Design and implementation of multipattern generators in analog VLSI

In recent years, computational biologists have shown through simulation that small neural networks with fixed connectivity are capable of producing multiple output rhythms in response to transient inputs. It is believed that such networks may play a key role in certain biological behaviors such as dynamic gait control. In this paper, we present a novel method for designing continuous-time recurrent neural networks (CTRNNs) that contain multiple embedded limit cycles, and we show that it is possible to switch the networks between these embedded limit cycles with simple transient inputs. We also describe the design and testing of a fully integrated four-neuron CTRNN chip that is used to implement the neural network pattern generators. We provide two example multipattern generators and show that the measured waveforms from the chip agree well with numerical simulations.     

Composing domain-specific physical models with general-purpose software modules in embedded control software

A considerable portion of software systems today are adopted in the embedded control domain. Embedded control software deals with controlling a physical system, and as such models of physical characteristics become part of the embedded control software. In current practices, usually general-purpose languages (GPL), such as C/C++ are used for embedded systems development. Although a GPL is suitable for expressing general-purpose computation, it falls short in expressing the models of physical characteristics as desired. This reduces not only the readability of the code but also hampers reuse due to the lack of dedicated abstractions and composition operators. Moreover, domain-specific static and dynamic checks may not be applied effectively. There exist domain-specific modeling languages (DSML) and tools to specify models of physical characteristics. Although they are commonly used for simulation and documentation of physical systems, they are often not used to implement embedded control software. This is due to the fact that these DSMLs are not suitable to express the general-purpose computation and they cannot be easily composed with other software modules that are implemented in GPL. This paper presents a novel approach to combine a DSML to model physical characteristics and a GPL to implement general-purpose computation. The composition filters model is used to compose models specified in the DSML with modules specified in the GPL at the abstraction level of both languages. As such, this approach combines the benefits of using a DSML to model physical characteristics with the freedom of a GPL to implement general-purpose computation. The approach is illustrated using two industrial case studies from the printing systems domain.     

神经网络及遗传算法在径流预报中的应用

提出用遗传算法和BP算法相结合的改进神经网络模型来进行径流预报。即先通过遗传算法对初始权值分布进行优化，在解空间定位出一个较好的搜索空间，然后采用BP算法，在这个较小的解空间中搜索出最优解。使网络收敛速度加快和避免局部极小。作为实例，以清江鸭子口的实测径流资料为样本进行训练并用以预测该水文站的日径流量。结果表明，该方法具有收敛速度快和预测精度高的特点。     

Tracking control of a nonholonomic mobile robot using compound cosine function neural networks

The purpose of this paper is to propose a compound cosine function neural network with continuous learning algorithm for the velocity and orientation angle tracking control of a nonholonomic mobile robot with nonlinear disturbances. Herein, two neural network (NN) controllers embedded in the closed-loop control system have the simple continuous learning and rapid convergence capability without the dynamics information of the mobile robot to realize the adaptive control of the mobile robot. The neuron function of the hidden layer in the three-layer feed-forward network structure is on the basis of combining a cosine function with a unipolar sigmoid function. The developed neural network controllers have simple algorithm and fast learning convergence because the weight values are only adjusted between the nodes in hidden layer and the output nodes, while the weight values between the input layer and the hidden layer are one, i.e. constant, without the weight adjustment. Therefore, the main advantages of this control system are the real-time control capability and the robustness by use of the proposed neural network controllers for a nonholonomic mobile robot with nonlinear disturbances. Through simulation experiments applied to the nonholonomic mobile robot with the nonlinear disturbances which are considered as dynamics uncertainty and external disturbances, the simulation results show that the proposed NN control system of nonholonomic mobile robots has real-time control capability, better robustness and higher control precision. The compound cosine function neural network provides us with a new way to solve tracking control problems for mobile robots.     

A general framework for concurrent simulation on neural networkmodels

The analysis of complex neural network models via analytical techniques is often quite difficult due to the large numbers of components involved and the nonlinearities associated with these components. The authors present a framework for simulating neural networks as discrete event nonlinear dynamical systems. This includes neural network models whose components are described by continuous-time differential equations or by discrete-time difference equations. Specifically, the authors consider the design and construction of a concurrent object-oriented discrete event simulation environment for neural networks. The use of an object-oriented language provides the data abstraction facilities necessary to support modification and extension of the simulation system at a high level of abstraction. Furthermore, the ability to specify concurrent processing supports execution on parallel architectures. The use of this system is demonstrated by simulating a specific neural network model on a general-purpose parallel computer     

两种典型神经网络容错方法的比较

Behnam提出的SC算法和文中提出的rehidden算法是两种典型的前向神经网络容错 算法,前者改进BP算法进行学习,后者对已学习的网络进行隐层节点冗余.这两种算法各有优 缺点.文中对这两种算法进行了仿真实验分析,最终得到了每种算法适用的网络规模和硬件条 件,在不同环境下应采用不同的方法才能得到可行的容错网络.最后还对SC算法的一些改进进 行了讨论.     

Development and Verification of Simulation Model Based on Real MANET Experiments for Transport Layer Protocols （UDP and TCP）

There is a lack of appropriate guidelines for realistic user traces, mobility models, routing protocols, considerations of real-life challenges, etc. for general-purpose mobile ad hoc networks (MANET). In this paper, four laptops are used in an open field environment in four scenarios to evaluate the performances of Internet control message protocol (ICMP) based ping and transmission control protocol (TCP) based streaming video applications using optimised link state routing (OLSR) implementation in an IEEE 802.11g wireless network. Corresponding simulations are developed in Network Simulator ns-2 by setting simulation parameters according to the real experiments. Difficulties faced to regenerate real-life scenarios have been discussed and the gaps between reality and simulation are identified. A setup guideline to produce realistic simulation results has been established.     

一种新的基于BP神经网络的拥塞控制算法

针对计算机高速互联网中发送端速率调节的问题，在一般网络模型基础上，将BP（Back Propagation神经网络运用到计算机网络的拥塞控制中，提出了一种基于BP神经网络的动态资源管理机制以解决网络的拥塞问题，对所提出的拥塞控制方案，进行了仿真分析，仿真结果显示，控制方案有较好的可扩展性，有效性，并使网络性能表现良好。     

Aerodynamic noise simulation of the flow past an airfoil trailing-edge using a hybrid zonal RANS-LES

This paper document the evaluation of a zonal RANS-LES approach for the prediction of broadband and tonal noise generated by the flow past an airfoil trailing edge at a high Reynolds number. A multi-domain decomposition is considered, where the acoustic sources are resolved with a LES sub-domain embedded in the RANS domain. At the RANS-LES interface, a stochastic vortex method is used to generate synthetic turbulent perturbations. The simulations are performed with the general-purpose unstructured control-volume code FLUENT. The far-field noise is calculated using the aeroacoustic analogy of Ffowcs-Williams and Hawkings. The results of the simulation are compared with available acoustic and mean velocity measurements. The investigation demonstrates the ability of this approach to predict the aerodynamic and aeroacoustic properties of the flow. Two simulations are performed in order to address the sensitivity of the results to the perturbation model. The comparison clearly indicates the critical influence of the model.     

A systematic method for configuring VLSI networks of spiking neurons

An increasing number of research groups are developing custom hybrid analog/digital very large scale integration (VLSI) chips and systems that implement hundreds to thousands of spiking neurons with biophysically realistic dynamics, with the intention of emulating brainlike real-world behavior in hardware and robotic systems rather than simply simulating their performance on general-purpose digital computers. Although the electronic engineering aspects of these emulation systems is proceeding well, progress toward the actual emulation of brainlike tasks is restricted by the lack of suitable high-level configuration methods of the kind that have already been developed over many decades for simulations on general-purpose computers. The key difficulty is that the dynamics of the CMOS electronic analogs are determined by transistor biases that do not map simply to the parameter types and values used in typical abstract mathematical models of neurons and their networks. Here we provide a general method for resolving this difficulty. We describe a parameter mapping technique that permits an automatic configuration of VLSI neural networks so that their electronic emulation conforms to a higher-level neuronal simulation. We show that the neurons configured by our method exhibit spike timing statistics and temporal dynamics that are the same as those observed in the software simulated neurons and, in particular, that the key parameters of recurrent VLSI neural networks (e.g., implementing soft winner-take-all) can be precisely tuned. The proposed method permits a seamless integration between software simulations with hardware emulations and intertranslatability between the parameters of abstract neuronal models and their emulation counterparts. Most important, our method offers a route toward a high-level task configuration language for neuromorphic VLSI systems.     

Genetic algorithm‐based neural‐network modeling approach applied to AlGaN/GaN devices

An accurate equivalent circuit large‐signal model (ECLSM) for AlGaN‐GaN high electron mobility transistor (HEMT) is presented. The model is derived from a distributed small‐signal model that efficiently describes the physics of the device. A genetic neural‐network‐based model for the gate and drain currents and charges is presented along with its parameters extraction procedure. This model is embedded in the ECLSM, which is then implemented in CAD software and validated by pulsed and continuous large‐signal measurements of on‐wafer 8 × 125‐μm GaN on SiC substrate HEMT. Pulsed IV simulations show that the model can efficiently describe the bias dependency of trapping and self‐heating effects. Single‐ and two‐tone simulation results show that the model can accurately predict the output power and its harmonics and the associated intermodulation distortion (IMD) under different input‐power and bias conditions. © 2012 Wiley Periodicals, Inc. Int J RF and Microwave CAE, 2013.     

Processor architecture considerations for embedded controller applications

The ways in which the environment of an embedded controller differs from that of a general-purpose CPU are described. A particular embedded controller application, the network interface is examined. The microprocessor used is the 32-bit VL86C010 Acorn RISC (reduced-instruction-set computer). The features of the network architecture, as they affect the choice of processor, are discussed. The impact of system latency on the choice of hardware is examined.<>     

一种基于BP神经网络的数字识别新方法

针对标准BP神经网络收敛速度慢、易陷入局部极小点的缺点,提出了一种新的BP神经网络改进算法。该算法通过变步长法和牛顿法来改进BP算法,加快了网络的收敛速度,且收敛速度快于其他的改进算法。在此基础上将BP神经网络应用于数字识别中,为其网络建立识别模型。利用仿真实验观察BP网络的泛化能力以及识别准确性,比较BP算法及其改进方案,提出改进方案中分别需要注意的地方。     

一种基于输入训练神经网络的非线性PCA 故障诊断方法

简要讨论了线性PCA故障诊断方法存在的问题，提出一种基于输入训练神经网络的非线性PCA故障诊断方法。该方法首先利用输入训练神经网络和BP网络双网络机制，实现非线性主元的识别，并采用统计方法进行故障检测与故障分离。对CSTR的仿真研究结果表明，该方法能够克服线性PCA方法在提取过程变量的非线性特征方面存在的不足，并能够准确地进行故障检测和分离。     

Augmented Hopfield network for mixed-integer programming

Watta and Hassoun (1996) proposed a coupled gradient neural network for mixed integer programming. In this network continuous neurons were used to represent discrete variables. For the larger temporal problem they attempted many of the solutions found were infeasible. This paper proposes an augmented Hopfield network which is similar to the coupled gradient network proposed by Watta and Hassoun. However, in this network truly discrete neurons are used. It is shown that this network can be applied to mixed integer programming. Results illustrate that feasible solutions are now obtained for the larger temporal problem.     

"弹性"BP神经网络在识别带有噪声字母中的应用

字符识别是模式识别中的一个典型应用,通过训练网络可以教会计算机如何识别字符,这在票据处理方面可以大大地提高效率.该文中所建立的神经网络具有Sigmoid型可微函数的三层BP神经网络,它可以以任意精度逼近任何连续函数,实现输入和输出之间的任意非线性映射.文中分析了BP神经网络的“弹性”学习算法,利用五位二进制数来识别的输出26种状态.建立的一个三层的BP神经网络能对带有噪声的26个英文大写字母进行识别.利用MATLAB编写仿真程序对BP神经网络进行训练,仿真结果表明训练的BP神经网络可以对给定的带有噪声的字母正确地识别.     

Division-based rainfall-runoff simulations with BP neural networks and Xinanjiang model

The application of artificial neural network (ANN) to rainfall-runoff simulations has provided promising results in recent years. However, it is difficult to obtain satisfying results by using raw data for the direct prediction of the time series of streamflows. To improve simulating daily streamflow with back-propagation (BP) neural networks, the whole data set in this study is divided into two independent groups, flood period and non-flood period. The approaches and techniques of applying the division-based BP (DBP) in runoff simulation are presented in this paper. A comparison of the DBP model to the primitive BP model and the Xinanjiang model was also conducted to evaluate the effectiveness of the improvement. The numerical experimental results indicate that DBP model still overestimated flow peak, but improved considerably the streamflow simulation in the non-flood period.     

字典神经网络方法快速湍流烟雾合成

目的 基于物理的烟雾模拟是计算机图形学的重要组成部分,渲染具有细小结构的高分辨率烟雾,需要大量的计算资源和高精度的数值求解方法。针对目前高精度湍流烟雾模拟速度慢,仿真困难的现状,提出了基于字典神经网络的方法,能够快速合成湍流烟雾,使得合成的结果增加细节的同时,保持高分辨率烟雾结果的重要结构信息。方法 使用高精度的数值仿真求解方法获得高分辨率和低分辨率的湍流烟雾数据,通过采集速度场局部块及相应的空间位置信息和时间特征生成数据集, 设计字典神经网络的网络架构,训练烟雾高频成分字典预测器,在GPU（graphic processing unit）上实现并行化,快速合成高分辨率的湍流烟雾结果。结果 实验表明,基于字典神经网络的方法能够在非常低分辨率的烟雾数据下合成空间和时间上连续的高分辨率湍流烟雾结果,效率比通过在GPU平台上直接仿真得到高分辨率湍流烟雾的结果快了一个数量级,且合成的烟雾结果与数值仿真方法得到的高分辨率湍流烟雾结果足够接近。结论 本文方法解决了烟雾的上采样问题,能够从非常低分辨率的烟雾仿真结果,通过设计基于字典神经网络结构以及特征描述符编码烟雾速度场的局部和全局信息,快速合成高分辨率湍流烟雾结果,且保持高精度烟雾的细节,与数值仿真方法的对比表明了本文方法的有效性。     

分式线性神经网络及其非线性逼近能力研究

提出了结构简单的分式线性神经网络,证明该种神经网络可无限逼近Rm上有界闭子集到Rn上的任意连续映射,同时,证实该种神经网络可无限逼近Rm上无界闭子集到Rn上的在无穷远有极限的任意连续映射,扩充了BP神经网络的非线性逼近能力;给出了实现分式线性神经网络逼近有界或无界区域上连续映射的反向传播算法.仿真实验表明所给出的反向传播算法可行有效.该结果为无界区域上的分类问题和决策问题的解决提供了理论基础.     

一种全局收敛的PCA神经网络学习算法

主元分析(PCA)也称为K-L变换是进行特征提取的一种重要方法。近年来，为了处理海量数据，许多基于Hebbian学习算法的PCA神经网络被提出来。传统的算法，通常不能保证其收敛性或者收敛速度较慢。基于CRLS神经网络，本文提出了一种新的确保权向量收敛的学习算法，本算法无须在计算中规格化权向量。同时也证明了该学习算法使得权向量收敛到最大特征值所对应的特征向量。实验表明，与传统的CRLS神经网络比较，本文算法准确性得到极大提高。