由于其强大的时空信息表示能力,尖峰神经网络(SNN)引起了很多关注。胶囊神经网络(CAPSNET)在不同级别的组装和耦合功能方面做得好。在这里,我们通过将胶囊引入尖刺神经网络的建模来提出尖峰帽。此外,我们提出了更具生物合理的尖峰定时依赖性可塑性路线机构。通过充分考虑低水平尖峰胶囊与高级尖峰胶囊之间的时空关系,它们之间的耦合能力进一步提高。我们在Mnist和FashionMnist数据集上进行了验证的实验。与其他优秀的SNN模型相比,我们的算法仍然实现了高性能。我们的尖峰帽完全结合了SNN和Capsnet的增强,并对噪声和仿射变换表现出强大的稳健性。通过向测试数据集添加不同的盐胡椒和高斯噪声,实验结果表明,当有更多的噪音时,我们的尖峰帽显示出更强大的性能,而人工神经网络无法正确澄清。同样,我们的尖峰帽显示出强烈的概括,可以在漂式数据集上仿射转换。
translated by 谷歌翻译
反向传播算法促进了深度学习的快速发展,但它依赖大量标记的数据,并且人类学习的方式仍然存在很大的差距。人的大脑可以以自组织和无监督的方式迅速学习各种概念知识,这是通过人类大脑中多个学习规则和结构的协调来实现的。依赖峰值的依赖性可塑性(STDP)是大脑中广泛的学习规则,但是单独使用STDP训练的尖峰神经网络效率低下且性能差。在本文中,从短期突触可塑性中汲取灵感,我们设计了一种自适应突触过滤器,并将自适应阈值平衡作为神经元可塑性介绍,以丰富SNN的表示能力。我们还引入了自适应的横向抑制连接,以动态调整尖峰平衡,以帮助网络学习更丰富的功能。为了加速和稳定无监督的尖峰神经网络的训练,我们设计了一个样本的时间批次STDP,该STDP根据多个样本和多个矩来更新重量。我们已经进行了有关MNIST和FashionMnist的实验,并实现了基于STDP的当前无监督的尖峰神经网络的最先进性能。我们的模型在小样本学习中还显示出强烈的优势。
translated by 谷歌翻译
尖峰神经网络(SNN)在各种智能场景中都表现出了出色的功能。大多数现有的训练SNN方法基于突触可塑性的概念。但是,在现实的大脑中学习还利用了神经元的内在非突触机制。生物神经元的尖峰阈值是一种关键的固有神经元特征,在毫秒的时间尺度上表现出丰富的动力学,并已被认为是一种促进神经信息处理的基本机制。在这项研究中,我们开发了一种新型的协同学习方法,该方法同时训练SNN中的突触权重和尖峰阈值。经过突触阈值协同学习(STL-SNN)训练的SNN在各种静态和神经形态数据集上的精度明显高于接受两种突触学习(SL)和阈值学习(TL)的单独学习模型(TL)的SNN。在训练过程中,协同学习方法优化了神经阈值,通过适当的触发速率为网络提供稳定的信号传输。进一步的分析表明,STL-SNN对嘈杂的数据是可靠的,并且对深网结构表现出低的能耗。此外,通过引入广义联合决策框架(JDF),可以进一步提高STL-SNN的性能。总体而言,我们的发现表明,突触和内在的非突触机制之间的生物学上合理的协同作用可能为开发高效的SNN学习方法提供了一种有希望的方法。
translated by 谷歌翻译
Emergence of deep neural networks (DNNs) has raised enormous attention towards artificial neural networks (ANNs) once again. They have become the state-of-the-art models and have won different machine learning challenges. Although these networks are inspired by the brain, they lack biological plausibility, and they have structural differences compared to the brain. Spiking neural networks (SNNs) have been around for a long time, and they have been investigated to understand the dynamics of the brain. However, their application in real-world and complicated machine learning tasks were limited. Recently, they have shown great potential in solving such tasks. Due to their energy efficiency and temporal dynamics there are many promises in their future development. In this work, we reviewed the structures and performances of SNNs on image classification tasks. The comparisons illustrate that these networks show great capabilities for more complicated problems. Furthermore, the simple learning rules developed for SNNs, such as STDP and R-STDP, can be a potential alternative to replace the backpropagation algorithm used in DNNs.
translated by 谷歌翻译
脑启发的尖峰神经网络(SNN)已成功应用于许多模式识别域。基于SNN的深层结构在感知任务(例如图像分类,目标检测)中取得了可观的结果。但是,深SNN在加强学习(RL)任务中的应用仍然是一个问题。尽管以前有关于SNN和RL组合的研究,但其中大多数专注于浅网络的机器人控制问题,或使用ANN-SNN转换方法来实施Spiking Spiking Deep Q Network(SDQN)。在这项工作中,我们数学分析了SDQN中尖峰信号特征消失的问题,并提出了一种基于潜在的层归一化(PBLN)方法,以直接训练尖峰尖峰深度Q网络。实验表明,与最先进的ANN-SNN转换方法和其他SDQN作品相比,建议的PBLN Spiking Deep Q Networks(PL-SDQN)在Atari游戏任务上取得了更好的性能。
translated by 谷歌翻译
尖峰神经网络(SNN)是一种受脑启发的模型,具有更时空的信息处理能力和计算能效效率。但是,随着SNN深度的增加,由SNN​​的重量引起的记忆问题逐渐引起了人们的注意。受到人工神经网络(ANN)量化技术的启发,引入了二进制SNN(BSNN)来解决记忆问题。由于缺乏合适的学习算法,BSNN通常由ANN-SNN转换获得,其准确性将受到训练有素的ANN的限制。在本文中,我们提出了具有准确性损失估计器的超低潜伏期自适应局部二进制二进制尖峰神经网络(ALBSNN),该网络层动态选择要进行二进制的网络层,以通过评估由二进制重量引起的错误来确保网络的准确性在网络学习过程中。实验结果表明,此方法可以将存储空间降低超过20%,而不会丢失网络准确性。同时,为了加速网络的训练速度,引入了全球平均池(GAP)层,以通过卷积和合并的组合替换完全连接的层,以便SNN可以使用少量时间获得更好识别准确性的步骤。在仅使用一个时间步骤的极端情况下,我们仍然可以在三个不同的数据集(FashionMnist,CIFAR-10和CIFAR-10和CIFAR-100)上获得92.92%,91.63%和63.54%的测试精度。
translated by 谷歌翻译
尖峰神经网络(SNNS)模仿大脑计算策略,并在时空信息处理中表现出很大的功能。作为人类感知的基本因素,视觉关注是指生物视觉系统中显着区域的动态选择过程。尽管视觉注意力的机制在计算机视觉上取得了巨大成功,但很少会引入SNN中。受到预测注意重新映射的实验观察的启发,我们在这里提出了一种新的时空通道拟合注意力(SCTFA)模块,该模块可以通过使用历史积累的空间通道信息来指导SNN有效地捕获潜在的目标区域。通过在三个事件流数据集(DVS手势,SL-Animals-DVS和MNIST-DVS)上进行系统评估,我们证明了带有SCTFA模块(SCTFA-SNN)的SNN不仅显着超过了基线SNN(BL-SNN)(BL-SNN)(BL-SNN)以及其他两个具有退化注意力模块的SNN模型,但也通过现有最新方法实现了竞争精度。此外,我们的详细分析表明,所提出的SCTFA-SNN模型对噪声和出色的稳定性具有强大的稳健性,同时保持了可接受的复杂性和效率。总体而言,这些发现表明,适当纳入大脑的认知机制可能会提供一种有希望的方法来提高SNN的能力。
translated by 谷歌翻译
尽管人工智能模型的进步,神经网络仍然无法实现人的表现,部分原因是由于信息是如何编码,并与人脑处理分歧。在一个人工神经网络(ANN)信息是使用统计方法来表示和处理为拟合函数,使在图像,文本和语音处理处理的结构模式。然而,实质性的变化的数据,例如统计特性,扭转的图像的背景,显着降低性能。在这里,我们提出了一个量子叠加扣球量子机制和现象在大脑中,它能够处理图像背景色的反转激发神经网络(QS-SNN)。的QS-SNN结合量子理论与脑启发从计算的角度来看尖峰神经网络模型,从而产生更鲁棒的性能与传统的人工神经网络模型进行比较,处理嘈杂输入时尤其如此。这里给出的结果将成为今后努力开发大脑启发的人工智能。
translated by 谷歌翻译
Tactile sensing is essential for a variety of daily tasks. And recent advances in event-driven tactile sensors and Spiking Neural Networks (SNNs) spur the research in related fields. However, SNN-enabled event-driven tactile learning is still in its infancy due to the limited representation abilities of existing spiking neurons and high spatio-temporal complexity in the event-driven tactile data. In this paper, to improve the representation capability of existing spiking neurons, we propose a novel neuron model called "location spiking neuron", which enables us to extract features of event-based data in a novel way. Specifically, based on the classical Time Spike Response Model (TSRM), we develop the Location Spike Response Model (LSRM). In addition, based on the most commonly-used Time Leaky Integrate-and-Fire (TLIF) model, we develop the Location Leaky Integrate-and-Fire (LLIF) model. Moreover, to demonstrate the representation effectiveness of our proposed neurons and capture the complex spatio-temporal dependencies in the event-driven tactile data, we exploit the location spiking neurons to propose two hybrid models for event-driven tactile learning. Specifically, the first hybrid model combines a fully-connected SNN with TSRM neurons and a fully-connected SNN with LSRM neurons. And the second hybrid model fuses the spatial spiking graph neural network with TLIF neurons and the temporal spiking graph neural network with LLIF neurons. Extensive experiments demonstrate the significant improvements of our models over the state-of-the-art methods on event-driven tactile learning. Moreover, compared to the counterpart artificial neural networks (ANNs), our SNN models are 10x to 100x energy-efficient, which shows the superior energy efficiency of our models and may bring new opportunities to the spike-based learning community and neuromorphic engineering.
translated by 谷歌翻译
尖峰神经网络(SNN)是第三代人工神经网络,可以在神经形态硬件上实施节能。但是,尖峰的离散传播给坚固且高性能的学习机制带来了重大挑战。大多数现有的作品仅着眼于神经元之间的学习,但忽略了突触之间的影响,从而导致稳健性和准确性丧失。为了解决这个问题,我们通过对突触(APB)(APB)之间的关联可塑性(APB)进行建模,从而提出了一种强大而有效的学习机制。使用提出的APB方法,当其他神经元同时刺激时,同一神经元的突触通过共享因素相互作用。此外,我们提出了一种时空种植和翻转(STCF)方法,以提高网络的概括能力。广泛的实验表明,我们的方法在静态CIFAR-10数据集和神经形态MNIST-DV的最新性能上实现了卓越的性能,通过轻量级卷积网络,CIFAR10-DVS数据集。据我们所知,这是第一次探索突触之间的学习方法和神经形态数据的扩展方法。
translated by 谷歌翻译
近年来,尖峰神经网络(SNN)由于其丰富的时空动力学,各种编码方法和事件驱动的特征而自然拟合神经形态硬件,因此在脑启发的智能上受到了广泛的关注。随着SNN的发展,受到脑科学成就启发和针对人工通用智能的新兴研究领域的脑力智能变得越来越热。本文回顾了最新进展,并讨论了来自五个主要研究主题的SNN的新领域,包括基本要素(即尖峰神经元模型,编码方法和拓扑结构),神经形态数据集,优化算法,软件,软件和硬件框架。我们希望我们的调查能够帮助研究人员更好地了解SNN,并激发新作品以推进这一领域。
translated by 谷歌翻译
Spiking neural networks (SNNs) are receiving increasing attention due to their low power consumption and strong bio-plausibility. Optimization of SNNs is a challenging task. Two main methods, artificial neural network (ANN)-to-SNN conversion and spike-based backpropagation (BP), both have their advantages and limitations. For ANN-to-SNN conversion, it requires a long inference time to approximate the accuracy of ANN, thus diminishing the benefits of SNN. With spike-based BP, training high-precision SNNs typically consumes dozens of times more computational resources and time than their ANN counterparts. In this paper, we propose a novel SNN training approach that combines the benefits of the two methods. We first train a single-step SNN by approximating the neural potential distribution with random noise, then convert the single-step SNN to a multi-step SNN losslessly. The introduction of Gaussian distributed noise leads to a significant gain in accuracy after conversion. The results show that our method considerably reduces the training and inference times of SNNs while maintaining their high accuracy. Compared to the previous two methods, ours can reduce training time by 65%-75% and achieves more than 100 times faster inference speed. We also argue that the neuron model augmented with noise makes it more bio-plausible.
translated by 谷歌翻译
最近的研究表明,卷积神经网络(CNNS)不是图像分类的唯一可行的解决方案。此外,CNN中使用的重量共享和反向验证不对应于预测灵长类动物视觉系统中存在的机制。为了提出更加生物合理的解决方案,我们设计了使用峰值定时依赖性塑性(STDP)和其奖励调制变体(R-STDP)学习规则训练的本地连接的尖峰神经网络(SNN)。使用尖刺神经元和局部连接以及强化学习(RL)将我们带到了所提出的架构中的命名法生物网络。我们的网络由速率编码的输入层组成,后跟局部连接的隐藏层和解码输出层。采用尖峰群体的投票方案进行解码。我们使用Mnist DataSet获取图像分类准确性,并评估我们有益于于不同目标响应的奖励系统的稳健性。
translated by 谷歌翻译
Event-based simulations of Spiking Neural Networks (SNNs) are fast and accurate. However, they are rarely used in the context of event-based gradient descent because their implementations on GPUs are difficult. Discretization with the forward Euler method is instead often used with gradient descent techniques but has the disadvantage of being computationally expensive. Moreover, the lack of precision of discretized simulations can create mismatches between the simulated models and analog neuromorphic hardware. In this work, we propose a new exact error-backpropagation through spikes method for SNNs, extending Fast \& Deep to multiple spikes per neuron. We show that our method can be efficiently implemented on GPUs in a fully event-based manner, making it fast to compute and precise enough for analog neuromorphic hardware. Compared to the original Fast \& Deep and the current state-of-the-art event-based gradient-descent algorithms, we demonstrate increased performance on several benchmark datasets with both feedforward and convolutional SNNs. In particular, we show that multi-spike SNNs can have advantages over single-spike networks in terms of convergence, sparsity, classification latency and sensitivity to the dead neuron problem.
translated by 谷歌翻译
Spiking neural networks (SNN) are a viable alternative to conventional artificial neural networks when energy efficiency and computational complexity are of importance. A major advantage of SNNs is their binary information transfer through spike trains. The training of SNN has, however, been a challenge, since neuron models are non-differentiable and traditional gradient-based backpropagation algorithms cannot be applied directly. Furthermore, spike-timing-dependent plasticity (STDP), albeit being a spike-based learning rule, updates weights locally and does not optimize for the output error of the network. We present desire backpropagation, a method to derive the desired spike activity of neurons from the output error. The loss function can then be evaluated locally for every neuron. Incorporating the desire values into the STDP weight update leads to global error minimization and increasing classification accuracy. At the same time, the neuron dynamics and computational efficiency of STDP are maintained, making it a spike-based supervised learning rule. We trained three-layer networks to classify MNIST and Fashion-MNIST images and reached an accuracy of 98.41% and 87.56%, respectively. Furthermore, we show that desire backpropagation is computationally less complex than backpropagation in traditional neural networks.
translated by 谷歌翻译
我们提出了一种新的学习算法,使用传统的人工神经网络(ANN)作为代理训练尖刺神经网络(SNN)。我们分别与具有相同网络架构和共享突触权重的集成和火(IF)和Relu神经元进行两次SNN和ANN网络。两个网络的前进通过完全独立。通过假设具有速率编码的神经元作为Relu的近似值,我们将SNN中的SNN的误差进行了回复,以更新共享权重,只需用SNN的ANN最终输出替换ANN最终输出。我们将建议的代理学习应用于深度卷积的SNNS,并在Fahion-Mnist和CiFar10的两个基准数据集上进行评估,分别为94.56%和93.11%的分类准确性。所提出的网络可以优于培训的其他深鼻涕,训练,替代学习,代理梯度学习,或从深处转换。转换的SNNS需要长时间的仿真时间来达到合理的准确性,而我们的代理学习导致高效的SNN,模拟时间较短。
translated by 谷歌翻译
尖峰神经网络(SNN)引起了脑启发的人工智能和计算神经科学的广泛关注。它们可用于在多个尺度上模拟大脑中的生物信息处理。更重要的是,SNN是适当的抽象水平,可以将大脑和认知的灵感带入人工智能。在本文中,我们介绍了脑启发的认知智力引擎(Braincog),用于创建脑启发的AI和脑模拟模型。 Braincog将不同类型的尖峰神经元模型,学习规则,大脑区域等作为平台提供的重要模块。基于这些易于使用的模块,BrainCog支持各种受脑启发的认知功能,包括感知和学习,决策,知识表示和推理,运动控制和社会认知。这些受脑启发的AI模型已在各种受监督,无监督和强化学习任务上有效验证,并且可以用来使AI模型具有多种受脑启发的认知功能。为了进行大脑模拟,Braincog实现了决策,工作记忆,神经回路的结构模拟以及小鼠大脑,猕猴大脑和人脑的整个大脑结构模拟的功能模拟。一个名为BORN的AI引擎是基于Braincog开发的,它演示了如何将Braincog的组件集成并用于构建AI模型和应用。为了使科学追求解码生物智能的性质并创建AI,Braincog旨在提供必要且易于使用的构件,并提供基础设施支持,以开发基于脑部的尖峰神经网络AI,并模拟认知大脑在多个尺度上。可以在https://github.com/braincog-x上找到Braincog的在线存储库。
translated by 谷歌翻译
尖峰神经网络(SNN)已成为用于分类任务的硬件有效体系结构。基于尖峰的编码的惩罚是缺乏完全使用尖峰执行的通用训练机制。已经进行了几项尝试,用于采用在非加速人工神经网络(ANN)中使用的强大反向传播(BP)技术:(1)SNN可以通过外部计算的数值梯度来训练。 (2)基于天然尖峰的学习的主要进步是使用具有分阶段的前向/向后传递的尖峰时间依赖性可塑性(STDP)的近似反向传播。但是,在此类阶段之间的信息传输需要外部内存和计算访问。这是神经形态硬件实现的挑战。在本文中,我们提出了一种基于随机SNN的后式Prop(SSNN-BP)算法,该算法利用复合神经元同时计算前向通行激活,并用尖峰明确计算前向传递梯度。尽管签名的梯度值是基于SPIKE的表示的挑战,但我们通过将梯度信号分为正和负流来解决这一问题。复合神经元以随机尖峰传播的形式编码信息,并将反向传播的权重更新转换为时间和空间上局部离散的STDP类似STDP的Spike Concike更新,使其与硬件友好的电阻式处理单元(RPU)兼容。此外,我们的方法使用足够长的尖峰训练来接近BP ANN基线。最后,我们表明,可以通过强制执行胜利者的抑制性横向连接来实现软磁体交叉渗透损失函数。我们的SNN通过与MNIST,时尚和扩展的MNIST数据集的ANN相当的性能来表现出极好的概括。因此,SSNN-BP可以使BP与纯粹基于尖峰的神经形态硬件兼容。
translated by 谷歌翻译
由于它们的低能量消耗,对神经形态计算设备上的尖刺神经网络(SNNS)越来越兴趣。最近的进展使培训SNNS在精度方面开始与传统人工神经网络(ANNS)进行竞争,同时在神经胸壁上运行时的节能。然而,培训SNNS的过程仍然基于最初为ANNS开发的密集的张量操作,这不利用SNN的时空稀疏性质。我们在这里介绍第一稀疏SNN BackPropagation算法,该算法与最新的现有技术实现相同或更好的准确性,同时显着更快,更高的记忆力。我们展示了我们对不同复杂性(时尚 - MNIST,神经影像学 - MNIST和Spiking Heidelberg数字的真实数据集的有效性,在不失精度的情况下实现了高达150倍的后向通行证的加速,而不会减少精度。
translated by 谷歌翻译
Sparse representation has attracted great attention because it can greatly save storage re- sources and find representative features of data in a low-dimensional space. As a result, it may be widely applied in engineering domains including feature extraction, compressed sensing, signal denoising, picture clustering, and dictionary learning, just to name a few. In this paper, we propose a spiking sampling network. This network is composed of spiking neurons, and it can dynamically decide which pixel points should be retained and which ones need to be masked according to the input. Our experiments demonstrate that this approach enables better sparse representation of the original image and facilitates image reconstruction compared to random sampling. We thus use this approach for compressing massive data from the dynamic vision sensor, which greatly reduces the storage requirements for event data.
translated by 谷歌翻译