Using optical hardware for neuromorphic computing has become more and more popular recently due to its efficient high-speed data processing capabilities and low power consumption. However, there are still some remaining obstacles to realizing the vision of a completely optical neuromorphic computer. One of them is that, depending on the technology used, optical weighting elements may not share the same resolution as in the electrical domain. Moreover, noise and drift are important considerations as well. In this article, we investigate a new method for improving the performance of optical weighting, even in the presence of noise and in the case of very low resolution. Even with only 8 to 32 levels of resolution, the method can outperform the naive traditional low-resolution weighting by several orders of magnitude in terms of bit error rate and can deliver performance very close to full-resolution weighting elements, also in noisy environments.
Jacobs University Bremen（不来梅雅各布大学）；University Medical Center Hamburg-Eppendorf（汉堡-埃彭多夫大学医学中心）
This chapter provides a comprehensive survey of the researches and motivations for hardware implementation of reservoir computing (RC) on neuromorphic electronic systems. Due to its computational efficiency and the fact that training amounts to a simple linear regression, both spiking and non-spiking implementations of reservoir computing on neuromorphic hardware have been developed. Here, a review of these experimental studies is provided to illustrate the progress in this area and to address the technical challenges which arise from this specific hardware implementation. Moreover, to deal wi…
Université Libre de Bruxelles（布鲁塞尔自由大学）；Ghent University（根特大学）
Reservoir computing is a new, powerful and flexible machine learning technique that is easily implemented in hardware. Recently, by using a time-multiplexed architecture, hardware reservoir computers have reached performance comparable to digital implementations. Operating speeds allowing for real time information operation have been reached using optoelectronic systems. At present the main performance bottleneck is the readout layer which uses slow, digital postprocessing. We have designed an analog readout suitable for time-multiplexed optoelectronic reservoir computers, capable of working i…
As Moore's law comes to an end, neuromorphic approaches to computing are on the rise. One of these, passive photonic reservoir computing, is a strong candidate for computing at high bitrates (> 10 Gbps) and with low energy consumption. Currently though, both benefits are limited by the necessity to perform training and readout operations in the electrical domain. Thus, efforts are currently underway in the photonic community to design an integrated optical readout, which allows to perform all operations in the optical domain. In addition to the technological challenge of designing such a reado…
University of Sheffield（谢菲尔德大学）；University of York（约克大学）
Neural networks have revolutionized the area of artificial intelligence and introduced transformative applications to almost every scientific field and industry. However, this success comes at a great price; the energy requirements for training advanced models are unsustainable. One promising way to address this pressing issue is by developing low-energy neuromorphic hardware that directly supports the algorithm's requirements. The intrinsic non-volatility, non-linearity, and memory of spintronic devices make them appealing candidates for neuromorphic devices. Here we focus on the reservoir co…
Recurrent neural network (RNN) based reinforcement learning (RL) is used for learning context-dependent tasks and has also attracted attention as a method with remarkable learning performance in recent research. However, RNN-based RL has some issues that the learning procedures tend to be more computationally expensive, and training with backpropagation through time (BPTT) is unstable because of vanishing/exploding gradients problem. An approach with replay memory introducing reservoir computing has been proposed, which trains an agent without BPTT and avoids these issues. The basic idea of th…
University of Vienna（维也纳大学）；Ludwig-Maximilians-Universität München（路德维希-马克西米利安慕尼黑大学）；Universität Konstanz（康斯坦茨大学）；Universität Sankt Gallen（圣加仑大学）；Centre National de la Recherche Scientifique (CNRS)（法国国家科学研究中心）；ETH Zürich（苏黎世联邦理工学院）
A new explanation of geometric nature of the reservoir computing phenomenon is presented. Reservoir computing is understood in the literature as the possibility of approximating input/output systems with randomly chosen recurrent neural systems and a trained linear readout layer. Light is shed on this phenomenon by constructing what is called strongly universal reservoir systems as random projections of a family of state-space systems that generate Volterra series expansions. This procedure yields a state-affine reservoir system with randomly generated coefficients in a dimension that is logar…
Università Degli Studi Di Pavia（帕维亚大学）；STMicroelectronics（意法半导体）
Echo State Networks (ESN) are a class of Recurrent Neural Networks (RNN) that has gained substantial popularity due to their effectiveness, ease of use and potential for compact hardware implementation. An ESN contains the three network layers input, reservoir and readout where the reservoir is the truly recurrent network. The input and reservoir layers of an ESN are initialized at random and never trained afterwards and the training of the ESN is applied to the readout layer only. The alternative of Recursive Neural Gas (RNG) is one of the many proposals of fully-trainable reservoirs that can…
The mushroom body is the key network for the representation of learned olfactory stimuli in Drosophila and insects. The sparse activity of Kenyon cells, the principal neurons in the mushroom body, plays a key role in the learned classification of different odours. In the specific case of the fruit fly, the sparseness of the network is enforced by an inhibitory feedback neuron called APL, and by an intrinsic high firing threshold of the Kenyon cells. In this work we took inspiration from the fruit fly brain to formulate a novel machine learning algorithm that is able to optimize the sparsity le…
We analyze the memory capacity of a delay based reservoir computer with a Hopf normal form as nonlinearity and numerically compute the linear as well as the higher order recall capabilities. A possible physical realisation could be a laser with external cavity, for which the information is fed via electrical injection. A task independent quantification of the computational capability of the reservoir system is done via a complete orthonormal set of basis functions. Our results suggest that even for constant readout dimension the total memory capacity is dependent on the ratio between the infor…
University Medical Center Hamburg-Eppendorf (UKE)（汉堡-埃彭多夫大学医学中心（UKE））；Jacobs University gGmbH（雅各布大学gGmbH）
The reservoir computing paradigm is employed to classify heartbeat anomalies online based on electrocardiogram signals. Inspired by the principles of information processing in the brain, reservoir computing provides a framework to design, train, and analyze recurrent neural networks (RNNs) for processing time-dependent information. Due to its computational efficiency and the fact that training amounts to a simple linear regression, this supervised learning algorithm has been variously considered as a strategy to implement useful computations not only on digital computers but also on emerging u…
Reservoir Computing (RC) refers to a Recurrent Neural Networks (RNNs) framework, frequently used for sequence learning and time series prediction. The RC system consists of a random fixed-weight RNN (the input-hidden reservoir layer) and a classifier (the hidden-output readout layer). Here we focus on the sequence learning problem, and we explore a different approach to RC. More specifically, we remove the non-linear neural activation function, and we consider an orthogonal reservoir acting on normalized states on the unit hypersphere. Surprisingly, our numerical results show that the system's…
Transforming Traditional Neural Networks into Neuromorphic Quantum-Cognitive Models: A Tutorial with Applications
Artificial Intelligence and Cyber Futures Institute, Charles Sturt University（查尔斯斯特大学人工智能与网络未来学院）；Cyber Futures Institute, Charles Sturt University（查尔斯斯特大学网络未来学院）
Quantum Reservoir Computing: Recent Advances and Future Directions
Interdisciplinary Centre for Security, Reliability and Trust (SnT), University of Luxembourg（安全、可靠性与信任跨学科中心（SnT），卢森堡大学）；School of Computing, Engineering and Digital Technologies, Teesside University（计算、工程与数字技术学院，泰赛大学）
Surface electromyogram (sEMG) signals result from muscle movement and hence they are an ideal candidate for benchmarking event-driven sensing and computing. We propose a simple yet novel approach for optimizing the spike encoding algorithm's hyper-parameters inspired by the readout layer concept in reservoir computing. Using a simple machine learning algorithm after spike encoding, we report performance higher than the state-of-the-art spiking neural networks on two open-source datasets for hand gesture recognition. The spike encoded data is processed through a spiking reservoir with a biologi…
Technische Universität Berlin（柏林工业大学）；Humboldt-Universität zu Berlin（柏林洪堡大学）；Instituto de Física Interdisciplinar y Sistemas Complejos, IFISC (CSIC-UIB)（跨学科物理与复杂系统研究所（IFISC，西班牙国家研究委员会-巴利阿里群岛大学））
The time-delay-based reservoir computing setup has seen tremendous success in both experiment and simulation. It allows for the construction of large neuromorphic computing systems with only few components. However, until now the interplay of the different timescales has not been investigated thoroughly. In this manuscript, we investigate the effects of a mismatch between the time-delay and the clock cycle for a general model. Typically, these two time scales are considered to be equal. Here we show that the case of equal or resonant time-delay and clock cycle could be actively detrimental and…
Atomic Switch Networks (ASN) comprising silver iodide (AgI) junctions, a material previously unexplored as functional memristive elements within highly-interconnected nanowire networks, were employed as a neuromorphic substrate for physical Reservoir Computing (RC). This new class of ASN-based devices has been physically characterized and utilized to classify spoken digit audio data, demonstrating the utility of substrate-based device architectures where intrinsic material properties can be exploited to perform computation in-materio. This work demonstrates high accuracy in the classification …
Reservoir computing is an emerging methodology for neuromorphic computing that is especially well-suited for hardware implementations in size, weight, and power (SWaP) constrained environments. This work proposes a novel hardware implementation of a reservoir computer using a planar nanomagnet array. A small nanomagnet reservoir is demonstrated via micromagnetic simulations to be able to identify simple waveforms with 100% accuracy. Planar nanomagnet reservoirs are a promising new solution to the growing need for dedicated neuromorphic hardware.
In this paper, we describe a new neuro-inspired, hardware-friendly readout stage for the liquid state machine (LSM), a popular model for reservoir computing. Compared to the parallel perceptron architecture trained by the p-delta algorithm, which is the state of the art in terms of performance of readout stages, our readout architecture and learning algorithm can attain better performance with significantly less synaptic resources making it attractive for VLSI implementation. Inspired by the nonlinear properties of dendrites in biological neurons, our readout stage incorporates neurons having …
INFN（意大利核物理国家研究所）；Universal Scientific Education and Research Network（环球科学教育与研究网络）；Universidad de Oviedo（奥维耶多大学）；ICTEA（高等科学技术研究中心）；University of Kaiserslautern-Landau (RPTU)（凯撒斯劳滕-兰道大学（RPTU））；National Institute of Science Education and Research（国家科学教育与研究学院）；Karlsruhe Institute of Technology（卡尔斯鲁厄理工学院）；Lund University（隆德大学）；Laboratoire de Physique Clermont Auvergne（克莱蒙奥弗涅物理实验室）
Autonomous Physical Computation: A Categorical Closure Criterion for Physical and Neuromorphic Reservoirs
McGovern Institute for Brain Research, MIT（麻省理工学院麦戈文脑研究所）；NSF AI Institute for Artificial Intelligence and Fundamental Interactions, MIT（麻省理工学院美国国家科学基金会人工智能基础相互作用研究所）
The universal approximation properties with respect to $L ^p $-type criteria of three important families of reservoir computers with stochastic discrete-time semi-infinite inputs is shown. First, it is proved that linear reservoir systems with either polynomial or neural network readout maps are universal. More importantly, it is proved that the same property holds for two families with linear readouts, namely, trigonometric state-affine systems and echo state networks, which are the most widely used reservoir systems in applications. The linearity in the readouts is a key feature in supervise…
Nonlinear waves have played a historical role in laying the foundations of the science of complexity. Recently, they have also allowed the development of a new reservoir computing paradigm: neuromorphic computing by waves. In these systems, the information transmission acts as the excitation of wave dynamics, whose evolution processes the information to perform complex tasks at low energy consumption. To enable nonlinear hydrodynamic waves to do computing, we designed the Aqua-Photonic-Advantaged Computing Machine by Artificial Neural Networks (Aqua-PACMANN), a system where wave propagation in…
We propose a novel molecular computing approach based on reservoir computing. In reservoir computing, a dynamical core, called a reservoir, is perturbed with an external input signal while a readout layer maps the reservoir dynamics to a target output. Computation takes place as a transformation from the input space to a high-dimensional spatiotemporal feature space created by the transient dynamics of the reservoir. The readout layer then combines these features to produce the target output. We show that coupled deoxyribozyme oscillators can act as the reservoir. We show that despite using on…
Reservoir computing is a computational framework suited for temporal/sequential data processing. It is derived from several recurrent neural network models, including echo state networks and liquid state machines. A reservoir computing system consists of a reservoir for mapping inputs into a high-dimensional space and a readout for pattern analysis from the high-dimensional states in the reservoir. The reservoir is fixed and only the readout is trained with a simple method such as linear regression and classification. Thus, the major advantage of reservoir computing compared to other recurrent…
Fabricating powerful neuromorphic chips the size of a thumb requires miniaturizing their basic units: synapses and neurons. The challenge for neurons is to scale them down to submicrometer diameters while maintaining the properties that allow for reliable information processing: high signal to noise ratio, endurance, stability, reproducibility. In this work, we show that compact spin-torque nano-oscillators can naturally implement such neurons, and quantify their ability to realize an actual cognitive task. In particular, we show that they can naturally implement reservoir computing with high …
In this paper we propose and numerically study a neuromorphic computing scheme that applies delay-based reservoir computing in a laser system consisting of two mutually coupled phase modulated lasers. The scheme can be monolithic integrated in a straightforward manner and alleviates the need for external optical injection, as the data can be directly applied on the on-chip phase modulator placed between the two lasers. The scheme also offers the benefit of increasing the nodes compared to a reservoir computing system using either one laser under feedback or laser under feedback and optical inj…
Unconventional computing explores multi-scale platforms connecting molecular-scale devices into networks for the development of scalable neuromorphic architectures, often based on new materials and components with new functionalities. We review some work investigating the functionalities of locally connected networks of different types of switching elements as computational substrates. In particular, we discuss reservoir computing with networks of nonlinear nanoscale components. In usual neuromorphic paradigms, the network synaptic weights are adjusted as a result of a training/learning proces…
Multivariate Time Series Forecasting with Gate-Based Quantum Reservoir Computing on NISQ Hardware
Polytechnique Montréal（波士顿理工学院）；Institut quantique, Université de Sherbrooke（量子研究所， Sherbrooke 大学）；Thales Digital Solutions（泰雷兹数字解决方案）；Université de Sherbrooke（Sherbrooke 大学）
As the compute demands for machine learning and artificial intelligence applications continue to grow, neuromorphic hardware has been touted as a potential solution. New emerging devices like memristors, atomic switches, etc have shown tremendous potential to replace CMOS-based circuits but have been hindered by multiple challenges with respect to device variability, stochastic behavior and scalability. In this paper we will introduce a Description<->Design framework to analyze past successes in computing, understand current problems and identify solutions moving forward. Engineering systems w…
Machine learning software applications are nowadays ubiquitous in many fields of science and society for their outstanding capability of solving computationally vast problems like the recognition of patterns and regularities in big datasets. One of the main goals of research is the realization of a physical neural network able to perform data processing in a much faster and energy-efficient way than the state-of-the-art technology. Here we show that lattices of exciton-polariton condensates accomplish neuromorphic computing using fast optical nonlinearities and with lower error rate than any p…
Networks of nanowires are currently being explored for a range of applications in brain-like (or neuromorphic) computing, and especially in reservoir computing (RC). Fabrication of real-world computing devices requires that the nanowires are deposited sequentially, leading to stacking of the wires on top of each other. However, most simulations of computational tasks using these systems treat the nanowires as 1D objects lying in a perfectly 2D plane - the effect of stacking on RC performance has not yet been established. Here we use detailed simulations to compare the performance of perfectly …
Dynamical Diversity for Reservoir Computing in Reconfigurable Nanomechanics
International Iberian Nanotechnology Laboratory (INL)（国际伊比利亚纳米技术实验室）；Bilkent University（比尔肯特大学）；UNAM - Institute of Materials Science and Nanotechnology, Bilkent University（比尔肯特大学 UNAM 材料科学与纳米技术研究所）；Sabanci University（萨班奇大学）；Koc University（科奇大学）
