In recent years, Neural Turing Machines have gathered attention by joining the flexibility of neural networks with the computational capabilities of Turing machines. However, Neural Turing Machines are notoriously hard to train, which limits their applicability. We propose reservoir memory machines, which are still able to solve some of the benchmark tests for Neural Turing Machines, but are much faster to train, requiring only an alignment algorithm and linear regression. Our model can also be seen as an extension of echo state networks with an external memory, enabling arbitrarily long storage without interference.
Techniques for Enhancing Memory Capacity of Reservoir Computing
Graduate School of Life Science and Systems Engineering, Kyushu Institute of Technology（九州工业大学生命科学与系统工程学院）；Research Center for Neuromorphic AI Hardware, Kyushu Institute of Technology（九州工业大学神经形态人工智能硬件研究中心）；Faculty of Informatics, The University of Fukuchiyama（福知山公立大学信息学部）
The University of Sydney（悉尼大学）；Humboldt-University of Berlin（柏林洪堡大学）；Bielefeld University（比勒费尔德大学）；National Research Council of Canada（加拿大国家研究委员会）
Differentiable neural computers extend artificial neural networks with an explicit memory without interference, thus enabling the model to perform classic computation tasks such as graph traversal. However, such models are difficult to train, requiring long training times and large datasets. In this work, we achieve some of the computational capabilities of differentiable neural computers with a model that can be trained very efficiently, namely an echo state network with an explicit memory without interference. This extension enables echo state networks to recognize all regular languages, inc…
INRIA Bordeaux Sud-Ouest（法国国家信息与自动化研究所波尔多西南中心）；LaBRI, Université de Bordeaux（波尔多大学LaBRI实验室）；IMN, Université de Bordeaux（波尔多大学IMN研究所）
The prefrontal cortex is known to be involved in many high-level cognitive functions, in particular, working memory. Here, we study to what extent a group of randomly connected units (namely an Echo State Network, ESN) can store and maintain (as output) an arbitrary real value from a streamed input, i.e. can act as a sustained working memory unit. Furthermore, we explore to what extent such an architecture can take advantage of the stored value in order to produce non-linear computations. Comparison between different architectures (with and without feedback, with and without a working memory u…
Institute of Theoretical Physics, Technische Universität Berlin（柏林工业大学理论物理研究所）；Department of Mathematics, Humboldt-Universität zu Berlin（柏林洪堡大学数学系）；Institute of Mathematics, Technische Universität Berlin（柏林工业大学数学研究所）
The Deep Time-Delay Reservoir Computing concept utilizes unidirectionally connected systems with time-delays for supervised learning. We present how the dynamical properties of a deep Ikeda-based reservoir are related to its memory capacity (MC) and how that can be used for optimization. In particular, we analyze bifurcations of the corresponding autonomous system and compute conditional Lyapunov exponents, which measure the generalized synchronization between the input and the layer dynamics. We show how the MC is related to the systems distance to bifurcations or magnitude of the conditional…
School of Electrical, Computer, and Energy Engineering, Arizona State University（亚利桑那州立大学电气、计算机与能源工程学院）；Department of Electrical and Computer Engineering, Colorado State University（科罗拉多州立大学电气与计算机工程系）；DEVCOM Army Research Office（DEVCOM陆军研究办公室）；Department of Physics, Arizona State University（亚利桑那州立大学物理系）
University of New Mexico（新墨西哥大学）；Portland State University（波特兰州立大学）
Reservoir computing (RC) is a novel approach to time series prediction using recurrent neural networks. In RC, an input signal perturbs the intrinsic dynamics of a medium called a reservoir. A readout layer is then trained to reconstruct a target output from the reservoir's state. The multitude of RC architectures and evaluation metrics poses a challenge to both practitioners and theorists who study the task-solving performance and computational power of RC. In addition, in contrast to traditional computation models, the reservoir is a dynamical system in which computation and memory are insep…
Reservoir Computing (RC) is a well-known strategy for designing Recurrent Neural Networks featured by striking efficiency of training. The crucial aspect of RC is to properly instantiate the hidden recurrent layer that serves as dynamical memory to the system. In this respect, the common recipe is to create a pool of randomly and sparsely connected recurrent neurons. While the aspect of sparsity in the design of RC systems has been debated in the literature, it is nowadays understood mainly as a way to enhance the efficiency of computation, exploiting sparse matrix operations. In this paper, w…
Dipartimento di Informatica Università di Pisa（比萨大学信息学院（Dipartimento di Informatica Università di Pisa））
The paper introduces concentric Echo State Network, an approach to design reservoir topologies that tries to bridge the gap between deterministically constructed simple cycle models and deep reservoir computing approaches. We show how to modularize the reservoir into simple unidirectional and concentric cycles with pairwise bidirectional jump connections between adjacent loops. We provide a preliminary experimental assessment showing how concentric reservoirs yield to superior predictive accuracy and memory capacity with respect to single cycle reservoirs and deep reservoir models.
Faculty of Physics, University of Duisburg-Essen（物理系，杜伊斯堡-埃森大学）；DyNaMat, Department of Solid State Sciences, Ghent University（DyNaMat，固态科学系，根特大学）；Senior Principle Engineer, Intel Corp. (Retired)（高级原则工程师，英特尔公司（退休））；Faculty of Physics（物理系）；Center for Nanointegration Duisburg-Essen (CENIDE), University of Duisburg-Essen（杜伊斯堡-埃森纳米集成中心（CENIDE），杜伊斯堡-埃森大学）
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…
In this paper we give a profound insight into the computation capability of delay-based reservoir computing via an eigenvalue analysis. We concentrate on the task-independent memory capacity to quantify the reservoir performance and compare these with the eigenvalue spectrum of the dynamical system. We show that these two quantities are deeply connected, and thus the reservoir computing performance is predictable by analyzing the small signal response of the reservoir. Our results suggest that any dynamical system used as a reservoir can be analyzed in this way. We apply our method exemplarily…
The extension of deep learning towards temporal data processing is gaining an increasing research interest. In this paper we investigate the properties of state dynamics developed in successive levels of deep recurrent neural networks (RNNs) in terms of short-term memory abilities. Our results reveal interesting insights that shed light on the nature of layering as a factor of RNN design. Noticeably, higher layers in a hierarchically organized RNN architecture results to be inherently biased towards longer memory spans even prior to training of the recurrent connections. Moreover, in the conte…
The most recent year has witnessed the success of applying the Vision Transformer (ViT) for image classification. However, there are still evidences indicating that ViT often suffers following two aspects, i) the high computation and the memory burden from applying the multiple Transformer layers for pre-training on a large-scale dataset, ii) the over-fitting when training on small datasets from scratch. To address these problems, a novel method, namely, Vision Reservoir computing (ViR), is proposed here for image classification, as a parallel to ViT. By splitting each image into a sequence of…
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…
The Ohio State University（俄亥俄州立大学）；ResCon Technologies, LLC（ResCon技术有限责任公司）
Forecasting the behavior of high-dimensional dynamical systems using machine learning requires efficient methods to learn the underlying physical model. We demonstrate spatiotemporal chaos prediction using a machine learning architecture that, when combined with a next-generation reservoir computer, displays state-of-the-art performance with a computational time $10^3-10^4$ times faster for training process and training data set $\sim 10^2$ times smaller than other machine learning algorithms. We also take advantage of the translational symmetry of the model to further reduce the computational…
Robust and Efficient Quantum Reservoir Computing with Discrete Time Crystal
Center for Quantum Technology Research（量子技术研究中心）；Key Laboratory of Advanced Optoelectronic Quantum Architecture（先进光电量子架构重点实验室）；Measurements (MOE), School of Physics, Beijing Institute of Technology（测量（MOE）、物理学院、北京理工大学）；Beijing Academy of Quantum Information Sciences（量子信息科学北京院）；Institute of Physics, Chinese Academy of Sciences（中国科学院物理研究所）；University of Chinese Academy of Sciences（中国科学院大学）；Beijing Key Laboratory of Fault-Tolerant Quantum Computing（北京容错量子计算重点实验室）；Xoherence Co., Ltd.（Xoherence公司）
We introduce a novel design for in-situ training of machine learning algorithms built into smart sensors, and illustrate distributed training scenarios using radio frequency (RF) spectrum sensors. Current RF sensors at the Edge lack the computational resources to support practical, in-situ training for intelligent signal classification. We propose a solution using Deepdelay Loop Reservoir Computing (DLR), a processing architecture that supports machine learning algorithms on resource-constrained edge-devices by leveraging delayloop reservoir computing in combination with innovative hardware. D…
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…
University of Alberta（阿尔伯塔大学）；Tsinghua University（清华大学）
Episodic memory is a psychology term which refers to the ability to recall specific events from the past. We suggest one advantage of this particular type of memory is the ability to easily assign credit to a specific state when remembered information is found to be useful. Inspired by this idea, and the increasing popularity of external memory mechanisms to handle long-term dependencies in deep learning systems, we propose a novel algorithm which uses a reservoir sampling procedure to maintain an external memory consisting of a fixed number of past states. The algorithm allows a deep reinforc…
We show that many delay-based reservoir computers considered in the literature can be characterized by a universal master memory function (MMF). Once computed for two independent parameters, this function provides linear memory capacity for any delay-based single-variable reservoir with small inputs. Moreover, we propose an analytical description of the MMF that enables its efficient and fast computation. Our approach can be applied not only to reservoirs governed by known dynamical rules such as Mackey-Glass or Ikeda-like systems but also to reservoirs whose dynamical model is not available. …
W. M. Keck Science Department of Pitzer, Scripps, and Claremont McKenna College（皮泽学院、斯克里普斯学院和克莱蒙特·麦肯纳学院W.M.凯克科学系）；Nanyang Technological University（南洋理工大学）；University of California at Davis（加州大学戴维斯分校）
Recurrent neural networks are used to forecast time series in finance, climate, language, and from many other domains. Reservoir computers are a particularly easily trainable form of recurrent neural network. Recently, a "next-generation" reservoir computer was introduced in which the memory trace involves only a finite number of previous symbols. We explore the inherent limitations of finite-past memory traces in this intriguing proposal. A lower bound from Fano's inequality shows that, on highly non-Markovian processes generated by large probabilistic state machines, next-generation reservoi…
G.B Pant Institute of Technology（G.B.潘特技术学院）；Netaji Subhas Institute of Technology（内塔吉·苏巴斯技术学院）；University of Delhi（德里大学）
A reliable forecast of inflows to the reservoir is a key factor in the optimal operation of reservoirs. Real-time operation of the reservoir based on forecasts of inflows can lead to substantial economic gains. However, the forecast of inflow is an intricate task as it has to incorporate the impacts of climate and hydrological changes. Therefore, the major objective of the present work is to develop a novel approach based on long short-term memory (LSTM) for the forecast of inflows. Real-time inflow forecast, in other words, daily inflow at the reservoir helps in efficient operation of water r…
Petrozavodsk State University（彼得罗扎沃茨克国立大学）；K-SkAI LLC（K-SkAI有限责任公司）
The presented compact algorithm for recognizing handwritten digits of the MNIST database, created on the LogNNet reservoir neural network, reaches the recognition accuracy of 82%. The algorithm was tested on a low-memory Arduino board with 2 Kb static RAM low-power microcontroller. The dependences of the accuracy and time of image recognition on the number of neurons in the reservoir have been investigated. The memory allocation demonstrates that the algorithm stores all the necessary information in RAM without using additional data storage, and operates with original images without preliminar…
Avoiding over-pressurization in subsurface reservoirs is critical for applications like CO2 sequestration and wastewater injection. Managing the pressures by controlling injection/extraction are challenging because of complex heterogeneity in the subsurface. The heterogeneity typically requires high-fidelity physics-based models to make predictions on CO$_2$ fate. Furthermore, characterizing the heterogeneity accurately is fraught with parametric uncertainty. Accounting for both, heterogeneity and uncertainty, makes this a computationally-intensive problem challenging for current reservoir sim…
University Sapienza（萨皮恩扎大学）；National Research Council (ISC-CNR)（国家研究委员会（复杂系统研究所））；University of Twente（特文特大学）；Heriot-Watt University（赫瑞-瓦特大学）
Novel machine learning computational tools open new perspectives for quantum information systems. Here we adopt the open-source programming library TensorFlow to design multi-level quantum gates including a computing reservoir represented by a random unitary matrix. In optics, the reservoir is a disordered medium or a multi-modal fiber. We show that trainable operators at the input and the readout enable one to realize multi-level gates. We study various qudit gates, including the scaling properties of the algorithms with the size of the reservoir. Despite an initial low slop learning stage, T…
The aim of this work was to predict the probability of the spread of rock formations with hydrocarbon-collecting properties in the studied coastal area using a stack of machine learning algorithms and data augmentation and modification methods. This research develops the direction of machine learning where training is conducted on well data and spatial attributes. Methods for overcoming the limitations of this direction are shown, two methods - augmentation and modification of the well data sample: Spindle and Revers-Calibration. Considering the difficulties for seismic data interpretation in …
Institute of Computer Science（计算机科学研究所）；AGH University of Science and Technology（AGH科技大学）
The growing number of IoT devices and their use to monitor the operation of machines and equipment increases interest in anomaly detection algorithms running on devices. However, the difficulty is the limitations of the available computational and memory resources on the devices. In the case of microcontrollers (MCUs), these are single megabytes of program and several hundred kilobytes of working memory. Consequently, algorithms must be appropriately matched to the capabilities of the devices. In the paper, we analyse the processing pipeline for anomaly detection and implementation of the Loca…
Role of scrambling and noise in temporal information processing with quantum systems
Institute of Physics, Ecole Polytechnique F\' e d\' e rale de Lausanne (EPFL), Lausanne, Switzerland；Centre for Quantum Science；Engineering, Ecole Polytechnique F\' e d\' e rale de Lausanne (EPFL), Lausanne, Switzerland；Complex Systems Lab, Department of Physics, Faculty of Science, Chulalongkorn University, Bangkok, Thailand
Skolkovo Institute of Science and Technology（斯科尔科沃科学技术学院）；JSC Zarubezhneft（扎鲁别日石油股份公司）
Well known oil recovery factor estimation techniques such as analogy, volumetric calculations, material balance, decline curve analysis, hydrodynamic simulations have certain limitations. Those techniques are time-consuming, require specific data and expert knowledge. Besides, though uncertainty estimation is highly desirable for this problem, the methods above do not include this by default. In this work, we present a data-driven technique for oil recovery factor estimation using reservoir parameters and representative statistics. We apply advanced machine learning methods to historical world…
A model of metabolic energy constraints is applied to a liquid state machine in order to analyze its effects on network performance. It was found that, in certain combinations of energy constraints, a significant increase in testing accuracy emerged; an improvement of 4.25% was observed on a seizure detection task using a digital liquid state machine while reducing overall reservoir spiking activity by 6.9%. The accuracy improvements appear to be linked to the energy constraints' impact on the reservoir's dynamics, as measured through metrics such as the Lyapunov exponent and the separation of…
Indian Institute of Technology, Kharagpur（印度理工学院卡拉格普尔分校）
Reservoir Characterization (RC) can be defined as the act of building a reservoir model that incorporates all the characteristics of the reservoir that are pertinent to its ability to store hydrocarbons and also to produce them.It is a difficult problem due to non-linear and heterogeneous subsurface properties and associated with a number of complex tasks such as data fusion, data mining, formulation of the knowledge base, and handling of the uncertainty.This present work describes the development of algorithms to obtain the functional relationships between predictor seismic attributes and tar…
Generalization with Reverse-Calibration of Well and Seismic Data Using Machine Learning Methods for Complex Reservoirs Predicting During Early-Stage Geological Exploration Oil Field
