations to work in a decentered control task, the disembodied arm problem, in which a mobile robot operates an arm fixed to a table to pick up objects. There is no physical linkage between the arm and the robot and so the robot's point of view must be decentered. This is done by developing a modular Artificial Neural Net system in three stages: (i) a classifier net is trained with laser scan data to output transformationally invariant position classes; (ii) an arm net is trained for picking up objects; (iii) an inter net is trained to communicate and coordinate the sensing and acting. The completed system is shown to create new nonsymbolic transformationally invariant representations in order to perform the effective generalization of decentered viewpoints.     

提高前馈神经网络推广能力的若干实际方法

提高前馈神经网络的推广能力是深受关注的问题，本文根据我们最近提出了一个网络有效推广的准则，从提高网络特征提取能力，分类能力和修改神经元激活函数等几方面给出了若干实际方案，我们在任意手写数字识别问题上的实验结果证实了这些方法的有效性。     

高氧化态（Ⅱ─Ⅳ）三核金属簇合物构型的人工神经网络判别方法

本文运用一典型的人工神经网络模型─“反向传播”模型，对高氧化态（Ⅱ─Ⅳ）三核金属簇合物的构型分布进行了分析，得到了较好的分类、预报结果为化合物结构分析提供了新的工具。     

BP算法的改进及用模拟电路实现的神经网络分类器

基于用模拟电路实现神经网络分类器的目的，对多层静态前馈神经网络的ＢＰ算法做了改进，采用线性限幅函数代替Ｓｉｇｍｏｉｄ函数作为神经元的激活函数，给出了改进的ＢＰ算法。对该算法性能的实验研究表明：这种改进算法不但方便了用线性模拟集成运算放大电路实现神经网络，而且具有学习速度快，映射能力强等优点。根据本文算法设计的神经网络分类器，无论是计算机仿真，还是模拟电路实现，都得到了比较高的识别率。     

Mixed Mode VLSI Implementation of a Neural Associative Memory

A mixed mode digital/analog special purpose VLSI hardware implementation of an associative memory with neural architecture is presented. The memory concept is based on a matrix architecture with binary storage elements holding the connection weights. To enhance the processing speed analog circuit techniques are applied to implement the algorithm for the association. To keep the memory density as high as possible two design strategies are considered. First, the number of transistors per storage element is kept to a minimum. In this paper a circuit technique that uses a single 6-transistor cell for weight storage and analog signal processing is proposed. Second, the device precision has been chosen to a moderate level to save area as much as possible. Since device mismatch limits the performance of analog circuits, the impact of device precision on the circuit performance is explicitly discussed. It is shown that the device precision limits the number of rows activated in parallel. Since the input vector as well as the output vector are considered to be sparsely coded it is concluded, that even for large matrices the proposed circuit technique is appropriate and ultra large scale integration with a large number of connection weights is feasible.     

Design and Implementation of a Flexible Manufacturing Control System Using Neural Network

Design and implementation of a sequential controller based on the concept of artificial neural networks for a flexible manufacturing system are presented. The recurrent neural network (RNN) type is used for such a purpose. Contrary to the programmable controller, an RNN-based sequential controller is based on a definite mathematical model rather than depending on experience and trial and error techniques. The proposed controller is also more flexible because it is not limited by the restrictions of the finite state automata theory. Adequate guidelines of how to construct an RNN-based sequential controller are presented. These guidelines are applied to different case studies. The proposed controller is tested by simulations and real-time experiments. These tests prove the successfulness of the proposed controller performances. Theoretical as well as experimental results are presented and discussed indicating that the proposed design procedure using Elman's RNN can be effective in designing a sequential controller for event-based type manufacturing systems. In addition, the simulation results assure the effectiveness of the proposed controller to outperform the effect of noisy inputs.     

振动力场作用下聚合物挤出制品结构与性能的质量控制与优化

利用实验数据，分析与研究振动场振动参数对聚合物挤出制品质量的影响，对聚合物挤出制品的熔体流动速率，微晶结构，拉伸强度等主要性能质量指标，建立以振动频率为主要控制变量的神经网络模型，并引入信息分配模型，探讨了一个网络输入节点下神经网络学习样本的特征提取与优化。实验结果表明，经过信息预处理的学习样本，可以使网络有更好的收敛效果。     

Image processing using cellular neural networks based on multi-valued and universal binary neurons

Multi-valued and universal binary neurons (MVN and UBN) are the neural processing elements with the complex-valued weights and high functionality. It is possible to implement an arbitrary mapping described by partially defined multiple-valued function on the single MVN. An arbitrary mapping described by partially defined or fully defined Boolean function, which can be non-threshold, may be implemented on the single UBN. The quickly converging learning algorithms exist for both types of neurons. Such features of the MVN and UBN may be used for solving the different problems. One of the most successful applications of the MVN and UBN is their usage as basic neurons in the Cellular Neural Networks (CNN). It opens the new effective opportunities in nonlinear image filtering and its applications to noise reduction, edge detection and solving of the super resolution problem. A number of experimental results are presented to illustrate the performance of the proposed algorithms.An erratum to this article can be found at