Data-driven modeling approaches such as jump tables are promising techniques to model populations of resistive random-access memory (ReRAM) or other emerging memory devices for hardware neural network simulations. As these tables rely on data interpolation, this work explores the open questions about their fidelity in relation to the stochastic device behavior they model. We study how various jump table device models impact the attained network performance estimates, a concept we define as modeling bias. Two methods of jump table device modeling, binning and Optuna-optimized binning, are explored using synthetic data with known distributions for benchmarking purposes, as well as experimental data obtained from TiOx ReRAM devices. Results on a multi-layer perceptron trained on MNIST show that device models based on binning can behave unpredictably particularly at low number of points in the device dataset, sometimes over-promising, sometimes under-promising target network accuracy. This paper also proposes device level metrics that indicate similar trends with the modeling bias metric at the network level. The proposed approach opens the possibility for future investigations into statistical device models with better performance, as well as experimentally verified modeling bias in different in-memory computing and neural network architectures.

神经网络的越来越大的规模及其越来越多的应用空间对更高的能量和记忆有效的人工智能特定硬件产生了需求。 venues为了缓解主要问题，von neumann瓶颈，包括内存和近记忆架构，以及算法方法。在这里，我们利用磁隧道结（MTJ）的低功耗和固有的二进制操作来展示基于MTJ的无源阵列的神经网络硬件推断。通常，由于设备到装置的变化，写入误差，寄生电阻和非前沿，在性能下将训练的网络模型转移到推动的硬件。为了量化这些硬件现实的效果，我们将300个唯一重量矩阵解决方案的23个唯一的重量矩阵解决方案进行分类，以分类葡萄酒数据集，用于分类准确性和写真保真度。尽管设备不完美，我们可以实现高达95.3％的软件等效精度，并在15 x 15 MTJ阵列中正确调整具有一系列设备尺寸的阵列。此调谐过程的成功表明，需要新的指标来表征混合信号硬件中再现的网络的性能和质量。

我们证明，与畴壁（DW）位置的大量随机变化的量化量（名义上是5态）突触的极低分辨率可以是节能的，并且与使用浮动精度相比，与类似尺寸的深度神经网络（DNN）相比具有相当高的测试精度。突触权重。具体地，电压控制的DW器件展示随机性的随机行为，与微磁性模拟严格，并且只能编码有限状态;但是，它们在训练和推论中都可以非常节能。我们表明，通过对学习算法实施合适的修改，我们可以解决随机行为以及减轻其低分辨率的影响，以实现高测试精度。在这项研究中，我们提出了原位和前地训练算法，基于Hubara等人提出的算法的修改。 [1]适用于突触权重的量化。我们使用2个，3和5状态DW设备作为Synapse培训Mnist DataSet上的几个5层DNN。对于原位训练，采用单独的高精度存储器单元来保护和累积重量梯度，然后被量化以编程低精密DW设备。此外，在训练期间使用尺寸的噪声公差余量来解决内部编程噪声。对于前训训练，首先基于所表征的DW设备模型和噪声公差余量进行前体DNN，其类似于原位培训。值得注意的是，对于原位推断，对设备的能量耗散装置仅是每次推断仅13页，因为在整个MNIST数据集上进行10个时期进行训练。

在神经形态计算中，人工突触提供了一种基于来自神经元的输入来设置的多重导电状态，类似于大脑。可能需要超出多重权重的突触的附加属性，并且可以取决于应用程序，需要需要从相同材料生成不同的突触行为。这里，我们基于使用磁隧道结和磁畴壁的磁性材料测量人造突触。通过在单个磁隧道结下面的畴壁轨道中制造光刻槽口，我们实现了4-5个稳定的电阻状态，可以使用自旋轨道扭矩电气可重复控制。我们分析几何形状对突触行为的影响，表明梯形装置具有高可控性的不对称性重量，而直线装置具有较高的随机性，但具有稳定的电阻水平。设备数据被输入到神经形态计算模拟器中以显示特定于应用程序突触函数的有用性。实施应用于流式的时尚 - MNIST数据的人工神经网络，我们表明梯形磁突出可以用作高效在线学习的元塑功能。为CiFar-100图像识别实施卷积神经网络，我们表明直流突触由于其电阻水平的稳定性而达到近乎理想的推理精度。这项工作显示多重磁突触是神经形态计算的可行技术，并为新兴人工突触技术提供设计指南。

Organic neuromorphic device networks can accelerate neural network algorithms and directly integrate with microfluidic systems or living tissues. Proposed devices based on the bio-compatible conductive polymer PEDOT:PSS have shown high switching speeds and low energy demand. However, as electrochemical systems, they are prone to self-discharge through parasitic electrochemical reactions. Therefore, the network's synapses forget their trained conductance states over time. This work integrates single-device high-resolution charge transport models to simulate neuromorphic device networks and analyze the impact of self-discharge on network performance. Simulation of a single-layer nine-pixel image classification network reveals no significant impact of self-discharge on training efficiency. And, even though the network's weights drift significantly during self-discharge, its predictions remain 100\% accurate for over ten hours. On the other hand, a multi-layer network for the approximation of the circle function is shown to degrade significantly over twenty minutes with a final mean-squared-error loss of 0.4. We propose to counter the effect by periodically reminding the network based on a map between a synapse's current state, the time since the last reminder, and the weight drift. We show that this method with a map obtained through validated simulations can reduce the effective loss to below 0.1 even with worst-case assumptions. Finally, while the training of this network is affected by self-discharge, a good classification is still obtained. Electrochemical organic neuromorphic devices have not been integrated into larger device networks. This work predicts their behavior under nonideal conditions, mitigates the worst-case effects of parasitic self-discharge, and opens the path toward implementing fast and efficient neural networks on organic neuromorphic hardware.

Brain-inspired computing proposes a set of algorithmic principles that hold promise for advancing artificial intelligence. They endow systems with self learning capabilities, efficient energy usage, and high storage capacity. A core concept that lies at the heart of brain computation is sequence learning and prediction. This form of computation is essential for almost all our daily tasks such as movement generation, perception, and language. Understanding how the brain performs such a computation is not only important to advance neuroscience but also to pave the way to new technological brain-inspired applications. A previously developed spiking neural network implementation of sequence prediction and recall learns complex, high-order sequences in an unsupervised manner by local, biologically inspired plasticity rules. An emerging type of hardware that holds promise for efficiently running this type of algorithm is neuromorphic hardware. It emulates the way the brain processes information and maps neurons and synapses directly into a physical substrate. Memristive devices have been identified as potential synaptic elements in neuromorphic hardware. In particular, redox-induced resistive random access memories (ReRAM) devices stand out at many aspects. They permit scalability, are energy efficient and fast, and can implement biological plasticity rules. In this work, we study the feasibility of using ReRAM devices as a replacement of the biological synapses in the sequence learning model. We implement and simulate the model including the ReRAM plasticity using the neural simulator NEST. We investigate the effect of different device properties on the performance characteristics of the sequence learning model, and demonstrate resilience with respect to different on-off ratios, conductance resolutions, device variability, and synaptic failure.

在2015年和2019年之间，地平线的成员2020年资助的创新培训网络名为“Amva4newphysics”，研究了高能量物理问题的先进多变量分析方法和统计学习工具的定制和应用，并开发了完全新的。其中许多方法已成功地用于提高Cern大型Hadron撞机的地图集和CMS实验所执行的数据分析的敏感性;其他几个人，仍然在测试阶段，承诺进一步提高基本物理参数测量的精确度以及新现象的搜索范围。在本文中，在研究和开发的那些中，最相关的新工具以及对其性能的评估。

Recent years have witnessed a growth in mathematics for deep learning--which seeks a deeper understanding of the concepts of deep learning with mathematics, and explores how to make it more robust--and deep learning for mathematics, where deep learning algorithms are used to solve problems in mathematics. The latter has popularised the field of scientific machine learning where deep learning is applied to problems in scientific computing. Specifically, more and more neural network architectures have been developed to solve specific classes of partial differential equations (PDEs). Such methods exploit properties that are inherent to PDEs and thus solve the PDEs better than classical feed-forward neural networks, recurrent neural networks, and convolutional neural networks. This has had a great impact in the area of mathematical modeling where parametric PDEs are widely used to model most natural and physical processes arising in science and engineering, In this work, we review such methods and extend them for parametric studies as well as for solving the related inverse problems. We equally proceed to show their relevance in some industrial applications.

我们训练神经形态硬件芯片以通过变分能最小化近似Quantum旋转模型的地面状态。与使用马尔可夫链蒙特卡罗进行样品生成的变分人工神经网络相比，这种方法具有优点：神经形态器件以快速和固有的并行方式产生样品。我们开发培训算法，并将其应用于横向场介绍模型，在中等系统尺寸下显示出良好的性能（$ n \ LEQ 10 $）。系统的普遍开心研究表明，较大系统尺寸的可扩展性主要取决于样品质量，该样品质量受到模拟神经芯片上的参数漂移的限制。学习性能显示阈值行为作为ansatz的变分参数的数量的函数，大约为50美元的隐藏神经元，足以表示关键地位，最高$ n = 10 $。网络参数的6 + 1位分辨率不会限制当前设置中的可达近似质量。我们的工作为利用神经形态硬件的能力提供了一种重要的一步，以解决量子数量问题中的维数诅咒。

Deep neural networks (DNNs) are currently widely used for many artificial intelligence (AI) applications including computer vision, speech recognition, and robotics. While DNNs deliver state-of-the-art accuracy on many AI tasks, it comes at the cost of high computational complexity. Accordingly, techniques that enable efficient processing of DNNs to improve energy efficiency and throughput without sacrificing application accuracy or increasing hardware cost are critical to the wide deployment of DNNs in AI systems.This article aims to provide a comprehensive tutorial and survey about the recent advances towards the goal of enabling efficient processing of DNNs. Specifically, it will provide an overview of DNNs, discuss various hardware platforms and architectures that support DNNs, and highlight key trends in reducing the computation cost of DNNs either solely via hardware design changes or via joint hardware design and DNN algorithm changes. It will also summarize various development resources that enable researchers and practitioners to quickly get started in this field, and highlight important benchmarking metrics and design considerations that should be used for evaluating the rapidly growing number of DNN hardware designs, optionally including algorithmic co-designs, being proposed in academia and industry.The reader will take away the following concepts from this article: understand the key design considerations for DNNs; be able to evaluate different DNN hardware implementations with benchmarks and comparison metrics; understand the trade-offs between various hardware architectures and platforms; be able to evaluate the utility of various DNN design techniques for efficient processing; and understand recent implementation trends and opportunities.

突触记忆巩固已被认为是支持神经形态人工智能（AI）系统中持续学习的关键机制之一。在这里，我们报告说，Fowler-Nordheim（FN）量子隧道设备可以实现突触存储器巩固，类似于通过算法合并模型（例如级联和弹性重量合并（EWC）模型）所能实现的。拟议的FN-Synapse不仅存储突触重量，而且还存储了Synapse在设备本身上的历史用法统计量。我们还表明，就突触寿命而言，FN合并的操作几乎是最佳的，并且我们证明了一个包含FN合成的网络在一个小基准测试持续学习任务上超过了可比的EWC网络。通过每次突触更新的Femtojoules的能量足迹，我们相信所提出的FN-Synapse为实施突触记忆巩固和持续学习提供了一种超能效率的方法。

The term ``neuromorphic'' refers to systems that are closely resembling the architecture and/or the dynamics of biological neural networks. Typical examples are novel computer chips designed to mimic the architecture of a biological brain, or sensors that get inspiration from, e.g., the visual or olfactory systems in insects and mammals to acquire information about the environment. This approach is not without ambition as it promises to enable engineered devices able to reproduce the level of performance observed in biological organisms -- the main immediate advantage being the efficient use of scarce resources, which translates into low power requirements. The emphasis on low power and energy efficiency of neuromorphic devices is a perfect match for space applications. Spacecraft -- especially miniaturized ones -- have strict energy constraints as they need to operate in an environment which is scarce with resources and extremely hostile. In this work we present an overview of early attempts made to study a neuromorphic approach in a space context at the European Space Agency's (ESA) Advanced Concepts Team (ACT).

IOT应用中的总是关于Tinyml的感知任务需要非常高的能量效率。模拟计算内存（CIM）使用非易失性存储器（NVM）承诺高效率，并提供自包含的片上模型存储。然而，模拟CIM推出了新的实际考虑因素，包括电导漂移，读/写噪声，固定的模数转换器增益等。必须解决这些附加约束，以实现可以通过可接受的模拟CIM部署的模型精度损失。这项工作描述了$ \ textit {analognets} $：tinyml模型用于关键字点（kws）和视觉唤醒词（VWW）的流行始终是on。模型架构专门为模拟CIM设计，我们详细介绍了一种全面的培训方法，以在推理时间内保持面对模拟非理想的精度和低精度数据转换器。我们还描述了AON-CIM，可编程，最小面积的相变存储器（PCM）模拟CIM加速器，具有新颖的层串行方法，以消除与完全流水线设计相关的复杂互连的成本。我们在校准的模拟器以及真正的硬件中评估了对校准模拟器的矛盾，并发现精度下降限制为KWS / VWW的PCM漂移（8位）24小时后的0.8 $ \％$ / 1.2 $ \％$。在14nm AON-CIM加速器上运行的analognets使用8位激活，分别使用8位激活，并增加到57.39 / 25.69个顶部/ w，以4美元$ 4 $ 57.39 / 25.69。

在本文中，提出了一种新的方法，该方法允许基于神经网络（NN）均衡器的低复杂性发展，以缓解高速相干光学传输系统中的损伤。在这项工作中，我们提供了已应用于馈电和经常性NN设计的各种深层模型压缩方法的全面描述和比较。此外，我们评估了这些策略对每个NN均衡器的性能的影响。考虑量化，重量聚类，修剪和其他用于模型压缩的尖端策略。在这项工作中，我们提出并评估贝叶斯优化辅助压缩，其中选择了压缩的超参数以同时降低复杂性并提高性能。总之，通过使用模拟和实验数据来评估每种压缩方法的复杂性及其性能之间的权衡，以完成分析。通过利用最佳压缩方法，我们表明可以设计基于NN的均衡器，该均衡器比传统的数字背部传播（DBP）均衡器具有更好的性能，并且只有一个步骤。这是通过减少使用加权聚类和修剪算法后在NN均衡器中使用的乘数数量来完成的。此外，我们证明了基于NN的均衡器也可以实现卓越的性能，同时仍然保持与完整的电子色色散补偿块相同的复杂性。我们通过强调开放问题和现有挑战以及未来的研究方向来结束分析。

近年来，人工智能（AI）的领域已经见证了巨大的增长，然而，持续发展的一些最紧迫的挑战是电子计算机架构所面临的基本带宽，能效和速度限制。利用用于执行神经网络推理操作的光子处理器越来越感兴趣，但是这些网络目前使用标准数字电子培训。这里，我们提出了由CMOS兼容的硅光子架构实现的神经网络的片上训练，以利用大规模平行，高效和快速数据操作的电位。我们的方案采用直接反馈对准训练算法，它使用错误反馈而不是错误反向化而培训神经网络，并且可以在每秒乘以数万亿乘以量的速度运行，同时每次MAC操作消耗小于一个微微约会。光子架构利用并行化矩阵 - 向量乘法利用微址谐振器阵列，用于沿着单个波导总线处理多通道模拟信号，以便原位计算每个神经网络层的梯度向量，这是在后向通过期间执行的最昂贵的操作。 。我们还通过片上MAC操作结果实验地示意使用MNIST数据集进行培训深度神经网络。我们的高效，超快速神经网络训练的新方法展示了光子学作为执行AI应用的有希望的平台。

为了寻求低功率，以生物启发的计算均基于回忆性和基于成年的人工神经网络（ANN）一直是对硬件实施神经形态计算的焦点的主题。进一步的一步，要求使用绝热计算的再生电容性神经网络，为降低能源消耗提供了诱人的途径，尤其是与“ Memimpedace”元素结合使用时。在这里，我们提出了一种人工神经元，具有绝热的突触电容器，以产生神经元的膜电位。后者通过动态闩锁比较器实现，并使用电阻随机访问存储器（RRAM）设备增强。我们最初的4位绝热电容性神经元概念验证示例显示了90％的突触能量节省。在4个突触/SOMA时，我们已经看到总体减少35％的能量。此外，工艺和温度对4位绝热突触的影响显示，在整个角落100度摄氏时，最大能量变化为30％，而没有任何功能损失。最后，我们对ANN的绝热方法的功效进行了512和1024突触/神经元的测试，最差和最佳的情况突触载荷条件以及可变的均衡电容的可变量化均等能力量化了均衡电容和最佳功率 - 电信频率范围之间的预期权衡。加载（即活动突触的百分比）。

FIG. 1. Schematic diagram of a Variational Quantum Algorithm (VQA). The inputs to a VQA are: a cost function C(θ), with θ a set of parameters that encodes the solution to the problem, an ansatz whose parameters are trained to minimize the cost, and (possibly) a set of training data {ρ k } used during the optimization. Here, the cost can often be expressed in the form in Eq. ( 3), for some set of functions {f k }. Also, the ansatz is shown as a parameterized quantum circuit (on the left), which is analogous to a neural network (also shown schematically on the right). At each iteration of the loop one uses a quantum computer to efficiently estimate the cost (or its gradients). This information is fed into a classical computer that leverages the power of optimizers to navigate the cost landscape C(θ) and solve the optimization problem in Eq. ( 1). Once a termination condition is met, the VQA outputs an estimate of the solution to the problem. The form of the output depends on the precise task at hand. The red box indicates some of the most common types of outputs.

我们提出了Memprop，即采用基于梯度的学习来培训完全的申请尖峰神经网络（MSNNS）。我们的方法利用固有的设备动力学来触发自然产生的电压尖峰。这些由回忆动力学发出的尖峰本质上是类似物，因此完全可区分，这消除了尖峰神经网络（SNN）文献中普遍存在的替代梯度方法的需求。回忆性神经网络通常将备忘录集成为映射离线培训网络的突触，或者以其他方式依靠关联学习机制来训练候选神经元的网络。相反，我们直接在循环神经元和突触的模拟香料模型上应用了通过时间（BPTT）训练算法的反向传播。我们的实现是完全的综合性，因为突触重量和尖峰神经元都集成在电阻RAM（RRAM）阵列上，而无需其他电路来实现尖峰动态，例如模数转换器（ADCS）或阈值比较器。结果，高阶电物理效应被充分利用，以在运行时使用磁性神经元的状态驱动动力学。通过朝着非同一梯度的学习迈进，我们在以前报道的几个基准上的轻巧密集的完全MSNN中获得了高度竞争的准确性。

This chapter sheds light on the synaptic organization of the brain from the perspective of computational neuroscience. It provides an introductory overview on how to account for empirical data in mathematical models, implement them in software, and perform simulations reflecting experiments. This path is demonstrated with respect to four key aspects of synaptic signaling: the connectivity of brain networks, synaptic transmission, synaptic plasticity, and the heterogeneity across synapses. Each step and aspect of the modeling and simulation workflow comes with its own challenges and pitfalls, which are highlighted and addressed in detail.

这本数字本书包含在物理模拟的背景下与深度学习相关的一切实际和全面的一切。尽可能多，所有主题都带有Jupyter笔记本的形式的动手代码示例，以便快速入门。除了标准的受监督学习的数据中，我们将看看物理丢失约束，更紧密耦合的学习算法，具有可微分的模拟，以及加强学习和不确定性建模。我们生活在令人兴奋的时期：这些方法具有从根本上改变计算机模拟可以实现的巨大潜力。