Training Passive Photonic Reservoirs with Integrated Optical Readout
Ghent University（根特大学）；imec（比利时微电子研究中心）
Matthias Freiberger, Andrew Katumba, Peter Bienstman, Joni Dambre
备注：
Accepted for publication in IEEE Transactions on Neural Networks and Learning Systems (TNNLS-2017-P-8539.R1), copyright 2018 IEEE. This research was funded by the EU Horizon 2020 PHRESCO Grant (Grant No. 688579) and the BELSPO IAP P7-35 program Photonics@be. 11 pages, 9 figures
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 readout, new algorithms have to be designed in order to train it. Foremost, suitable algorithms need to be able to deal with the fact that the actual on-chip reservoir states are not directly observable. In this work, we investigate several options for such a training algorithm and propose a solution in which the complex states of the reservoir can be observed by appropriately setting the readout weights, while iterating over a predefined input sequence. We perform numerical simulations in order to compare our method with an ideal baseline requiring full observability as well as with an established black-box optimization approach (CMA-ES).
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…
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 weig…
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…
Insect-Wing Structured Microfluidic System for Reservoir Computing
School of Computing, University of Nebraska-Lincoln（计算机学院，内布拉斯加大学林肯分校）；Department of Mechanical and Materials Engineering, University of Nebraska-Lincoln（机械与材料工程学院，内布拉斯加大学林肯分校）
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…
Harnessing Synthetic Active Particles for Physical Reservoir Computing
Peter Debye Institute for Soft Matter Physics, Leipzig University（莱比锡大学彼得·德拜软物质物理研究所）；Center for Scalable Data Analytics and Artificial Intelligence (ScaDS.AI) Dresden/Leipzig（德累斯顿/莱比锡可扩展数据分析与人工智能中心（ScaDS.AI））
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…
University of Maryland（马里兰大学）；Department of Computer Science（计算机科学系）；Department of Physics（物理系）；Institute for Adv. Computer Studies（高级计算机研究所）
In many real-world applications, fully-differentiable RNNs such as LSTMs and GRUs have been widely deployed to solve time series learning tasks. These networks train via Backpropagation Through Time, which can work well in practice but involves a biologically unrealistic unrolling of the network in time for gradient updates, are computationally expensive, and can be hard to tune. A second paradigm, Reservoir Computing, keeps the recurrent weight matrix fixed and random. Here, we propose a novel hybrid network, which we call Hybrid Backpropagation Parallel Echo State Network (HBP-ESN) which com…
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）
Wyant College of Optical Sciences, University of Arizona（亚利桑那大学怀恩特光学科学学院）；School of Electrical Engineering and Telecommunications, University of New South Wales（新南威尔士大学电气工程与电信学院）
A new class of non-homogeneous state-affine systems is introduced for use in reservoir computing. Sufficient conditions are identified that guarantee first, that the associated reservoir computers with linear readouts are causal, time-invariant, and satisfy the fading memory property and second, that a subset of this class is universal in the category of fading memory filters with stochastic almost surely uniformly bounded inputs. This means that any discrete-time filter that satisfies the fading memory property with random inputs of that type can be uniformly approximated by elements in the n…
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…
Data-Specific Hyper-Parameter Design: A Paradigm Shift in Reservoir Computing
University of Pretoria. Department of Mathematics and Applied Mathematics（南非大学 Pretoria分校 数学与应用数学系）；Nanyang Technological University. Division of Mathematical Sciences. School of Physical and Mathematical Sciences（南洋理工大学 数学科学学院 物理与数学科学学院）
Photonic reservoir computing with dimensionally compressed readout
Université de Lorraine, CentraleSupélec（洛林大学、中央苏佩莱克）；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）
Introduction. Reservoir Computing is a bio-inspired computing paradigm for processing time-dependent signals. The performance of its hardware implementation is comparable to state-of-the-art digital algorithms on a series of benchmark tasks. The major bottleneck of these implementation is the readout layer, based on slow offline post-processing. Few analogue solutions have been proposed, but all suffered from notice able decrease in performance due to added complexity of the setup. Methods. Here we propose the use of online training to solve these issues. We study the applicability of this met…
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…
We propose a deep architecture for the classification of multivariate time series. By means of a recurrent and untrained reservoir we generate a vectorial representation that embeds temporal relationships in the data. To improve the memorization capability, we implement a bidirectional reservoir, whose last state captures also past dependencies in the input. We apply dimensionality reduction to the final reservoir states to obtain compressed fixed size representations of the time series. These are subsequently fed into a deep feedforward network trained to perform the final classification. We …
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）
Neuro-Inspired Visual Pattern Recognition via Biological Reservoir Computing
Institute of Information Science and Technologies of the National Research Council of Italy (ISTI-CNR)（意大利国家研究理事会信息科学与技术研究所）；Institute of Biophysics of the National Research Council of Italy (IBF-CNR)（意大利国家研究理事会生物物理研究所）
Reservoir computing is a bio-inspired computing paradigm for processing time dependent signals. The performance of its analogue implementations matches other digital algorithms on a series of benchmark tasks. Their potential can be further increased by feeding the output signal back into the reservoir, which would allow to apply the algorithm to time series generation. This requires, in principle, implementing a sufficiently fast readout layer for real-time output computation. Here we achieve this with a digital output layer driven by a FPGA chip. We demonstrate the first opto-electronic reser…
