一种以环路作为存储单元的联想记忆神经网络

文章提出了一种新型联想记忆神经网络,每个模式被存储在一个通过网络中所有神经元的环路中,连接包括逻辑状态和一组神经元编号,网络中处理和传递的信号为神经元编号组成的序列,神经元执行一组处理这种序列的符号和逻辑运算;网络记忆容量为2N-2N、完全消除了假模式、同时具有更高的记忆效率和可靠性。     

小通用同质脉冲神经膜系统

最近,许多学者针对寻找基于脉冲神经膜系统的小通用计算设备问题进行了研究.脉冲神经膜系统是一种源于神经元之间通过电子脉冲传递信息方式的分布式、并行计算模型.同质脉冲神经膜系统是指一种系统中所有神经元具有相同规则集合的脉冲神经膜系统的受限变体.本文研究了同质脉冲神经膜系统的小通用性:在使用标准规则和权值情况下,作为计算函数的装置,需要53个神经元可以构造一个通用同质脉冲神经膜系统;作为产生数的装置,则需要52个神经元.     

神经元环路中主神经元的模型分析

神经元环路是大脑神经系统的基本单元,而环路的信息输出则由主神经元所决定.本文通过对小脑皮层、嗅球和海马CA1三类不同环路中的主神经元：浦肯野神经元、僧帽神经元和锥体神经元建立给予神经元几何形态和电缆传递的多房室模型,通过它们的动作电位分析和比较,说明不同类型的外界刺激,三个环路中主神经元动作电位的区别;并进一步比较对同类刺激,三类主神经元动作电位的不同,模型验证它们所属环路在神经系统中所起的不同输出功能.     

离散时间Hopfield网络的动力系统分析

离散时间的Hopfield网络模型是一个非线性动力系统．对网络的状态变量引入新的能量函数，利用凸函数次梯度性质可以得到网络状态能量单调减少的条件．对于神经元的连接权值且激活函数单调非减(不一定严格单调增加)的Hopfield网络，若神经元激活函数的增益大于权值矩阵的最小特征值，则全并行时渐进收敛；而当网络串行时，只要网络中每个神经元激活函数的增益与该神经元的自反馈连接权值的和大于零即可．同时，若神经元激活函数单调，网络连接权值对称，利用凸函数次梯度的性质，证明了离散时间的Hopfield网络模型全并行时收敛到周期不大于2的极限环．     

基于粒子群算法优化Spiking神经网络

Spiking神经网络采用神经元的发放时间点进行信息编码,更接近于生物神经元.学习算法的选取对发挥Spiking神经网络的性能有很大的影响.基于BP算法的SpikeProp采用多突触连接的网络结构,利用梯度信息进行网络参数的调整,易于陷入局部最优解;且连接权值的选取只能为正值,否则将不收敛.采用粒子群算法(Particle Swarm Optimization,PSO)进行Spiking网络连接参数的调整,全局收敛性好,减少了对连接权值的约束,简化了网络结构.实验表明,该方法是一种有效的Spiking网络学习方法.     

进化大规模脉冲神经网络的发育方法

通过自然进化得到的脑包含几十亿的神经元和几万亿的神经连接,并表现出复杂的智能行为.受生物脑进化与发育的启发,研究者给出了进化神经网络的发育编码方法,特点是通过基因重用可在较小的基因空间中进行大规模神经网络的快速搜索.以人工基因组模型为框架描述基因调控网络,用基因表达的动态特性表示细胞命运特化的发育过程,提出了一种进化大规模脉冲神经网络的发育方法.该方法的特点在于可以快速有效地发育生成脉冲神经元、神经连接和突触可塑性.相应的食物采集进化实验突现了以神经驱动的自主智能体的智能行为,并验证了该方法对大规模脉冲神经网络的进化能力.     

基于脉冲耦合神经网络的灰度图像边缘提取

提出一种局域窗口内边缘值的计算方法，用所得的结果调制脉冲耦合神经网络神经元的脉冲发放值，利用神经元的同步脉冲发放特性进行图像的边缘提取，在一定程度上消除了噪声的影响，提高了边缘提取的自适应性和准确性。此外引入了图像增强机制，用网络的输出实时地计算更新图像灰度值，从而提高模糊边缘的检测质量。实验表明该算法可以得到令人满意的结果。     

基于改进GA-Elman的无线智能传播损耗预测方法

在5G移动通信系统商用落地的背景下,设计准确、高效的信道估计方法对无线网络性能优化具有重要意义。基于改进GA-Elman算法,提出一种新的无线智能传播损耗预测方法。对Elman神经网络中的连接权值、阈值和隐藏神经元进行实数编码,在隐藏神经元编码中加入二进制控制基因,同时利用自适应遗传算法对权值、阈值和隐藏神经元数量进行优化,解决网络易陷入局部极小值和神经元数目难以确定的问题,从而提高预测性能。仿真结果表明,与仅优化连接权值及阈值的GA-Elman神经网络和标准Elman神经网络相比,该方法具有较高的预测精度。     

视觉感知中特征捆绑建模方法的研究

针对视觉感知中特征的捆绑问题,在传统脉冲耦合神经网络(PCNN)的基础上,提出一种基于强度的PCNN模型。在该模型中,神经元邻域内脉冲发放总强度将不同的特征分离开来,而神经元自身的脉冲发放强度又将属于同一感知对象的不同特征捆绑起来。仿真结果证明,该模型可以实现特征的分离和捆绑。     

用于多脑区神经环路解析的新型光电极阵列

光遗传技术已被广泛用于神经环路的精确解析,帮助人们深入理解神经精神疾病的发病机制。然而在活体水平实现多脑区的光遗传调控和电生理记录仍然极具挑战。文章介绍了一种制备多脑区光电极阵列的方法。这种光电极阵列包含微电极支架和步进装置,可以同时对小鼠 4 个脑区的自发电生理信号(包括神经元放电和场电位)和光遗传调控后诱发的电生理变化进行记录。此外,还采用电化学修饰技术,显著降低了电极界面阻抗,提高了电生理记录信号的质量和稳定性。文章利用该光电极阵列对光遗传调控前后不同脑区之间神经元的同步化关系进行了分析,通过 4'', 6-二脒基-2-苯基吲哚染色确定了光电极的植入位点。实验结果表明,这种多脑区光电极阵列适用于多脑区水平的研究,并且容易与其他在体研究方法结合,实现对特定神经环路的精确解析。     

A Modified Spiking Neuron that Involves Derivative of the State Function at Firing Time

In usual spiking neural networks, the real world information is interpreted as spike time. A spiking neuron of the spiking neural network receives input vector of spike times, and activates a state function x(t) by increasing the time t until the value of x(t) reaches certain threshold value at a firing time t ^a . And t ^a is the output of the spiking neuron. In this paper we propose, and investigate the performance of, a modified spiking neuron, of which the output is a linear combination of the firing time t ^a and the derivative x??(t ^a ). The merit of the modified spiking neuron is shown by numerical experiments for solving some benchmark problems: The computational time of a modified spiking neuron is a little greater than that of a usual spiking neuron, but the accuracy of a modified spiking neuron is almost as good as a usual spiking neural network with a hidden layer.     

Learning Temporally Encoded Patterns in Networks of Spiking Neurons

Networks of spiking neurons are very powerful and versatile models for biological and artificial information processing systems. Especially for modelling pattern analysis tasks in a biologically plausible way that require short response times with high precision they seem to be more appropriate than networks of threshold gates or models that encode analog values in average firing rates. We investigate the question how neurons can learn on the basis of time differences between firing times. In particular, we provide learning rules of the Hebbian type in terms of single spiking events of the pre- and postsynaptic neuron and show that the weights approach some value given by the difference between pre- and postsynaptic firing times with arbitrary high precision.     

Stochastic dynamics of a finite-size spiking neural network

We present a simple Markov model of spiking neural dynamics that can be analytically solved to characterize the stochastic dynamics of a finite-size spiking neural network. We give closed-form estimates for the equilibrium distribution, mean rate, variance, and autocorrelation function of the network activity. The model is applicable to any network where the probability of firing of a neuron in the network depends on only the number of neurons that fired in a previous temporal epoch. Networks with statistically homogeneous connectivity and membrane and synaptic time constants that are not excessively long could satisfy these conditions. Our model completely accounts for the size of the network and correlations in the firing activity. It also allows us to examine how the network dynamics can deviate from mean field theory. We show that the model and solutions are applicable to spiking neural networks in biophysically plausible parameter regimes.     

Improved Izhikevich neurons for spiking neural networks

Spiking neural networks constitute a modern neural network paradigm that overlaps machine learning and computational neurosciences. Spiking neural networks use neuron models that possess a great degree of biological realism. The most realistic model of the neuron is the one created by Alan Lloyd Hodgkin and Andrew Huxley. However, the Hodgkin–Huxley model, while accurate, is computationally very inefficient. Eugene Izhikevich created a simplified neuron model based on the Hodgkin–Huxley equations. This model has better computational efficiency than the original proposed by Hodgkin and Huxley, and yet it can successfully reproduce all known firing patterns. However, there are not many articles dealing with implementations of this model for a functional neural network. This study presents a spiking neural network architecture that utilizes improved Izhikevich neurons with the purpose of evaluating its speed and efficiency. Since the field of spiking neural networks has reinvigorated the interest in biological plausibility, biological realism was an additional goal. The network is tested on the correct classification of logic gates (including XOR) and on the iris dataset. Results and possible improvements are also discussed.     

Accelerating event-driven simulation of spiking neurons with multiple synaptic time constants

The simulation of spiking neural networks (SNNs) is known to be a very time-consuming task. This limits the size of SNN that can be simulated in reasonable time or forces users to overly limit the complexity of the neuron models. This is one of the driving forces behind much of the recent research on event-driven simulation strategies. Although event-driven simulation allows precise and efficient simulation of certain spiking neuron models, it is not straightforward to generalize the technique to more complex neuron models, mostly because the firing time of these neuron models is computationally expensive to evaluate. Most solutions proposed in literature concentrate on algorithms that can solve this problem efficiently. However, these solutions do not scale well when more state variables are involved in the neuron model, which is, for example, the case when multiple synaptic time constants for each neuron are used. In this letter, we show that an exact prediction of the firing time is not required in order to guarantee exact simulation results. Several techniques are presented that try to do the least possible amount of work to predict the firing times. We propose an elegant algorithm for the simulation of leaky integrate-and-fire (LIF) neurons with an arbitrary number of (unconstrained) synaptic time constants, which is able to combine these algorithmic techniques efficiently, resulting in very high simulation speed. Moreover, our algorithm is highly independent of the complexity (i.e., number of synaptic time constants) of the underlying neuron model.     

Spiking神经元输入脉冲扰动敏感性研究

脉冲神经网络是一种基于生物的网络模型,它的输入输出为具有时间特性的脉冲序列,其运行机制相比其他传统人工神经网络更加接近于生物神经网络。神经元之间通过脉冲序列传递信息,这些信息通过脉冲的激发时间编码能够更有效地发挥网络的学习性能。脉冲神经元的时间特性导致了其工作机制较为复杂,而spiking神经元的敏感性反映了当神经元输入发生扰动时输出的spike的变化情况,可以作为研究神经元内部工作机制的工具。不同于传统的神经网络,spiking神经元敏感性定义为输出脉冲的变化时刻个数与运行时间长度的比值,能直接反映出输入扰动对输出的影响程度。通过对不同形式的输入扰动敏感性的分析,可以看出spiking神经元的敏感性较为复杂,当全体突触发生扰动时,神经元为定值,而当部分突触发生扰动时,不同突触的扰动会导致不同大小的神经元敏感性。     

仿生型脉冲神经网络学习算法和网络模型

为解决脉冲神经网络训练困难的问题,基于仿生学思路,提出脉冲神经网络的权值学习算法和结构学习算法,设计一种含有卷积结构的脉冲神经网络模型,搭建适合脉冲神经网络的软件仿真平台。实验结果表明,权值学习算法训练的网络对MNIST数据集识别准确率能够达到84.12%,具备良好的快速收敛能力和低功耗特点;结构学习算法能够自动生成网络结构,具有高度生物相似性。     

Multistability in spiking neuron models of delayed recurrent inhibitory loops

We consider the effect of the effective timing of a delayed feedback on the excitatory neuron in a recurrent inhibitory loop, when biological realities of firing and absolute refractory period are incorporated into a phenomenological spiking linear or quadratic integrate-and-fire neuron model. We show that such models are capable of generating a large number of asymptotically stable periodic solutions with predictable patterns of oscillations. We observe that the number of fixed points of the so-called phase resetting map coincides with the number of distinct periods of all stable periodic solutions rather than the number of stable patterns. We demonstrate how configurational information corresponding to these distinct periods can be explored to calculate and predict the number of stable patterns.     

Action Recognition Using a Bio-Inspired Feedforward Spiking Network

We propose a bio-inspired feedforward spiking network modeling two brain areas dedicated to motion (V1 and MT), and we show how the spiking output can be exploited in a computer vision application: action recognition. In order to analyze spike trains, we consider two characteristics of the neural code: mean firing rate of each neuron and synchrony between neurons. Interestingly, we show that they carry some relevant information for the action recognition application. We compare our results to Jhuang et al. (Proceedings of the 11th international conference on computer vision, pp. 1–8, 2007) on the Weizmann database. As a conclusion, we are convinced that spiking networks represent a powerful alternative framework for real vision applications that will benefit from recent advances in computational neuroscience.     

基于脉冲神经网络的红外目标提取

模拟生物信息处理机制,设计了一种用于红外目标提取的脉冲神经网络(SNN)。首先,利用输入层脉冲神经元将激励图像转化为脉冲序列;其次,采用中间层脉冲神经元输出脉冲的密度编码红外图像目标的轮廓像素和非目标轮廓像素;最后,根据输出层神经元输出脉冲的密度是否超过阈值提取红外目标。实验结果表明,设计的脉冲神经网络具有较好的红外目标提取性能,并且符合生物视觉信息处理机制。