A Hopf physical reservoir computer

Artificial neural networks built with optoelectronic synaptic devices have been proven to process visual information effectively. However, it takes great latency time and energy consumption, especially facing dynamic visual information, due to the separated optical sensor, memory, and process unit. Reservoir computing (RC) based on optoelectronic synaptic devices provides an in-sensor RC for processing temporal information efficiently. It achieves efficient computation by sensing and processing optical signals directly with optoelectronic synaptic devices. Optoelectronic synaptic devices shine in visual information processing, whose application in visual sensing and processing will provide a viable hardware solution for in-sensor computing. Therefore, the application of optoelectronic synaptic devices in reservoir computing has prompted increasing attention. Herein, for promoting the application of physical reservoir computing (PRC) with optoelectrical synapses in machine vision, synaptic plasticity will be introduced first in this work and then illustrate the basic functions of optoelectronic synapses as well as their application in reservoir computing further, and provide a perspective on PRC with optoelectronic synapses in the final.

Physical reservoir computing (RC) systems have emerged as a prominent research frontier due to their exceptional efficiency in temporal information processing. However, existing implementations, predominantly utilizing resistive devices, face challenges pertaining to power efficiency and dynamic richness. Here, we propose a ferroelectric capacitor-linear capacitor (FC-LC) series device for RC implementation. By leveraging nonlinear polarization switching and back-switching, the FC-LC series device realizes two essential reservoir properties: nonlinearity and fading memory. In addition, the device exhibits an ultralow power consumption, which, along with its direct voltage readout capability, marks a significant advance over resistive reservoir devices. Moreover, the device features bidirectional operation and widely tunable time constants, thereby enhancing reservoir space dimensionality and state richness. Building upon these FC-LC series devices, a ferroelectric capacitive RC system is developed, which demonstrates superior performance in various benchmark tasks. By exploiting the bidirectional operation of the device, the RC system not only delivers enhanced performance in waveform classification but also enables high-accuracy multimodal digit recognition. Through strategically hybridizing the FC-LC series devices with varying time constants, the RC system achieves remarkable performance in Mackey-Glass time-series prediction. Our study paves the way for power-efficient, dynamic-rich RC systems capable of handling diverse temporal tasks.

Physical reservoir computing, which is a promising method for the implementation of highly efficient artificial intelligence devices, requires a physical system with nonlinearity, fading memory, and the ability to map in high dimensions. Although it is expected that spin wave interference can perform as highly efficient reservoir computing in some micromagnetic simulations, there has been no experimental verification to date. Herein, reservoir computing is demonstrated that utilizes multidetected nonlinear spin wave interference in an yttrium‐iron‐garnet single crystal. The subject computing system achieves excellent performance when used for hand‐written digit recognition, second‐order nonlinear dynamical tasks, and nonlinear autoregressive moving average (NARMA). It is of particular note that normalized mean square errors for NARMA2 and second‐order nonlinear dynamical tasks are 1.81 × 10−2 and 8.37 × 10−5, respectively, which are the lowest figures for any experimental physical reservoir so far reported. Said high performance is achieved with higher nonlinearity and the large memory capacity of interfered spin wave multidetection.

Analysis and fully memristor-based reservoir computing for temporal data classification

Physical reservoir computing is a computational paradigm that enables spatiotemporal pattern recognition to be performed directly in matter. The use of physical matter leads the way toward energy‐efficient devices capable of solving machine learning problems without having to build a system of millions of interconnected neurons. Proposed herein is a high‐performance “skyrmion mixture reservoir” that implements the reservoir computing model with multidimensional inputs. This implementation solves spoken digit classification tasks with an overall model accuracy of 97.4% and a < 1% word error ratethe best performance ever reported for in materio reservoir computers. Due to the quality of the results and the low‐power properties of magnetic texture reservoirs, it is evident that skyrmion fabrics are a compelling candidate for reservoir computing.

With the growing use of artificial neural networks (ANNs) in temporal data processing tasks, the cost of training for complex ANNs is an escalating concern. Physical reservoir computing (RC), a variation of recurrent neural networks (RNNs), obviate the need for most data intensive matrix vector multiplication in the recurrent layer by evolving the RC’s internal states with the inherent nonlinear dynamics and short-term memory. In this study, we show that magnetic skyrmion confined in a fixed geometry forming the soft layer of a magnetic tunnel junction (MTJ) can work as a RC and perform autonomous long-term prediction of temporal data. Our proposed skyrmion reservoir allows for manipulation of spin dynamics with ultra energy efficient voltage controlled magnetic anisotropy modulation (VCMA) method. Furthermore, the boundary effect on the skyrmion from the geometric edges provides necessary consistency property of the reservoir. We employ our proposed reservoir for the modeling and prediction of the chaotic time series such as Mackey-Glass and dynamic time-series data, such as household building energy loads. For autonomous run, the predicted output is fed to the input of the reservoir. By comparing our spintronic physical RC approach with energy load forecasting algorithms, such as LSTMs and RNNs, we conclude that the proposed framework presents good performance in achieving high predictions accuracy, while also requiring low memory and energy both of which are at a premium in hardware resource and power constrained edge applications. Further, the proposed approach is shown to require very small training datasets and at the same time being at least 16× energy efficient compared to the sequence to sequence LSTM for accurate household load predictions. Higher endurance, fast processing and well-established technology (i.e., MTJ) to integrate with CMOS technology makes such spintronic reservoir attractive over other emergent memory device-based reservoirs.

Physical reservoir computing (RC) is a recently introduced framework for information processing using the complex dynamics of physical systems. In this paper, a physical reservoir based on a molecular network of polyoxometalate (POM) decorated single-walled carbon nanotubes (SWCNT) with PBMA composite is fabricated. By the lab-built hardware platform, we experimentally demonstrate its excellent performance in a time series prediction benchmark with large short-term memory capacity (MC), indicating SWCNT/POM network as a promising substrate for reservoir computing because abundant inner charge and discharge in junctions leading to special electron transport characteristics that make rich dynamic and high-dimensional mapping properties appear in the POM-decorated SWCNT composite structure.

An electrocardiogram (ECG) is a medical test that records the electrical activity of the heart over a period of time. This non-invasive and painless test makes ECG an essential tool in cardiology for diagnosing and monitoring heart health. Phonocardiogram (PCG) are typically used as an adjunct to the expertise of healthcare professionals rather than as a standalone diagnostic tool. By applying ECG signals to predict the corresponding PCG signals, no additional test for PCG is needed. These predictions can assist doctors in making informed decisions about patient care and treatment plans by merely collecting ECG signals. Physical reservoir computing (RC), as a bio-inspired algorithm, has received growing research interest. Under the term neuromorphic, physical RC processes the raw signals in the analogue domain with in-memory computing, thus reducing massive power consumption. At the same time, RC is a special type of Recurrent Neural Network (RNN) that is suitable for time-dependent signal processing. The ECG/PCG dataset we used here was experimentally collected by 10 people. We applied a recently proposed physical RC architecture called Rotating Neuron Reservoir and achieved an average NRMSE of 0.3690 for prediction, aiming to propose and construct a neuromorphic processing core for the ECG-to-PCG prediction task.

It is known that it is possible to develop a chemically intelligent robot that can perceive spatial extent using the BZ reaction. If the BZ reaction can be used for learning, there is a possibility of developing a chemically intelligent robot that can make complex judgments about situations like living organisms. In the physical reservoir calculation, it is possible to construct a learning system using a material system, so in this study, we build a physical reservoir calculation using the BZ reaction and confirmed that learning is possible. The physical reservoir computation was capable of performing tasks such as time series prediction and speech recognition. BZ reaction, nonlinear chemical reaction, reservoir computing, time series prediction, speech recognition

In the present paper, we propose and experimentally verify a concept of a magnonic reservoir computer. The system utilizes the nonlinear behavior of propagating magnetostatic surface spin waves in a yttrium-iron garnet thin film and the time delay inherent in the active ring configuration to process time-dependent data streams. Higher reservoir dimensionality is obtained through the time-multiplexing method, whereby inputs to the system are multiplied by a mask to drive complex dynamics in the ring and the output is sampled in time to create a series of ``virtual'' neurons for each sample. The input mask is implemented as a train of microwave pulses injected to the system. To demonstrate the efficacy of the concept, the reservoir computer is evaluated on the short-term memory and parity-check benchmark tasks, and the physical system parameters are tuned to optimize performance. By incorporating a reference line to mix the input signal directly onto the ring-resonator output, both the amplitude and phase nonlinearity of the spin waves can be exploited. The addition of a second spin-wave delay line increases the delay time of the ring and enhances the fading memory capacity of the system. Configuring the second delay line to transmit backward volume spin waves also partly compensates the dispersive pulse broadening that is present because of the large delay time.

Reservoir computing is a brain-inspired machine learning framework for processing temporal data by mapping inputs into high-dimensional spaces. Physical reservoir computers (PRCs) leverage native fading memory and nonlinearity in physical substrates, including atomic switches, photonics, volatile memristors, and, recently, memcapacitors, to achieve efficient high-dimensional mapping. Traditional PRCs often consist of homogeneous device arrays, which rely on input encoding methods and large stochastic device-to-device variations for increased nonlinearity and high-dimensional mapping. These approaches incur high preprocessing costs and restrict real-time deployment. Here, we introduce a heterogeneous memcapacitor-based PRC that exploits internal voltage offsets to enable both monotonic and nonmonotonic input-state correlations crucial for efficient high-dimensional transformations. We demonstrate our approach’s efficacy by predicting a second-order nonlinear dynamical system with a low prediction error (1.80 × 10–4). Additionally, we predict a chaotic Hénon map, achieving a low normalized root-mean-square error (0.080). Unlike previous PRCs, such errors are achieved without input encoding methods, underscoring the power of distinct input-state correlations. Most importantly, we generalize our approach to other neuromorphic devices that lack inherent voltage offsets using externally applied offsets to realize various input-state correlations. Our approach and the unprecedented performance are major milestones toward high-performance full in-materia PRCs.

Reservoir computing derived from recurrent neural networks is more applicable to real world systems than deep learning because of its low computational cost and potential for physical implementation. Specifically, physical reservoir computing, which replaces the dynamics of reservoir units with physical phenomena, has recently received considerable attention. In this study, we propose a method of exploiting the dynamics of road traffic as a reservoir, and numerically confirm its feasibility by applying several prediction tasks based on a simple mathematical model of the traffic flow.

We investigated physical reservoir computing (RC) using a vortex-type spin torque oscillator (STO) as a resource of nonlinear dynamics, which is essential for processing information in time-series data. Forced synchronization was used to suppress the thermal fluctuation of the oscillation trajectory of the STO. We examined the memory property of the STO dynamics, called short-term memory (STM), by using a virtual node technique. The STM capacity increased about twofold compared with that obtained without forced synchronization. The performance index for the nonlinear transformation of the STO also increased; it was evaluated in a parity-check task. The results prove that the synchronized STO has great potential for physical RC based on nanotechnology.

Reservoir computing leverages the dynamic properties of a fixed, randomly connected neural network to facilitate simplified training and enhanced computational efficiency. Many forms of physical reservoir computers have been proposed. In this paper, we use a three-dimensional (3D)-printed reservoir computer as the design environment, develop analytic models to describe its performance, and validate the models through simulations. This approach offers practical insights for designing physical reservoirs with targeted computational capabilities and enables the assessment of the influence of reservoir parameters such as scale or material choice, on performance metrics, including speed and power consumption. Additionally, the proposed approach may be employed to optimally design physical reservoir computers to solve specific problems. This work contributes to the understanding of physical RC systems by providing a detailed analysis of the physical basis that connects computational performance with multidomain physical interactions at the device level. The methods and results from this work not only propel the development of future 3D-printed physical RC systems but also serves as a framework for evaluating and designing diverse physical RC models based on other approaches. Published by the American Physical Society 2024

Artificial neural networks and recurrent neural networks are foundational to machine learning; although successful, their simplified components lack the intricate dynamics and high functional density of biological neural networks, limiting their efficiency. Physical reservoir computing (PRC) offers an alternative by leveraging the intrinsic dynamics of physical systems while restricting training to the readout layer. However, two significant shortcomings hinder the PRC's efficacy: the memory‐nonlinearity trade‐off, where increasing nonlinearity reduces memory capacity, and limited timescale adaptability, constraining it to contrived task‐device matching. This work presents a biomolecular PRC system that integrates heterogeneous nodes with complementary memimpedance properties using droplet interface bilayers. The system combines ion channel‐based memristive (nonlinear, fast‐switching) and biomembrane‐based memcapacitive (linear, slow‐switching) nodes within a single device, addressing the trade‐off and enabling multiscale temporal processing. Predicting a second‐order nonlinear system is demonstrated to address the trade‐off, achieving a normalized mean square error of 0.176 with the hybrid system outperforming memristive and memcapacitive reservoirs. Additionally, two real‐time classification tasks validate the system's ability to process signals across temporal scales, achieving 100% accuracy in both tasks. This approach expands PRC's applicability across diverse tasks without preoptimization, underscoring the potential of PRC and soft biomolecular materials for adaptive energy‐efficient computing.