一种脉冲神经元监督学习的直接计算方法

精确脉冲定时作为一种神经元信息编码方式更具生物可解释性,使用精确脉冲定时编码的脉冲神经元具有更为强大的时空信号处理能力.脉冲神经元监督学习是神经计算的重要方面,目的是使神经元对给定输入脉冲在期望时刻发放脉冲.通过分析输入脉冲序列、期望输出脉冲序列与实际输出脉冲序列的关系,发现已有脉冲神经元监督学习算法的脉冲选择与计算较为复杂,致使不能达到理想学习效果.通过去除影响整体学习效果的多余脉冲计算,构建用于脉冲神经元突触权值调整的双脉冲单元,提出了一种适用于脉冲神经元监督学习的直接计算方法.该方法基于输入脉冲,使用期望输出脉冲与实际输出脉冲的时序关系,直接计算突触权值的调整量;每个输入脉冲在每次迭代中最多计算一次,有效减少了脉冲计算次数.实验结果表明,直接计算方法作为脉冲神经元监督学习的一般性脉冲计算优化策略,可以大幅提高已有算法的学习准确率.     

脉冲神经网络的监督学习算法研究综述

脉冲神经网络是进行复杂时空信息处理的有效工具,但由于其内在的不连续和非线性机制,构建高效的脉冲神经网络监督学习算法非常困难,同时也是该研究领域的重要问题.本文介绍了脉冲神经网络监督学习算法的基本框架,以及性能评价原则,包括脉冲序列学习能力、离线与在线处理性能、学习规则的局部特性和对神经网络结构的适用性.此外,对脉冲神经网络监督学习算法的梯度下降学习规则、突触可塑性学习规则和脉冲序列卷积学习规则进行了详细的讨论,通过对比分析指出现有算法存在的优缺点,并展望了该领域未来的研究方向.     

基于脉冲神经网络的边缘检测

提出了一种利用脉冲神经元的脉冲放电时间对图像像素进行编码和边缘提取的方法.首先将图像像素转化为神经元的输出脉冲序列.再用脉冲序列的首个脉冲放电时间编码图像的像素.并将一个窗口内的首个脉冲同时输入下一层的一个脉神经元,若窗口内对应的像素在一个平坦的区域,这些脉冲同时到达神经元,只能激发出稀疏的脉冲序列;如果窗口内对应的像素在一个边缘区域,这些脉冲在不同时刻到达神经元,将激发出稠密的脉冲序列.最后设定一个阈值,根据输出脉冲序列的密度区分边缘像素和非边缘像素,提取图像的边缘.实验结果表明该方法具有良好的边缘检测效果,更加符合生物信息处理机制.     

基于差分自相关矩阵的激光脉冲编码识别

在分析了激光脉冲编码方式的基础上,提出基于自相关矩阵统计的激光脉冲编码识别方法:利用接收到的脉冲序列,构造一阶差分自相关矩阵和二阶差分自相关矩阵,分别对其进行直方图统汁,根据直方图特点识别激光脉冲序列的编码方式,并解算出脉冲时间参数.通过仿真实验.验证算法的有效性,用计算机仿真生成不同类型的脉冲序列,并设定脉冲丢失概率和虚假脉冲概率,验证编码识别算法.实验证明该编码识别箅法正确率高,实时性好,有较强的抗干扰脉冲能力.     

基于FPGA的激光脉冲编码研究

对目标指示信号进行编码能够有效的降低敌方的干扰,详细介绍了激光指示信号3种编码样式,即脉冲间隔编码（PCM）、有限位随机周期脉冲序列编码和伪随机码。对3种编码的特点进行了全面的分析,并从原理上说明了激光脉冲编码的生成机理。通过Modelsim软件对2种脉冲编码进行了仿真研究,并对有限位随机周期脉冲序列编码和伪随机码的特点进行了比较,伪随机码具有更好的保密性和抗干扰能力。     

一种最大集合期望损失的多目标Sarsa(λ)算法

针对RoboCup这一典型的多目标强化学习问题,提出一种基于最大集合期望损失的多目标强化学习算法LRGM-Sarsa(λ)算法.该算法预估各个目标的最大集合期望损失,在平衡各个目标的前提下选择最佳联合动作以产生最优联合策略.在单个目标训练的过程中,采用基于改进MSBR误差函数的Sarsa(λ)算法,并对动作选择概率函数和步长参数进行优化,解决了强化学习在使用非线性函数泛化时,算法不稳定、不收敛的问题.将该算法应用到RoboCup射门局部策略训练中,取得了较好的效果,表明该学习算法的有效性.     

基于Costas编码跳频雷达信号分析及成像研究

常用的跳频宽带雷达大都是基于发射顺序步进载频的脉冲信号形式,而这种信号的模糊图为斜刀刃形,存在距离-速度耦合,容易造成测距不准和多普勒效应.为了改善高分辨力雷达测距测速性能,提出了在ISAR成像中采用Costas编码脉冲序列,推导并比较了Costas编码脉冲序列和常规步进频脉冲序列的模糊图,分析了Costas编码跳频雷达信号形式,指出它可以消除距离-速度耦合,具有更好的测距和测速性能,并给出了ISAR成像的算法步骤.最后仿真验证了该算法的正确性.     

基于突触可塑性的SNN随钻陀螺仪漂移处理

针对随钻振动引起MEMS陀螺仪的数据漂移问题,文中提出了一种脉冲神经网络算法.首先根据陀螺仪漂移误差的时间特性,利用脉冲网络的脉冲时间编码陀螺仪的信息强度.然后利用Izhikevich神经元模型的突触可塑性,调节激发性突触电导并抑制性突触电导,增强网络的鲁棒性,从而提高陀螺仪信号对噪声的抗干扰能力.在不同振动频率下,分...     

基于多重分选的脉冲配对时差检测

大基线时差定位具有定位快、精度高的优点,但大基线各定位站接收到的脉冲序列之间的时延变大,各基线时差测定的难度增加,因此如何准确实现各基线之间脉冲序列配对成了大基线时差测定的关键。在分析时差定位原理的基础上,研究了时差定位中相同序列脉冲多重分选及检测方法,分析了非周期脉冲重复间隔（PRI）和具有骨架或固定PRI对脉冲配对模糊性,给出一种基于多重分选的脉冲序列的分选配对方法,并针对模糊性进行定量分析,说明该脉冲序列多重分选配对方法在时差定位中的有效性。     

一种自适应容差的雷达信号分选聚类算法

雷达信号分选的目的就是从交错的、密集复杂的脉冲信号流中提取出同一辐射源的脉冲序列。战场环境中信号流的密集性,信号形式的复杂性,给信号分选带来了严重的挑战。面对如此复杂的信号环境,传统的基于直方图统计的雷达信号分选算法的分选结果可信度越来越差。在聚类雷达信号分选算法的基础之上提出了一种自适应容差的雷达信号聚类算法,克服了传统的雷达信号聚类分选算法中容差选择困难的问题。仿真结果表明该方法能够准确地分选出各个辐射源的脉冲序列。     

Spike Based Normalizing Hebbian Learning in an Analog VLSI Artificial Neuron

Recent neurophysiological results indicate that changes in synaptic efficacy are dependent on co-occurrence of a pre and a postsynaptic spike at the synapse [5,8]. There are only a few models of parts of the nervous system that use temporal correlation of single spikes in learning [1]. In most models of artificial neural networks neurons communicate by analog signals representing frequencies, and their learning rules are also defined on these continuous signals. Timing of single spikes is not used, nor is it represented. This simplification has proven useful in many applications and it makes simulations in software simpler and faster. Spiking systems have been avoided because they are computationally more difficult. However, by implementing spiking and learning artificial neurons in analog VLSI it is possible to examine the behavior of these more detailed models in real time. This is why ourselves and others [4] have started to use silicon models of spiking learning neurons. We have formulated one possible mechanism of weight normalization: a Hebbian learning rule that makes use of temporal correlations between single spikes. We have implemented it on a CMOS chip and demonstrate its normalizing behavior.     

Unsupervised deconvolution of sparse spike trains using stochasticapproximation

This paper presents an unsupervised method for restoration of sparse spike trains. These signals are modeled as random Bernoulli-Gaussian processes, and their unsupervised restoration requires (i) estimation of the hyperparameters that control the stochastic models of the input and noise signals and (ii) deconvolution of the pulse process. Classically, the problem is solved iteratively using a maximum generalized likelihood approach despite questionable statistical properties. The contribution of the article is threefold. First, we present a new “core algorithm” for supervised deconvolution of spike trains, which exhibits enhanced numerical efficiency and reduced memory requirements. Second, we propose an original implementation of a hyperparameter estimation procedure that is based upon a stochastic version of the expectation-maximization (EM) algorithm. This procedure utilizes the same core algorithm as the supervised deconvolution method. Third, Monte Carlo simulations show that the proposed unsupervised restoration method exhibits satisfactory theoretical and practical behavior and that, in addition, good global numerical efficiency is achieved     

基于一种杂交学习算法的自适应复信道均衡技术

本文提出了一种基于多层前馈神经网络杂交学习算法的自适应复信道均衡的新方法。该学习算法用来训练一个输入、输出、权值和激活函数均为复数的神经网络。神经网络的训练利用了监督和非监督相结合的杂交技术,而权值的调整是基于TLS（total least square)准则进行的。计算机仿真结果表明,无论是在线性还是在非线性信道中,所提出的方法都表现出了很好的性能,这为自适应复信道均衡提供了一种新方法。     

Nonlinear dynamic modeling of synaptically driven single hippocampal neuron intracellular activity

A high-order nonlinear dynamic model of the input-output properties of single hippocampal CA1 pyramidal neurons was developed based on synaptically driven intracellular activity. The purpose of this study is to construct a model that: 1) can capture the nonlinear dynamics of both subthreshold activities [postsynaptic potentials (PSPs)] and suprathreshold activities (action potentials) in a single formalism; 2) is sufficiently general to be applied to any spike-input and spike-output neurons (point process input and point process output neural systems); and 3) is computationally efficient. The model consisted of three major components: 1) feedforward kernels (up to third order) that transform presynaptic action potentials into PSPs; 2) a constant threshold, above which action potentials are generated; and 3) a feedback kernel (first order) that describes spike-triggered after-potentials. The model was applied to CA1 pyramidal cells, as they were electrically stimulated with broadband Poisson random impulse trains through the Schaffer collaterals. The random impulse trains used here have physiological properties similar to spiking patterns observed in CA3 hippocampal neurons. PSPs and action potentials were recorded from the soma of CA1 pyramidal neurons using whole-cell patch-clamp recording. We evaluated the model performance separately with respect to PSP waveforms and the occurrence of spikes. The average normalized mean square error of PSP prediction is 14.4%. The average spike prediction error rate is 18.8%. In summary, although prediction errors still could be reduced, the model successfully captures the majority of high-order nonlinear dynamics of the single-neuron intracellular activity. The model captures the general biophysical processes with a small set of open parameters that are directly constrained by the intracellular recording, and thus, can be easily applied to any spike-input and spike-output neuron.     

Spiking neuro-fuzzy clustering system and its memristor crossbar based implementation

This study proposes a spiking neuro-fuzzy clustering system based on a novel spike encoding scheme and a compatible learning algorithm. In this system, we utilize an analog to binary encoding scheme that properly maps the concept of “distance” in multi-dimensional analog spaces to the concept of “dissimilarity” of binary bits in the equivalent binary spaces. When this scheme is combined with a novel binary to spike encoding scheme and a proper learning algorithm is applied, a powerful clustering algorithm is produced. This algorithm creates flexible fuzzy clusters in its analog input space and modifies their shapes to different convex shapes during the learning process. This system has plausible biological support due to its spike-based learning mechanism, its Quasi Spike Time Dependent Plasticity learning policy and its brain-like fuzzy clustering performance. Moreover, this neuro-fuzzy system is fully implementable on the hybrid memristor-crossbar/CMOS platform. The resultant circuit was simulated on one clustering task carried out in the binary input space on the Simon Lucas handwritten dataset and another clustering task carried out in the analog input space on Fisher׳s Iris standard dataset. The results show that it attained a higher clustering rate in comparison with other algorithms such as the Self Organizing Map, K-mean and the Spiking Radial Basis Function. The circuit was also successfully simulated on an image segmentation task and some clustering tasks performed in noisy spaces with various cluster sizes. Furthermore, the circuit variability analysis shows that device and signal variations up to 20% had no significant impact on the circuit׳s clustering performance, so the system is sufficiently immune to different variations due to its fuzzy nature.     

利用隐含观测量估计将复杂神经网络分解为多个单隐元学习的新方法

本文从统计学的角度研究多层多隐元前神经网络（ＮＮ）的参数估计学习问题,利用ＮＮ激励函数的析线线性近似,提出一种求解多隐层多隐元ＮＮ每个隐元指导信号（隐含观测量）的新方法,利用每个隐元的指导信号估计可以半多隐多层多隐元ＮＮ的参数估计学习转化为多个相互独立的单隐元ＮＮ参数估计学习训练问题,从而将复杂系统参数估计问题转化为简单系统的参数估计问题而得以解决。     

主动学习半监督聚类入侵检测算法

针对聚类的入侵检测算法误报率高的问题,提出一种主动学习半监督聚类入侵检测算法.在半监督聚类过程中应用主动学习策略,主动查询网络中未标记数据与标记数据的约束关系,利用少量的标记数据生成正确的样本模型来指导大量的未标记数据聚类,对聚类后仍未能标记的数据采用改进的K-近邻法进一步确定未标记数据的类型,实现对新攻击类型的检测.实验结果表明了算法的可行性及有效性.     

基于MATLAB仿真的神经元锋电位序列的生成

为了更加逼真地模拟和分析神经系统,提出了一种基于MATLAB的锋电位序列生成方法,这种方法既简单又高效.通过二分高斯(Dichotomized Gaussian DG)模型模拟产生了具有特定相关性系数的二进制锋电位序列,并且做了相关仿真及分析.另外,对这种生成机制扩展到不同时间上的相关性作了分析,并且提出了一种有效的方法来模拟产生相关的锋电位计数.     

Quantized Spiking Neuron With A/D Conversion Functions

This brief presents a simple artificial spiking neuron and proposes its application to an A/D converter. Depending on the initial state, which is an analog input, the neuron can generate spike trains having various spike position patterns. Based on spike position modulation, the spike train can be symbolized by a digital output. As a result, the analog input can be encoded into the digital output. Adjusting a reconfigurable parameter, the neuron can realize various encodings such as binary and Gray encodings. This brief also proposes a simple reconfigurable implementation circuit and experimentally confirms typical A/D conversion functions