双向联想记忆神经网络的开关电流技术实现

本文研究了双向联想记忆（ＢＡＭ）神经网络的开关电流技术实现，提出了实现负权值及存储联想矢量的两个开关电流单元电路，基于此，给出了双向联想记忆网络的开关电流电路，文中对三神经元双向联想记忆ＳＩ网络进行了ＰＳＰＩＣＥ仿真，结果表明所提出的ＳＩ联想记忆网络是正确的。     

适合于数字VLSI实现的指数相关联想记忆等效运算算法

适合于数字ＶＬＳＩ实现的指数相关联想记忆等效运算算法杨绿溪，王保云，何振亚（东南大学无线电工程系，南京２１００１８）自１９８２年Ｈｏｐｆｉｅｌｄ网络被用于联想记忆，人们一直在致力于研究新的高容量联想记忆神经网络，Ｒ．Ｍ．Ｇｏｏｄｍａｎ等人提出的指数相...     

基于改进的Hopfield离散神经网络的模式识别

本文介绍基于改进的Ｈｏｐｆｉｅｌｄ离散神经网络（ＩＨＤＮ）的模式识别。当一个要求存贮在网络中的模式输入时，我们计算它与其它模式的类似测试，并把类似测试在网络综合中加以考虑。当输入任一矢量时，由于网络的联想能力，该矢量将进化到与它距离最近的一个存贮模式中。理论分析和实验仿真结果表明，ＩＨＤＮ比原Ｈｏｐｆｉｅｌｄ离散神经网络（ＨＤＮ）有更大的存贮容量和更强的联想能力。     

Hopfield连续联想记忆的吸引域和指数收敛速度的估计及其应用

本文得到了Ｈｏｐｆｉｅｌｄ连续联想记忆各记忆模式的吸引域及其中每一点趋向记忆模式的指数收敛速度的估计结果，它们可用来评价Ｈｏｐｆｉｅｌｄ连续反馈联想记忆的容错能力，且可用于综合更为实用的连续联想记忆神经网络。     

离散Hopfield神经网络的PWM型脉冲流技术实现

研究了离散Hopfield神经网络的PWM(脉冲宽度调制)型脉冲流技术实现。利用MOS开关管和电压比较器实现了离散Hopfield神经网络，并提出了利用离散Hopfiled神经网络实现自联想记忆时相应的PWM型脉冲流电路。所提出的电路结构简单，易于芯片间通讯及系统扩展。     

离散神经网络的关联优化存储

离散神经网络的关联优化存储郭东辉，陈振湘，刘瑞堂，吴伯僖（厦门大学物理系，厦门３６１００５）离散Ｈｏｐｆｉｅｌｄ神经网络是一个比较典型的联想存储模型，它的存储容量一直是人们关心的问题。已有不少文章对它进行详细分析后认为：对于随机的存储样本，该离散神经...     

Hopfield型联想记忆神经网络一种新的分析方法

本文通过定义一种新的能量函数，分析了Ｈｏｐｆｉｅｌｄ型神经网络的渐近稳定性与联想记忆问题，得到了四组保证网络平衡点是渐近稳定平衡点的充分条件，应用这些条件，便可设计联想记忆神经网络，文中给出了应用这些结论设计联想记忆神经网络的实验结果及分析。     

环结构神经网络及其互联想性能

本文提出一种称为环结构神经网络（ＬＡＮＮ）模型及其学习算法，它能像Ｈｏｐｆｉｅｌｄ网络，双向联想记忆（ＢＡＭ）网络和其它类似网络一样工作，特别是它能执行多类样本之间的互联想记忆，理论分析和计算机模拟都证明ＬＡＮＮ具有很好的收敛性，是一种有效的网络结构，最后本文给出了计算机模拟结果。     

压缩正交矢量构成的关联记忆矩阵的存储方法

压缩正交矢量构成的关联记忆矩阵的存储方法郑师海，李德华，陈岩松（中国科学院物理所北京１０００８０）在用正交的单极矢量作为神经元，构成离散的随机Ｈｏｐｆｉｅｌｄ神经网络模型的关联记忆矩阵时，由于其存储矢量的特殊性，关联记忆矩阵是正交的，而且行列具有某些...     

二进Hopfield型神经网络的记忆容量

本文证明了具有Ｎ个神经元的二进Ｈｏｐｆｉｅｌｄ型神经网络可存储的记忆模式的最大数目为２＾Ｎ，对于任意Ｋ（１≤Ｋ≤２＾Ｎ）个Ｎ维二进值向量，给出了它们成为具有Ｎ个神经元的二进Ｈｏｐｆｉｅｌｄ型神经网络稳定态的充要条件。文中指出了一个二进Ｈｏｐｆｉｅｌｄ型神经网络有可能没有任何稳定态，这是与连续Ｈｏｐｆｉｅｌｄ型神经网络的一个重要区别。最后，给出本文的主要结论。     

Wavelet Neural Network Approach for Testing of Switched-Current Circuits

Combining the time and frequency location and multiple-scale analysis of wavelet transform with the nonlinear mapping and generalizing of neural network, an efficient defect-oriented parametric test method using Wavelet Neural Network (WNN) for switched-current integrated circuits is proposed. Contraposing to the fully compatible digital CMOS technology and current scaling calculation of SI circuits, parameter cohort of switched current elements is used to compute the sensitivity and gain tolerance and is applied for selecting the test models. The selecting of the appropriate wavelet function based on particular switched current fault signal is discussed, and the number of network input and output nodes are determined by the circuit status and dimension of eigenvector which is the energy of wavelet decomposition coefficient. To simplify configuration of the neural network, the sampled data was preprocessed by wavelet transform. Illustrative examples show that the proposed wavelet neural network method for testing of switched current circuits is effective.     

开关电流技术：一种新的模拟抽样数据处理方法

开关电流（ＳＩ）技术是一种新的模拟抽样数据处理技术，介绍了开关电流电路的基本单元结构，讨论了目前开关电流技术中存在的问题及其解决方法。对开关电流技术与开关电容技术的一些基本特征进行了比较，ＳＩ技术不仅结构简单，而且与标准ＣＭＯＳ工艺兼容，可望替代开关电容电路。     

A new swarm-SVM-based fault diagnosis approach for switched current circuit by using kurtosis and entropy as a preprocessor

This paper presents a new fault diagnosis method for switched current (SI) circuits. The kurtoses and entropies of the signals are calculated by extracting the original signals from the output terminals of the circuit. Support vector machine (SVM) is introduced for fault diagnosis using the entropies and kurtoses as inputs. In this technique, a particle swarm optimization is proposed to optimize the SVM to diagnose switched current circuits. The proposed method can identify faulty components in switched current circuit. A low-pass SI filter circuit has been used as test beached to verify the effectiveness of the proposed method. The accuracy of fault recognition achieved is about 97 % although there are some overlapping data when tolerance is considered. A comparison of our work with Long et al. (Analog Integr Circuit Signal Process 66:93–102, 2011), which only used entropy as a preprocessor, reveals that our method performs well in the part of fault diagnostic accuracy.     

Accurate SI filters using RGC integrators

The design and implementation of single-ended and fully-differential switched current (SI) biquadratic high-Q bandpass filters to meet the specifications of the dual-tone multiple-frequency (DTMF) system are presented. Both designs use the regulated-gate cascode (RGC) dynamic current mirror to obtain center frequency accuracy of 0.1% and a quality factor of 24. Compared to the equivalent switched capacitor (SC) implementation of these filters, the single-ended SI filter requires 30% less area for the same minimum-sized capacitance, power dissipation and performance     

A new switched current circuit fault diagnosis approach based on pseudorandom test and preprocess by using entropy and Haar wavelet transform

This paper presents a new switched current (SI) circuit fault diagnosis approach based on pseudorandom test and preprocess by using entropy and Haar wavelet transform. The proposed method has the capability to detect and identify faulty transistors in SI circuit by analyzing its time response. The use of pseudorandom sequences as a stimulate signal to SI circuit reduces the cost of testing and the overhead of the test generation circuit, and using entropy and Haar wavelet transform to preprocess the time response for feature extraction drastically improves the fault diagnosis efficiency. For both actual experiment and analysis of switched current filters in Z transform (ASIZ) simulation, a low-pass, a band-pass SI filter and a clock feed-through cancellation circuit have been used as test examples to verify the effectiveness of the proposed method. The result shows that the accuracy of fault recognition achieved is about 100% by analyzing low-frequency approximations entropy and high-frequency details entropy. Therefore, it indicates that the presented method is superior than other methods.     

Prospect of the future of switched-current circuits with regard to future CMOS technologies

Low supply voltages in modern CMOS technologies are expected to reduce the maximum resolution of analog to digital converters in voltage mode operation. This paper outlines the functionality and possibilities of switched current (SI) circuit techniques in medium accuracy ΔΣ modulators. Starting with the presentation of different kinds of switched current cells, this paper gives an overview about the simulated performance followed by a comparison of switched current and switched capacitor circuits. A prospect of the future of switched current circuits with regard to future CMOS technologies is given.     

A simple structure wavelet transform circuit employing function link neural networks and SI filters

Signal processing by means of analog circuits offers advantages from a power consumption viewpoint. Implementing wavelet transform (WT) using analog circuits is of great interest when low-power consumption becomes an important issue. In this article, a novel simple structure WT circuit in analog domain is presented by employing functional link neural network (FLNN) and switched-current (SI) filters. First, the wavelet base is approximated using FLNN algorithms for giving a filter transfer function that is suitable for simple structure WT circuit implementation. Next, the WT circuit is constructed with the wavelet filter bank, whose impulse response is the approximated wavelet and its dilations. The filter design that follows is based on a follow-the-leader feedback (FLF) structure with multiple output bilinear SI integrators and current mirrors as the main building blocks. SI filter is well suited for this application since the dilation constant across different scales of the transform can be precisely implemented and controlled by the clock frequency of the circuit with the same system architecture. Finally, to illustrate the design procedure, a seventh-order FLNN-approximated Gaussian wavelet is implemented as an example. Simulations have successfully verified that the designed simple structure WT circuit has low sensitivity, low-power consumption and litter effect to the imperfections.     

一种新型Class AB开关电流存储单元的设计

设计了一种新型高性能Class AB开关电流(SI)第一代存储单元电路。电路由对称的电压反转跟随器(FVF)连接Class AB SI存储单元组成,输入级采用电流传输器结构,输出级采用可调共源共栅结构,电路具有误差小、功耗低、性能高等特点。基于此存储单元,设计了延时器和双线性积分器进行验证。电路采用SMIC 0.18μm工艺,在Spectre中进行仿真。结果表明,该存储单元具有较好的性能和应用价值。     

级联开关电流滤波器设计

本文提出了一种新的有源器件开关电流运算放大器(SIOA)。新元件的引入大大减化了电路的作图,十分便于开关电流(SI)电路的分析和综合。以开关电容(SC)电路为原型,导出了若干新的全极点和椭圆(二阶或三阶)SI电路。这些电路既可作为滤波节单独使用,也可用于级联设计以实现高阶转移函数。为了说明设计方法,给出了一个五阶SI低通滤波器设计例子。