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。     

脉冲神经元脉冲序列学习方法综述

脉冲神经元是一种新颖的人工神经元模型,其有监督学习的目的是通过学习使得神经元激发出一串通过精确时间编码来表达特定信息的脉冲序列,故称为脉冲序列学习。针对单神经元的脉冲序列学习应用价值显著、理论基础多样、影响因素众多的特点,对已有脉冲序列学习方法进行了综述对比。首先介绍了脉冲神经元模型与脉冲序列学习的基本概念;然后详细介绍了典型的脉冲序列学习方法,指出了每种方法的理论基础和突触权值调整方式;最后通过实验比较了这些学习方法的性能,系统总结了每种方法的特点,并且讨论了脉冲序列学习的研究现状和进一步的发展方向。该研究结果有助于脉冲序列学习方法的综合应用。     

面向图像识别的多层脉冲神经网络学习算法综述

相较于第1代和第2代神经网络,第3代神经网络的脉冲神经网络是一种更加接近于生物神经网络的模型,因此更具有生物可解释性和低功耗性。基于脉冲神经元模型,脉冲神经网络可以通过脉冲信号的形式模拟生物信号在神经网络中的传播,通过脉冲神经元的膜电位变化来发放脉冲序列,脉冲序列通过时空联合表达不仅传递了空间信息还传递了时间信息。当前面向模式识别任务的脉冲神经网络模型性能还不及深度学习,其中一个重要原因在于脉冲神经网络的学习方法不成熟,深度学习中神经网络的人工神经元是基于实数形式的输出,这使得其可以使用全局性的反向传播算法对深度神经网络的参数进行训练,脉冲序列是二值性的离散输出,这直接导致对脉冲神经网络的训练存在一定困难,如何对脉冲神经网络进行高效训练是一个具有挑战的研究问题。本文首先总结了脉冲神经网络研究领域中的相关学习算法,然后对其中主要的方法:直接监督学习、无监督学习的算法以及ANN2SNN的转换算法进行分析介绍,并对其中代表性的工作进行对比分析,最后基于对当前主流方法的总结,对未来更高效、更仿生的脉冲神经网络参数学习方法进行展望。     

基于卷积计算的多层脉冲神经网络的监督学习

针对脉冲神经元基于精确定时的多脉冲编码信息的特点,提出了一种基于卷积计算的多层脉冲神经网络监督学习的新算法。该算法应用核函数的卷积计算将离散的脉冲序列转换为连续函数,在多层前馈脉冲神经网络结构中,使用梯度下降的方法得到基于核函数卷积表示的学习规则,并用来调整神经元连接的突触权值。在实验部分,首先验证了该算法学习脉冲序列的效果,然后应用该算法对Iris数据集进行分类。结果显示,该算法能够实现脉冲序列复杂时空模式的学习,对非线性模式分类问题具有较高的分类正确率。     

基于脉冲神经网络的语音识别方法的初步探究

本文提出了一种基于脉冲神经网络SNN的语音识剐方法。该方法以H-H脉冲神经网络模型为基础,采用圆映射的脉冲编码理论将脉冲序列转化为符号序列;同时,以符号序列的距离函数作为语音识别的相似度函数,结合SNN计算能力和实时性强等优势,对语音识别问题进行了初步探讨和研究。实验结果表明,本文提出的特别的研究方法是可行的,
具有深入研究的价值。     

基于梯度下降的脉冲神经元精确序列学习算法

基于梯度下降的脉冲神经元有监督学习算法通过计算梯度最小化目标序列和实际输出序列间的误差使得神经元能激发出目标脉冲序列。然而该算法中的误差函数是基于实际输出脉冲序列和相对应的目标输出脉冲序列动态构建而成,导致算法在收敛时可能出现实际输出序列的个数和期望输出个数不相等的情况。针对这一缺陷提出了一种改进的脉冲神经元梯度下降学习算法,算法在学习过程中检测目标序列脉冲个数和实际激发脉冲个数,并引入虚拟实际激发脉冲和期望激发脉冲构建误差函数以分别解决激发个数不足和激发个数多余的问题。实验结果证明该算法能有效地防止学习算法在输出脉冲个数不等的情况下提前结束,使得神经元能够精确地激发出目标脉冲序列。     

基于HVS与PCNN的彩色图像增强

提出一种新的彩色图像增强方法:将RGB空间转化为HIS空间后保持H分量不变,对S分量进行指数拉伸;而对I分量则利用脉冲耦合神经网络的特性将原始图像的灰度信息与空间信息一起耦合到神经元的内部活动项,然后利用人类视觉系统模型构建动态阈值与其比较得到增强图像.实验证实了这种方法的有效性.     

基于BPCNN的图像分割方法

研究一种双向脉冲耦合神经网络(BPCNN)的图像分割问题.首先将彩色图像量化结果或灰度图像作为BPCNN的外部输入激励,每个神经元根据BPCNN的正向脉冲产生器或逆向脉冲产生器发布脉冲信号,实现对图像的初始分割;然后根据初分割图像的区域距离合并过分割区域,最后提出一种综合多种分割评价准则的分割评价体系,并对分割结果进行了评价.实验结果表明,BPCNN算法在多类图像上均取得较好的分割效果,利用实验数据对比了多种常用分割算法,BPCNN算法在综合评价体系上有明显的优越性.     

跨脉冲传播的深度脉冲神经网络训练方法

基于反向传播的脉冲神经网络（SNNs）的训练方法仍面临着诸多问题与挑战,包括脉冲发放过程不可微分、脉冲神经元具有复杂的时空动力过程等。此外,SNNs反向传播训练方法往往没有考虑误差信号在相邻脉冲间的关系,大大降低了网络模型的准确性。为此,提出一种跨脉冲误差传播的深度脉冲神经网络训练方法（cross-spike error backpropagation,CSBP）,将神经元的误差反向传播分成脉冲发放时间随突触后膜电位变化关系和相邻脉冲发放时刻点间的依赖关系两种依赖关系。其中,通过前者解决了脉冲不可微分的问题,通过后者明确了脉冲间的依赖关系,使得误差信号能跨脉冲传播,提升了生物合理性。此外,并对早期脉冲残差网络架构存在的模型表示能力不足问题进行研究,通过修改脉冲残余块的结构顺序,进一步提高了网络性能。实验结果表明,所提方法比基于脉冲时间的最优训练算法有着明显的提升,相同架构下,在CIFAR10数据集上提升2.98%,在DVS-CIFAR10数据集上提升2.26%。     

基于自适应编码的脉冲神经网络

脉冲神经网络(SNN)采用脉冲序列表征和传递信息,与传统人工神经网络相比更具有生物可解释性,但典型SNN的特征提取能力受到其结构限制,对于图像数据等多分类任务的识别准确率不高,不能与卷积神经网络相媲美。为此提出一种新型的自适应编码脉冲神经网络(SCSNN),将CNN的特征提取能力与SNN的生物可解释性结合起来,采用生物神经元动态脉冲触发特性构建网络结构,并设计了一种新的替代梯度反向传播方法直接训练网络参数。所提出的SCSNN分别在MNIST和Fashion-MNIST数据集进行验证,取得较好的识别结果,在MNIST数据集上准确率达到了99.62%,在Fashion-MNIST数据集上准确率达到了93.52%,验证了其有效性。     

A gradient descent rule for spiking neurons emitting multiple spikes

A supervised learning rule for Spiking Neural Networks (SNNs) is presented that can cope with neurons that spike multiple times. The rule is developed by extending the existing SpikeProp algorithm which could only be used for one spike per neuron. The problem caused by the discontinuity in the spike process is counteracted with a simple but effective rule, which makes the learning process more efficient. Our learning rule is successfully tested on a classification task of Poisson spike trains. We also applied the algorithm on a temporal version of the XOR problem and show that it is possible to learn this classical problem using only one spiking neuron making use of a hair-trigger situation.     

Finding the event structure of neuronal spike trains

Neurons in sensory systems convey information about physical stimuli in their spike trains. In vitro, single neurons respond precisely and reliably to the repeated injection of the same fluctuating current, producing regions of elevated firing rate, termed events. Analysis of these spike trains reveals that multiple distinct spike patterns can be identified as trial-to-trial correlations between spike times (Fellous, Tiesinga, Thomas, & Sejnowski, 2004 ). Finding events in data with realistic spiking statistics is challenging because events belonging to different spike patterns may overlap. We propose a method for finding spiking events that uses contextual information to disambiguate which pattern a trial belongs to. The procedure can be applied to spike trains of the same neuron across multiple trials to detect and separate responses obtained during different brain states. The procedure can also be applied to spike trains from multiple simultaneously recorded neurons in order to identify volleys of near-synchronous activity or to distinguish between excitatory and inhibitory neurons. The procedure was tested using artificial data as well as recordings in vitro in response to fluctuating current waveforms.     

脉冲神经膜系统在穷举使用规则下产生的二进制字符串语言

脉冲神经膜系统是基于大脑中神经元之间通过突触相瓦协作、处理脉冲的生物现象提出的一种新的模型,文中在穷举使用规则的情况下考虑将脉冲神经膜系统作为串语言产生器:当输出神经元发送出一个或多个神经脉冲时,用数字1表示,否则用数字0表示,当计算停止时,把产生的二进制串定义为系统的计算结果.在文中,作者让明了在穷举使用规则的情况下,具有一个神经元的脉冲神经膜系统可以刻画二进制有限语言,并且证明了在不限制神经元个数的情况下,该系统可以刻画递归可枚举语言.     

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.     

脉冲视觉研究进展

视频是视觉信息处理的基础概念,传统视频的帧率只有几十Hz,不能记录光的高速变化过程,成为限制机器视觉速度的天花板,其根本原因在于视频概念脱胎于胶片成像,未能发挥电子和数字技术的潜力。脉冲视觉模型通过感光器件捕获光子,累积能量达到约定阈值时产生脉冲,形成脉冲的时间越长,表明收到的光信号越弱,反之光信号越强,据此可估计任意时刻的光强,从而实现连续成像。采用普通器件,研制了比影视视频快千倍的超高速成像芯片和相机,进而基于脉冲神经网络实现了超高速目标检测、跟踪和识别,打破了机器视觉提速依赖算力线性增长的传统范式。本文从脉冲视觉模型表达视觉信息的生物学基础和物理原理出发,介绍了脉冲视觉原理的软件模拟器及其模拟真实世界光子传播的计算过程,描述了基于脉冲视觉原理的高灵敏光电传感器件及芯片的工作机理和结构设计、基于脉冲视觉的影像重建原理以及脉冲视觉信号与普通图像信号融合的计算摄像算法与计算摄像系统,介绍了基于脉冲神经网络的超高速运动目标检测、跟踪与识别,通过对比国际国内相关研究内容和发展现状,展望了脉冲视觉的发展与演进方向。脉冲视觉芯片和系统在工业(高铁、电力和轮机等不停机监测,智能制造高速监视等)、民用(高速相机、智能交通、辅助驾驶、司法取证和体育判罚等)以及国防(高速对抗)等领域都具有巨大应用潜力,是未来值得重点关注和研究的一个重要方向。     

The dependence of spike field coherence on expected intensity

The coherence between neural spike trains and local-field potential recordings, called spike-field coherence, is of key importance in many neuroscience studies. In this work, aside from questions of estimator performance, we demonstrate that theoretical spike-field coherence for a broad class of spiking models depends on the expected rate of spiking. This rate dependence confounds the phase locking of spike events to field-potential oscillations with overall neuron activity and is demonstrated analytically, for a large class of stochastic models, and in simulation. Finally, the relationship between the spike-field coherence and the intensity field coherence is detailed analytically. This latter quantity is independent of neuron firing rate and, under commonly found conditions, is proportional to the probability that a neuron spikes at a specific phase of field oscillation. Hence, intensity field coherence is a rate-independent measure and a candidate on which to base the appropriate statistical inference of spike field synchrony.     

Learning beyond finite memory in recurrent networks of spiking neurons

We investigate possibilities of inducing temporal structures without fading memory in recurrent networks of spiking neurons strictly operating in the pulse-coding regime. We extend the existing gradient-based algorithm for training feedforward spiking neuron networks, SpikeProp (Bohte, Kok, & La Poutré, 2002), to recurrent network topologies, so that temporal dependencies in the input stream are taken into account. It is shown that temporal structures with unbounded input memory specified by simple Moore machines (MM) can be induced by recurrent spiking neuron networks (RSNN). The networks are able to discover pulse-coded representations of abstract information processing states coding potentially unbounded histories of processed inputs. We show that it is often possible to extract from trained RSNN the target MM by grouping together similar spike trains appearing in the recurrent layer. Even when the target MM was not perfectly induced in a RSNN, the extraction procedure was able to reveal weaknesses of the induced mechanism and the extent to which the target machine had been learned.     

What can a neuron learn with spike-timing-dependent plasticity?

Spiking neurons are very flexible computational modules, which can implement with different values of their adjustable synaptic parameters an enormous variety of different transformations F from input spike trains to output spike trains. We examine in this letter the question to what extent a spiking neuron with biologically realistic models for dynamic synapses can be taught via spike-timing-dependent plasticity (STDP) to implement a given transformation F. We consider a supervised learning paradigm where during training, the output of the neuron is clamped to the target signal (teacher forcing). The well-known perceptron convergence theorem asserts the convergence of a simple supervised learning algorithm for drastically simplified neuron models (McCulloch-Pitts neurons). We show that in contrast to the perceptron convergence theorem, no theoretical guarantee can be given for the convergence of STDP with teacher forcing that holds for arbitrary input spike patterns. On the other hand, we prove that average case versions of the perceptron convergence theorem hold for STDP in the case of uncorrelated and correlated Poisson input spike trains and simple models for spiking neurons. For a wide class of cross-correlation functions of the input spike trains, the resulting necessary and sufficient condition can be formulated in terms of linear separability, analogously as the well-known condition of learnability by perceptrons. However, the linear separability criterion has to be applied here to the columns of the correlation matrix of the Poisson input. We demonstrate through extensive computer simulations that the theoretically predicted convergence of STDP with teacher forcing also holds for more realistic models for neurons, dynamic synapses, and more general input distributions. In addition, we show through computer simulations that these positive learning results hold not only for the common interpretation of STDP, where STDP changes the weights of synapses, but also for a more realistic interpretation suggested by experimental data where STDP modulates the initial release probability of dynamic synapses.