Optoelectronic memristor is generating growing research interest for high efficient computing and sensing-memory applications.In this work,an optoelectronic memristor with Au/a-C:Te/Pt structure is developed.Synaptic ...Optoelectronic memristor is generating growing research interest for high efficient computing and sensing-memory applications.In this work,an optoelectronic memristor with Au/a-C:Te/Pt structure is developed.Synaptic functions,i.e.,excita-tory post-synaptic current and pair-pulse facilitation are successfully mimicked with the memristor under electrical and optical stimulations.More importantly,the device exhibited distinguishable response currents by adjusting 4-bit input electrical/opti-cal signals.A multi-mode reservoir computing(RC)system is constructed with the optoelectronic memristors to emulate human tactile-visual fusion recognition and an accuracy of 98.7%is achieved.The optoelectronic memristor provides potential for developing multi-mode RC system.展开更多
Memristive devices based on in-memory computing architectures offer a promising strategy for overcoming the energy bottlenecks inherent in big data systems.However,uncontrolled ion migration at the material level rema...Memristive devices based on in-memory computing architectures offer a promising strategy for overcoming the energy bottlenecks inherent in big data systems.However,uncontrolled ion migration at the material level remains a key challenge,compromising device stability and hindering practical applications.Here,we employ a chemical optimization strategy that dynamically induces the precipitation of Ag atoms under applied voltage,creating fixed atomic sites to achieve precise control over ion migration,synergistically enhancing the memory and computing capabilities of the device.Compared to unoptimized samples,the proposed device exhibits an approximately 8-fold improvement in robustness,a 3-fold enhancement in stability,high mechanical endurance,and reliable multilevel data storage capability.We further construct a device array and incorporate an efficient reservoir computing model,achieving handwritten digit recognition with an accuracy of up to 90.81%.In summary,this work proposes a dynamic Ag/Ag^(+)anchoring strategy and demonstrates a memristor-based approach that integrates storage and computation to enable energy-efficient artificial intelligence processing,offering a scalable solution for sustainable intelligence in the big data era.展开更多
Recurrent neural networks(RNNs)have proven to be indispensable for processing sequential and temporal data,with extensive applications in language modeling,text generation,machine translation,and time-series forecasti...Recurrent neural networks(RNNs)have proven to be indispensable for processing sequential and temporal data,with extensive applications in language modeling,text generation,machine translation,and time-series forecasting.Despite their versatility,RNNs are frequently beset by significant training expenses and slow convergence times,which impinge upon their deployment in edge AI applications.Reservoir computing(RC),a specialized RNN variant,is attracting increased attention as a cost-effective alternative for processing temporal and sequential data at the edge.RC’s distinctive advantage stems from its compatibility with emerging memristive hardware,which leverages the energy efficiency and reduced footprint of analog in-memory and in-sensor computing,offering a streamlined and energy-efficient solution.This review offers a comprehensive explanation of RC’s underlying principles,fabrication processes,and surveys recent progress in nano-memristive device based RC systems from the viewpoints of in-memory and in-sensor RC function.It covers a spectrum of memristive device,from established oxide-based memristive device to cutting-edge material science developments,providing readers with a lucid understanding of RC’s hardware implementation and fostering innovative designs for in-sensor RC systems.Lastly,we identify prevailing challenges and suggest viable solutions,paving the way for future advancements in in-sensor RC technology.展开更多
Model-free,data-driven prediction of chaotic motions is a long-standing challenge in nonlinear science.Stimulated by the recent progress in machine learning,considerable attention has been given to the inference of ch...Model-free,data-driven prediction of chaotic motions is a long-standing challenge in nonlinear science.Stimulated by the recent progress in machine learning,considerable attention has been given to the inference of chaos by the technique of reservoir computing(RC).In particular,by incorporating a parameter-control channel into the standard RC,it is demonstrated that the machine is able to not only replicate the dynamics of the training states,but also infer new dynamics not included in the training set.The new machine-learning scheme,termed parameter-aware RC,opens up new avenues for data-based analysis of chaotic systems,and holds promise for predicting and controlling many real-world complex systems.Here,using typical chaotic systems as examples,we give a comprehensive introduction to this powerful machine-learning technique,including the algorithm,the implementation,the performance,and the open questions calling for further studies.展开更多
Optical reservoir computing(ORC)offers advantages,such as high computational speed,low power consumption,and high training speed,so it has become a competitive candidate for time series analysis in recent years.The cu...Optical reservoir computing(ORC)offers advantages,such as high computational speed,low power consumption,and high training speed,so it has become a competitive candidate for time series analysis in recent years.The current ORC employs single-dimensional encoding for computation,which limits input resolution and introduces extraneous information due to interactions between optical dimensions during propagation,thus constraining performance.Here,we propose complex-value encoding-based optoelectronic reservoir computing(CE-ORC),in which the amplitude and phase of the input optical field are both modulated to improve the input resolution and prevent the influence of extraneous information on computation.In addition,scale factors in the amplitude encoding can fine-tune the optical reservoir dynamics for better performance.We built a CE-ORC processing unit with an iteration rate of up to∼1.2 kHz using high-speed communication interfaces and field programmable gate arrays(FPGAs)and demonstrated the excellent performance of CE-ORC in two time series prediction tasks.In comparison with the conventional ORC for the Mackey–Glass task,CE-ORC showed a decrease in normalized mean square error by∼75%.Furthermore,we applied this method in a weather time series analysis and effectively predicted the temperature and humidity within a range of 24 h.展开更多
Neuromorphic computing,inspired by the human brain,uses memristor devices for complex tasks.Recent studies show that self-organizing random nanowires can implement neuromorphic information processing,enabling data ana...Neuromorphic computing,inspired by the human brain,uses memristor devices for complex tasks.Recent studies show that self-organizing random nanowires can implement neuromorphic information processing,enabling data analysis.This paper presents a model based on these nanowire networks,with an improved conductance variation profile.We suggest using these networks for temporal information processing via a reservoir computing scheme and propose an efficient data encoding method using voltage pulses.The nanowire network layer generates dynamic behaviors for pulse voltages,allowing time series prediction analysis.Our experiment uses a double stochastic nanowire network architecture for processing multiple input signals,outperforming traditional reservoir computing in terms of fewer nodes,enriched dynamics and improved prediction accuracy.Experimental results confirm the high accuracy of this architecture on multiple real-time series datasets,making neuromorphic nanowire networks promising for physical implementation of reservoir computing.展开更多
The blockchain-empowered Internet of Vehicles(IoV)enables various services and achieves data security and privacy,significantly advancing modern vehicle systems.However,the increased frequency of data transmission and...The blockchain-empowered Internet of Vehicles(IoV)enables various services and achieves data security and privacy,significantly advancing modern vehicle systems.However,the increased frequency of data transmission and complex network connections among nodes also make them more susceptible to adversarial attacks.As a result,an efficient intrusion detection system(IDS)becomes crucial for securing the IoV environment.Existing IDSs based on convolutional neural networks(CNN)often suffer from high training time and storage requirements.In this paper,we propose a lightweight IDS solution to protect IoV against both intra-vehicle and external threats.Our approach achieves superior performance,as demonstrated by key metrics such as accuracy and precision.Specifically,our method achieves accuracy rates ranging from 99.08% to 100% on the Car-Hacking dataset,with a remarkably short training time.展开更多
Graphene oxide,as a 2D material with nanometer thickness,offers ultra-high mobility,chaotic properties,and low cost.These make graphene oxide memristors beneficial for reservoir computing(RC)networks.In this study,con...Graphene oxide,as a 2D material with nanometer thickness,offers ultra-high mobility,chaotic properties,and low cost.These make graphene oxide memristors beneficial for reservoir computing(RC)networks.In this study,continuous-wave(CW)laser processing is used to reduce chaotic graphene oxide(CGO)films,resulting in the non-volatile storage capability based on the reduced chaotic graphene oxide(rCGO)films.Laser power significantly impacts the characteristics of the rCGO memristor.Material characterization indicates that laser radiation can effectively reduce the oxygen content in CGO films.With optimized laser power,the rCGO memristor achieves a large ratio at 18 mW laser power.Benefiting from the short-term mem-ory characteristics,distinct conductive states are achieved,which are further utilized to construct RC networks.With a third con-trol probe,the rCGO memristor can express rich reservoir states,demonstrating accuracy in predicting the Hénon map with an NRMSE below 0.3.These findings provide the potential for developing flexible RC networks based on graphene oxide memris-tors via laser processing.展开更多
Artificial neural networks with internal dynamics exhibit remarkable capability in processing information.Reservoir computing(RC)is a canonical example that features rich computing expressivity and compatibility with ...Artificial neural networks with internal dynamics exhibit remarkable capability in processing information.Reservoir computing(RC)is a canonical example that features rich computing expressivity and compatibility with physical implementations for enhanced efficiency.Recently,a new RC paradigm known as next generation reservoir computing(NGRC)further improves expressivity but compromises its physical openness,posing challenges for realizations in physical systems.Here we demonstrate optical NGRC with computations performed by light scattering through disordered media.In contrast to conventional optical RC implementations,we directly and solely drive our optical reservoir with time-delayed inputs.Much like digital NGRC that relies on polynomial features of delayed inputs,our optical reservoir also implicitly generates these polynomial features for desired functionalities.By leveraging the domain knowledge of the reservoir inputs,we show that the optical NGRC not only predicts the short-term dynamics of the low-dimensional Lorenz63 and large-scale Kuramoto-Sivashinsky chaotic time series,but also replicates their long-term ergodic properties.Optical NGRC shows superiority in shorter training length and fewer hyperparameters compared to conventional optical RC based on scattering media,while achieving better forecasting performance.Our optical NGRC framework may inspire the realization of NGRC in other physical RC systems,new applications beyond time-series processing,and the development of deep and parallel architectures broadly.展开更多
We utilize three parallel reservoir computers using semiconductor lasers with optical feedback and light injection to model radar probe signals with delays.Three radar probe signals are generated by driving lasers con...We utilize three parallel reservoir computers using semiconductor lasers with optical feedback and light injection to model radar probe signals with delays.Three radar probe signals are generated by driving lasers constructed by a threeelement laser array with self-feedback.The response lasers are implemented also by a three-element lase array with both delay-time feedback and optical injection,which are utilized as nonlinear nodes to realize the reservoirs.We show that each delayed radar probe signal can be predicted well and to synchronize with its corresponding trained reservoir,even when parameter mismatches exist between the response laser array and the driving laser array.Based on this,the three synchronous probe signals are utilized for ranging to three targets,respectively,using Hilbert transform.It is demonstrated that the relative errors for ranging can be very small and less than 0.6%.Our findings show that optical reservoir computing provides an effective way for applications of target ranging.展开更多
Memristors have been emerging as promising candidates for computing systems in post-Moore applications,particularly electrochemical metallizationbased memristors,which are poised to play a crucial role in neuromorphic...Memristors have been emerging as promising candidates for computing systems in post-Moore applications,particularly electrochemical metallizationbased memristors,which are poised to play a crucial role in neuromorphic computing and machine learning.These devices are favored for their high integration density,low power consumption,rapid switching speed,and significant on/off ratio.Despite advancements in various materials,achieving adequate electrical performance—characterized by threshold switching(TS)behavior,spontaneous reset,and low off-state resistance—remains challenging due to the limitations in conductance filament control within the nanoscale resistive switching layer.In this study,we introduce an efficient method to control the ZrO_(2) crystallinity for tunable volatility memristor by establishing the filament paths through a simple thermal treatment process in a single oxide layer.The effect of ZrO_(2) crystallinity to create localized filament paths for enhancing Ag migration and improving TS behavior is also investigated.In contrast to its amorphous counterpart,crystallized ZrO_(2) volatile memristor,treated by rapid thermal annealing,demonstrates a steep switching slope(0.21 mV dec^(–1)),a high resistance state(25 GΩ),and forming-free characteristics.The superior volatile performance is attributed to localized conductive filaments along lowenergy pathways,such as dislocations and grain boundaries.By coupling with enhanced volatile switching behavior,we believe that the volatility is finely tuned to function as short-term memory for reservoir computing,making it particularly well-suited for tasks such as audio and image recognition.展开更多
Physical reservoir computing(PRC)offers an effective computing paradigm for spatiotemporal information processing with low training costs.Achieving controllable regulation over the temporal dynamics of devices to meet...Physical reservoir computing(PRC)offers an effective computing paradigm for spatiotemporal information processing with low training costs.Achieving controllable regulation over the temporal dynamics of devices to meet the computational demands of each physical layer is a key challenge for realizing highperformance PRC chips.Here,we proposed a homogeneously integrated all-PRC with tunable temporal dynamics.Utilizing the modulation effect of oxygen vacancies on the energy barrier of the pentacene/ZnO interface,shortterm memory,and long-term memory switching characteristics have been achieved within the same device structure.Furthermore,by altering the gate voltage,the reservoir exhibited a broad range ratio of temporal characteristics(>10^(2)),which provides the potential to map information with different temporal characteristics.Inspired by the process of encoding and reconstructing spatiotemporal information in the human visual system,a biomimetic obstacle recognition system has been constructed to assist visually impaired individuals in walking,demonstrating excellent accuracy in obstacle types(100%)and distances(97.2%)recognition.This work offers a promising avenue for the development of an integrated PRC system with multi-timescale information processing capability.展开更多
Artificial visual sensors(AVSs)with bio-inspired sensing and neuromorphic signal processing are essential for next-generation intelligent systems.Conventional optoelectronic devices employed in AVSs operate discretely...Artificial visual sensors(AVSs)with bio-inspired sensing and neuromorphic signal processing are essential for next-generation intelligent systems.Conventional optoelectronic devices employed in AVSs operate discretely in terms of sensing,processing,and memorization,and not ideal for applications necessitating shape deformation to achieve wide fields-of-view and deep depths-of-field.Here,we present stretchable artificial visual sensors(S-AVS)capable of concurrently sensing and processing optical signals while adapting to shape deformations.Specifically,these S-AVSs use a stretchable transistor structure with a meticulously engineered photosensitive semiconductor layer,comprising an organic semiconductor,thermoplastic elastomer,and cesium lead bromide quantum dots(CsPbBr_(3) QDs).They exhibit synaptic behaviors such as excitatory postsynaptic current(EPSC)and paired-pulse facilitation(PPF)under optical signals,maintaining functionality under 30%strain and repeated stretching.The nonlinear response and fading memory effect support in-sensor reservoir computing,achieving image recognition accuracies of 97.46%and 97.1%at 0%and 30%strain,respectively.展开更多
The artificial intelligence era has witnessed a surge of demand in detection and recognition of biometric information,with applications from financial services to information security.However,the physical separation o...The artificial intelligence era has witnessed a surge of demand in detection and recognition of biometric information,with applications from financial services to information security.However,the physical separation of sensing,memory,and computational units in traditional biometric systems introduces severe decision latency and operational power consumption.Herein,an in-sensor reservoir computing(RC)system based on MoTe_(2)/BaTiO_(3)optical synapses is proposed to detect and recognize the faces and fingerprints information.In optical operation mode,the device exhibits low energy consumption of 41.2 pJ,long retention time of 3×10^(4)s,high endurance of 10^(4)switching cycles,and multifunctional sensing-memory-computing visual simulations.The light intensity-dependent optical sensing and multilevel optical storage properties are exploited to achieve sunburned eye simulation and image memory functions.These nonlinear,multi-state,short-term storage,and long-term memory characteristics make MoTe_(2)/BaTiO_(3)optical synapses a suitable reservoir layer and readout layer,with short-term properties to project complicated input features into high-dimensional output features,and long-term properties to be used as a readout layer,thus further building an in-sensor RC system for face and fingerprint recognition.Under the 40%Gaussian noise environment,the system achieves 91.73%recognition accuracy for face and 97.50%for fingerprint images,and experimental verification is carried out,which shows potential in practical applications.These results provide a strategy for constructing a high-performance in-sensor RC system for high-accuracy biometric identification.展开更多
In this study,TiN/NbO_(x)/Pt memristor devices with short-term memory(STM)and self-rectifying characteristics are used for reservoir computing.The STM characteristics of the device are detected using direct current sw...In this study,TiN/NbO_(x)/Pt memristor devices with short-term memory(STM)and self-rectifying characteristics are used for reservoir computing.The STM characteristics of the device are detected using direct current sweep and pulse transients.The self-rectifying characteristics of the device can be explained by the work function differences between the TiN and Pt electrodes.Furthermore,neural network simulations were conducted for pattern recognition accuracy when the conductance was used as the synaptic weight.The emulation of synaptic memory and forgetfulness by short-term memory effects are demonstrated using paired-pulse facilitation and excitatory postsynaptic potential.The efficient training reservoir computing consisted of all 16 states(4-bit)in the memristor device as a physical reservoir and the artificial neural network simulation as a readout layer and yielded a pattern recognition accuracy of 92.34%for the modified National Institute of Standards and Technology dataset.Finally,it is found that STM and long-term memory in the device coexist by adjusting the intensity of pulse stimulation.展开更多
In this study,we examined plant health prediction through the Normalized Difference Vegetation Index(NDVI)calculated from satellite image derived reflectance values in the near-infrared and red spectra.The problem is ...In this study,we examined plant health prediction through the Normalized Difference Vegetation Index(NDVI)calculated from satellite image derived reflectance values in the near-infrared and red spectra.The problem is formulated as a temporal data prediction problem.Using MODIS/Terra Vegetation Indices 16-Day L3 Global 250 m SIN Grid V061 dataset,we designed and implemented Reservoir Computing(RC)models and transformer-based models including pretrained language model,and compared the prediction performance of these models to traditional machine learning and deep learning methods such as Nonlinear Regression,Decision Tree,Convolutional Neural Network(CNN),Long Short-Term Memory(LSTM)network,and DLinear.It is observed that the DLinear/LSTM model showed exceptional predictive accuracy,while the pretrained RC model significantly enhanced traditional RC model forecasts.Additionally,Frozen Pretrained Transformer(FPT),a pretrained language model,showed superior performance in predicting specific NDVI values(most often peak or lowest NDVI),suggesting its effectiveness in precise temporal predictions.Furthermore,transformer-based models,specifically PatchTST and FPT,demonstrated substantial mean squared error reductions,particularly in limited data scenarios(1%,5%,15%and 50%sample sizes),indicating their robustness in precise NDVI temporal predictions when data is limited.The findings in this study demonstrated the effectiveness of emerging machine learning techniques such as reservoir computing and pretrained language model for remote sensing and their contributions in precision agriculture.展开更多
Real-time prediction of ship motions is crucial for ensuring the safety of offshore activities.In this study,we investigate the performance of the reservoir computing(RC)model in predicting the motions of a ship saili...Real-time prediction of ship motions is crucial for ensuring the safety of offshore activities.In this study,we investigate the performance of the reservoir computing(RC)model in predicting the motions of a ship sailing in irregular waves,comparing it with the long short-term memory(LSTM),bidirectional LSTM(BiLSTM),and gated recurrent unit(GRU)networks.The model tests are carried out in a towing tank to generate the datasets for training and testing the machine learning models.First,we explore the performance of machine learning models trained solely on motion data.It is found that the RC model outperforms the L STM,BiL STM,and GRU networks in both accuracy and efficiency for predicting ship motions.Besides,we investigate the performance of the RC model trained using the historical motion and wave elevation data.It is shown that,compared with the RC model trained solely on motion data,the RC model trained on the motion and wave elevation data can significantly improve the motion prediction accuracy.This study validates the effectiveness and efficiency of the RC model in ship motion prediction during sailing and highlights the utility of wave elevation data in enhancing the RC model’s prediction accuracy.展开更多
Recently, with the emergence of ChatGPT, the field of artificial intelligence has garnered widespread attention from various sectors of society. Reservoir Computing (RC) is a neuromorphic computing algorithm used to a...Recently, with the emergence of ChatGPT, the field of artificial intelligence has garnered widespread attention from various sectors of society. Reservoir Computing (RC) is a neuromorphic computing algorithm used to analyze time-series data. Unlike traditional artificial neural networks that require the weight values of all nodes in the trained network, RC only needs to train the readout layer. This makes the training process faster and more efficient, and it has been used in various applications, including speech recognition, image classification, and control systems. Its flexibility and efficiency make it a popular choice for processing large amounts of complex data. A recent research trend is to develop physical RC, which utilizes the nonlinear dynamic and short-term memory properties of physical systems (photonic modules, spintronic devices, memristors, etc.) to construct a fixed random neural network structure for processing input data to reduce computing time and energy. In this paper, we introduced the recent development of memristors and demonstrated the remarkable data processing capability of RC systems based on memristors. Not only do they possess excellent data processing ability comparable to digital RC systems, but they also have lower energy consumption and greater robustness. Finally, we discussed the development prospects and challenges faced by memristors-based RC systems.展开更多
Reservoir computing(RC)is an energy-efficient computational framework with low training cost and high efficiency in processing spatiotemporal information.The state-of-the-art fully memristor-based hardware RC system s...Reservoir computing(RC)is an energy-efficient computational framework with low training cost and high efficiency in processing spatiotemporal information.The state-of-the-art fully memristor-based hardware RC system suffers from bottlenecks in the computation efficiencies and accuracy due to the limited temporal tunability in the volatile memristor for the reservoir layer and the nonlinearity in the nonvolatile memristor for the readout layer.Additionally,integrating different types of memristors brings fabrication and integration complexities.To overcome the challenges,a multifunctional multi-terminal electrolyte-gated transistor(MTEGT)that combines both electrostatic and electrochemical doping mechanisms is proposed in this work,integrating both widely tunable volatile dynamics with high temporal tunable range of 10^(2) and nonvolatile memory properties with high long-term potentiation/long-term depression(LTP/LTD)linearity into a single device.An ion-controlled physical RC system fully implemented with only one type of MTEGT is constructed for image recognition using the volatile dynamics for the reservoir and nonvolatility for the readout layer.Moreover,an ultralow normalized mean square error of 0.002 is achieved in a time series prediction task.It is believed that the MTEGT would underlie next-generation neuromorphic computing systems with low hardware costs and high computational performance.展开更多
Photonic platforms are gradually emerging as a promising option to encounter the ever-growing demand for artificial intelligence,among which photonic time-delay reservoir computing(TDRC)is widely anticipated.While suc...Photonic platforms are gradually emerging as a promising option to encounter the ever-growing demand for artificial intelligence,among which photonic time-delay reservoir computing(TDRC)is widely anticipated.While such a computing paradigm can only employ a single photonic device as the nonlinear node for data processing,the performance highly relies on the fading memory provided by the delay feedback loop(FL),which sets a restriction on the extensibility of physical implementation,especially for highly integrated chips.Here,we present a simplified photonic scheme for more flexible parameter configurations leveraging the designed quasi-convolution coding(QC),which completely gets rid of the dependence on FL.Unlike delay-based TDRC,encoded data in QC-based RC(QRC)enables temporal feature extraction,facilitating augmented memory capabilities.Thus,our proposed QRC is enabled to deal with time-related tasks or sequential data without the implementation of FL.Furthermore,we can implement this hardware with a low-power,easily integrable vertical-cavity surface-emitting laser for high-performance parallel processing.We illustrate the concept validation through simulation and experimental comparison of QRC and TDRC,wherein the simpler-structured QRC outperforms across various benchmark tasks.Our results may underscore an auspicious solution for the hardware implementation of deep neural networks.展开更多
基金supported by the"Science and Technology Development Plan Project of Jilin Province,China"(Grant No.20240101018JJ)the Fundamental Research Funds for the Central Universities(Grant No.2412023YQ004)the National Natural Science Foundation of China(Grant Nos.52072065,52272140,52372137,and U23A20568).
文摘Optoelectronic memristor is generating growing research interest for high efficient computing and sensing-memory applications.In this work,an optoelectronic memristor with Au/a-C:Te/Pt structure is developed.Synaptic functions,i.e.,excita-tory post-synaptic current and pair-pulse facilitation are successfully mimicked with the memristor under electrical and optical stimulations.More importantly,the device exhibited distinguishable response currents by adjusting 4-bit input electrical/opti-cal signals.A multi-mode reservoir computing(RC)system is constructed with the optoelectronic memristors to emulate human tactile-visual fusion recognition and an accuracy of 98.7%is achieved.The optoelectronic memristor provides potential for developing multi-mode RC system.
基金supported by the National Natural Science Foundation of China(NSFC,no.61804063)the Natural Science Foundation of Jilin Province(nos.YDZJ202401307ZYTS and 20220201070GX)。
文摘Memristive devices based on in-memory computing architectures offer a promising strategy for overcoming the energy bottlenecks inherent in big data systems.However,uncontrolled ion migration at the material level remains a key challenge,compromising device stability and hindering practical applications.Here,we employ a chemical optimization strategy that dynamically induces the precipitation of Ag atoms under applied voltage,creating fixed atomic sites to achieve precise control over ion migration,synergistically enhancing the memory and computing capabilities of the device.Compared to unoptimized samples,the proposed device exhibits an approximately 8-fold improvement in robustness,a 3-fold enhancement in stability,high mechanical endurance,and reliable multilevel data storage capability.We further construct a device array and incorporate an efficient reservoir computing model,achieving handwritten digit recognition with an accuracy of up to 90.81%.In summary,this work proposes a dynamic Ag/Ag^(+)anchoring strategy and demonstrates a memristor-based approach that integrates storage and computation to enable energy-efficient artificial intelligence processing,offering a scalable solution for sustainable intelligence in the big data era.
基金supported by National Key Research and Development Program of China(Grant No.2022YFA1405600)Beijing Natural Science Foundation(Grant No.Z210006)+3 种基金National Natural Science Foundation of China—Young Scientists Fund(Grant No.12104051,62122004)Hong Kong Research Grant Council(Grant Nos.27206321,17205922,17212923 and C1009-22GF)Shenzhen Science and Technology Innovation Commission(SGDX20220530111405040)partially supported by ACCESS—AI Chip Center for Emerging Smart Systems,sponsored by Innovation and Technology Fund(ITF),Hong Kong SAR。
文摘Recurrent neural networks(RNNs)have proven to be indispensable for processing sequential and temporal data,with extensive applications in language modeling,text generation,machine translation,and time-series forecasting.Despite their versatility,RNNs are frequently beset by significant training expenses and slow convergence times,which impinge upon their deployment in edge AI applications.Reservoir computing(RC),a specialized RNN variant,is attracting increased attention as a cost-effective alternative for processing temporal and sequential data at the edge.RC’s distinctive advantage stems from its compatibility with emerging memristive hardware,which leverages the energy efficiency and reduced footprint of analog in-memory and in-sensor computing,offering a streamlined and energy-efficient solution.This review offers a comprehensive explanation of RC’s underlying principles,fabrication processes,and surveys recent progress in nano-memristive device based RC systems from the viewpoints of in-memory and in-sensor RC function.It covers a spectrum of memristive device,from established oxide-based memristive device to cutting-edge material science developments,providing readers with a lucid understanding of RC’s hardware implementation and fostering innovative designs for in-sensor RC systems.Lastly,we identify prevailing challenges and suggest viable solutions,paving the way for future advancements in in-sensor RC technology.
基金Project supported by the National Natural Science Foundation of China(Grant No.12275165)XGW was also supported by the Fundamental Research Funds for the Central Universities(Grant No.GK202202003).
文摘Model-free,data-driven prediction of chaotic motions is a long-standing challenge in nonlinear science.Stimulated by the recent progress in machine learning,considerable attention has been given to the inference of chaos by the technique of reservoir computing(RC).In particular,by incorporating a parameter-control channel into the standard RC,it is demonstrated that the machine is able to not only replicate the dynamics of the training states,but also infer new dynamics not included in the training set.The new machine-learning scheme,termed parameter-aware RC,opens up new avenues for data-based analysis of chaotic systems,and holds promise for predicting and controlling many real-world complex systems.Here,using typical chaotic systems as examples,we give a comprehensive introduction to this powerful machine-learning technique,including the algorithm,the implementation,the performance,and the open questions calling for further studies.
基金the National Natural Science Foundation of China(Grant Nos.62375171,62305208,62205189,62105203,and 62405182)the Shanghai Pujiang Program(Grant No.22PJ1407500)+4 种基金the Oceanic Interdisciplinary Program of Shanghai Jiao Tong University(SJTU)(Grant No.SL2022ZD205)the National Key Research and Development Program of China(Grant No.2022YFC2806600)the Science Foundation of Donghai Laboratory(Grant Nos.DH-2022KF01001 and DH-2022KF01005)the Startup Fund for Young Faculty at SJTU(Grant No.24X010500120)the Science and Technology Commission of Shanghai Municipality(Grant No.20DZ2220400).
文摘Optical reservoir computing(ORC)offers advantages,such as high computational speed,low power consumption,and high training speed,so it has become a competitive candidate for time series analysis in recent years.The current ORC employs single-dimensional encoding for computation,which limits input resolution and introduces extraneous information due to interactions between optical dimensions during propagation,thus constraining performance.Here,we propose complex-value encoding-based optoelectronic reservoir computing(CE-ORC),in which the amplitude and phase of the input optical field are both modulated to improve the input resolution and prevent the influence of extraneous information on computation.In addition,scale factors in the amplitude encoding can fine-tune the optical reservoir dynamics for better performance.We built a CE-ORC processing unit with an iteration rate of up to∼1.2 kHz using high-speed communication interfaces and field programmable gate arrays(FPGAs)and demonstrated the excellent performance of CE-ORC in two time series prediction tasks.In comparison with the conventional ORC for the Mackey–Glass task,CE-ORC showed a decrease in normalized mean square error by∼75%.Furthermore,we applied this method in a weather time series analysis and effectively predicted the temperature and humidity within a range of 24 h.
基金Project supported by the National Natural Science Foundation of China (Grant Nos. U20A20227,62076208, and 62076207)Chongqing Talent Plan “Contract System” Project (Grant No. CQYC20210302257)+3 种基金National Key Laboratory of Smart Vehicle Safety Technology Open Fund Project (Grant No. IVSTSKL-202309)the Chongqing Technology Innovation and Application Development Special Major Project (Grant No. CSTB2023TIAD-STX0020)College of Artificial Intelligence, Southwest UniversityState Key Laboratory of Intelligent Vehicle Safety Technology
文摘Neuromorphic computing,inspired by the human brain,uses memristor devices for complex tasks.Recent studies show that self-organizing random nanowires can implement neuromorphic information processing,enabling data analysis.This paper presents a model based on these nanowire networks,with an improved conductance variation profile.We suggest using these networks for temporal information processing via a reservoir computing scheme and propose an efficient data encoding method using voltage pulses.The nanowire network layer generates dynamic behaviors for pulse voltages,allowing time series prediction analysis.Our experiment uses a double stochastic nanowire network architecture for processing multiple input signals,outperforming traditional reservoir computing in terms of fewer nodes,enriched dynamics and improved prediction accuracy.Experimental results confirm the high accuracy of this architecture on multiple real-time series datasets,making neuromorphic nanowire networks promising for physical implementation of reservoir computing.
基金supported in part by the Open Research Fund of Joint Laboratory on Cyberspace Security,China Southern Power Grid(Grant No.CSS2022KF03)the Science and Technology Planning Project of Guangzhou,China(GrantNo.202201010388)the Fundamental Research Funds for the Central Universities.
文摘The blockchain-empowered Internet of Vehicles(IoV)enables various services and achieves data security and privacy,significantly advancing modern vehicle systems.However,the increased frequency of data transmission and complex network connections among nodes also make them more susceptible to adversarial attacks.As a result,an efficient intrusion detection system(IDS)becomes crucial for securing the IoV environment.Existing IDSs based on convolutional neural networks(CNN)often suffer from high training time and storage requirements.In this paper,we propose a lightweight IDS solution to protect IoV against both intra-vehicle and external threats.Our approach achieves superior performance,as demonstrated by key metrics such as accuracy and precision.Specifically,our method achieves accuracy rates ranging from 99.08% to 100% on the Car-Hacking dataset,with a remarkably short training time.
基金supported by National Key Research and Development Program of China (2023YFB4402500,2023YFB4402400)National Natural Science Foundation of China (621041314)+1 种基金Natural Science Foundation of Shandong Province (ZR2023LZH007)Program of Qilu Young Scholars of Shandong University.
文摘Graphene oxide,as a 2D material with nanometer thickness,offers ultra-high mobility,chaotic properties,and low cost.These make graphene oxide memristors beneficial for reservoir computing(RC)networks.In this study,continuous-wave(CW)laser processing is used to reduce chaotic graphene oxide(CGO)films,resulting in the non-volatile storage capability based on the reduced chaotic graphene oxide(rCGO)films.Laser power significantly impacts the characteristics of the rCGO memristor.Material characterization indicates that laser radiation can effectively reduce the oxygen content in CGO films.With optimized laser power,the rCGO memristor achieves a large ratio at 18 mW laser power.Benefiting from the short-term mem-ory characteristics,distinct conductive states are achieved,which are further utilized to construct RC networks.With a third con-trol probe,the rCGO memristor can express rich reservoir states,demonstrating accuracy in predicting the Hénon map with an NRMSE below 0.3.These findings provide the potential for developing flexible RC networks based on graphene oxide memris-tors via laser processing.
基金supported by Swiss National Science Foundation(SNF)projects LION,ERC SMARTIES and Institut Universitaire de France.H.W.acknowledges China Scholarship Council and National Natural Science Foundation of China(623B2064 and 62275137)J.H.acknowledges SNF fellowship(P2ELP2_199825)+3 种基金Y.B.acknowledges the support from Basic Science Research Program through the National Research Foundation of Korea(NRF)funded by the Ministry of Education(2022R1A6A3A03072108)European Union’s Horizon Europe research and innovation program(N.101105899)Q.L.acknowledges National Natural Science Foundation of China(62275137)the Tsinghua University(Department of Precision Instrument)-North Laser Research Institute Co.,Ltd Joint Research Center for Advanced Laser Technology(20244910194).
文摘Artificial neural networks with internal dynamics exhibit remarkable capability in processing information.Reservoir computing(RC)is a canonical example that features rich computing expressivity and compatibility with physical implementations for enhanced efficiency.Recently,a new RC paradigm known as next generation reservoir computing(NGRC)further improves expressivity but compromises its physical openness,posing challenges for realizations in physical systems.Here we demonstrate optical NGRC with computations performed by light scattering through disordered media.In contrast to conventional optical RC implementations,we directly and solely drive our optical reservoir with time-delayed inputs.Much like digital NGRC that relies on polynomial features of delayed inputs,our optical reservoir also implicitly generates these polynomial features for desired functionalities.By leveraging the domain knowledge of the reservoir inputs,we show that the optical NGRC not only predicts the short-term dynamics of the low-dimensional Lorenz63 and large-scale Kuramoto-Sivashinsky chaotic time series,but also replicates their long-term ergodic properties.Optical NGRC shows superiority in shorter training length and fewer hyperparameters compared to conventional optical RC based on scattering media,while achieving better forecasting performance.Our optical NGRC framework may inspire the realization of NGRC in other physical RC systems,new applications beyond time-series processing,and the development of deep and parallel architectures broadly.
基金the National Natural Science Foundation of China(Grant No.62075168)Guang Dong Basic and Applied Basic Research Foundation(Grant No.2020A1515011088)Special Project in Key Fields of Guangdong Provincial Department of Education of China(Grant No.2020ZDZX3052 and 2019KZDZX1025)。
文摘We utilize three parallel reservoir computers using semiconductor lasers with optical feedback and light injection to model radar probe signals with delays.Three radar probe signals are generated by driving lasers constructed by a threeelement laser array with self-feedback.The response lasers are implemented also by a three-element lase array with both delay-time feedback and optical injection,which are utilized as nonlinear nodes to realize the reservoirs.We show that each delayed radar probe signal can be predicted well and to synchronize with its corresponding trained reservoir,even when parameter mismatches exist between the response laser array and the driving laser array.Based on this,the three synchronous probe signals are utilized for ranging to three targets,respectively,using Hilbert transform.It is demonstrated that the relative errors for ranging can be very small and less than 0.6%.Our findings show that optical reservoir computing provides an effective way for applications of target ranging.
基金National Research Foundation of Korea(NRF),Grant/Award Numbers:2021M3F3A2A01037738,RS-2023-00262880Korea Institute of Science and Technology(KIST),Grant/Award Number:2E32960。
文摘Memristors have been emerging as promising candidates for computing systems in post-Moore applications,particularly electrochemical metallizationbased memristors,which are poised to play a crucial role in neuromorphic computing and machine learning.These devices are favored for their high integration density,low power consumption,rapid switching speed,and significant on/off ratio.Despite advancements in various materials,achieving adequate electrical performance—characterized by threshold switching(TS)behavior,spontaneous reset,and low off-state resistance—remains challenging due to the limitations in conductance filament control within the nanoscale resistive switching layer.In this study,we introduce an efficient method to control the ZrO_(2) crystallinity for tunable volatility memristor by establishing the filament paths through a simple thermal treatment process in a single oxide layer.The effect of ZrO_(2) crystallinity to create localized filament paths for enhancing Ag migration and improving TS behavior is also investigated.In contrast to its amorphous counterpart,crystallized ZrO_(2) volatile memristor,treated by rapid thermal annealing,demonstrates a steep switching slope(0.21 mV dec^(–1)),a high resistance state(25 GΩ),and forming-free characteristics.The superior volatile performance is attributed to localized conductive filaments along lowenergy pathways,such as dislocations and grain boundaries.By coupling with enhanced volatile switching behavior,we believe that the volatility is finely tuned to function as short-term memory for reservoir computing,making it particularly well-suited for tasks such as audio and image recognition.
基金National Key Research and Development Program of China,Grant/Award Number:2021YFA0717900National Natural Science Foundation of China,Grant/Award Numbers:62471251,62288102,22275098,62405144+1 种基金Basic Research Program of Jiangsu,Grant/Award Numbers:BK20240033,BK20243057Jiangsu Funding Program for Excellent Postdoctoral Talent,Grant/Award Number:2022ZB402。
文摘Physical reservoir computing(PRC)offers an effective computing paradigm for spatiotemporal information processing with low training costs.Achieving controllable regulation over the temporal dynamics of devices to meet the computational demands of each physical layer is a key challenge for realizing highperformance PRC chips.Here,we proposed a homogeneously integrated all-PRC with tunable temporal dynamics.Utilizing the modulation effect of oxygen vacancies on the energy barrier of the pentacene/ZnO interface,shortterm memory,and long-term memory switching characteristics have been achieved within the same device structure.Furthermore,by altering the gate voltage,the reservoir exhibited a broad range ratio of temporal characteristics(>10^(2)),which provides the potential to map information with different temporal characteristics.Inspired by the process of encoding and reconstructing spatiotemporal information in the human visual system,a biomimetic obstacle recognition system has been constructed to assist visually impaired individuals in walking,demonstrating excellent accuracy in obstacle types(100%)and distances(97.2%)recognition.This work offers a promising avenue for the development of an integrated PRC system with multi-timescale information processing capability.
基金supported by the the Innovation Program of Shanghai Municipal Education Commission(No.2021-01-07-00-07-E00096)the National Natural Science Foundation of China(Nos.62074111 and 62374115)the National Key Research and Development Program of China(No.2022YFB3203502).
文摘Artificial visual sensors(AVSs)with bio-inspired sensing and neuromorphic signal processing are essential for next-generation intelligent systems.Conventional optoelectronic devices employed in AVSs operate discretely in terms of sensing,processing,and memorization,and not ideal for applications necessitating shape deformation to achieve wide fields-of-view and deep depths-of-field.Here,we present stretchable artificial visual sensors(S-AVS)capable of concurrently sensing and processing optical signals while adapting to shape deformations.Specifically,these S-AVSs use a stretchable transistor structure with a meticulously engineered photosensitive semiconductor layer,comprising an organic semiconductor,thermoplastic elastomer,and cesium lead bromide quantum dots(CsPbBr_(3) QDs).They exhibit synaptic behaviors such as excitatory postsynaptic current(EPSC)and paired-pulse facilitation(PPF)under optical signals,maintaining functionality under 30%strain and repeated stretching.The nonlinear response and fading memory effect support in-sensor reservoir computing,achieving image recognition accuracies of 97.46%and 97.1%at 0%and 30%strain,respectively.
基金supported by the National Key R&D Plan“Nano Frontier”Key Special Project(Grant No.2021YFA1200502)Cultivation Projects of National Major R&D Project(Grant No.92164109)+13 种基金the National Natural Science Foundation of China(Grant Nos.61874158,62004056,and 62104058)the Special Project of Strategic Leading Science and Technology of Chinese Academy of Sciences(Grant No.XDB44000000-7)Key R&D Plan Projects in Hebei Province(Grant No.22311101D)Hebei Basic Research Special Key Project(Grant No.F2021201045)the Support Program for the Top Young Talents of Hebei Province(Grant No.70280011807)the Supporting Plan for 100 Excellent Innovative Talents in Colleges and Universities of Hebei Province(Grant No.SLRC2019018)the Interdisciplinary Research Program of Natural Science of Hebei University(No.DXK202101)the Institute of Life Sciences and Green Development(No.521100311)the Natural Science Foundation of Hebei Province(Nos.F2022201054 and F2021201022)the Outstanding Young Scientific Research and Innovation Team of Hebei University(Grant No.605020521001)the Special Support Funds for National High Level Talents(Grant No.041500120001)the Advanced Talents Incubation Program of the Hebei University(Grant Nos.521000981426,521100221071,and 521000981363)the Science and Technology Project of Hebei Education Department(Grant Nos.QN2020178 and QN2021026)Postgraduate's Innovation Fund Project of Hebei Province(CXZZBS2024004).
文摘The artificial intelligence era has witnessed a surge of demand in detection and recognition of biometric information,with applications from financial services to information security.However,the physical separation of sensing,memory,and computational units in traditional biometric systems introduces severe decision latency and operational power consumption.Herein,an in-sensor reservoir computing(RC)system based on MoTe_(2)/BaTiO_(3)optical synapses is proposed to detect and recognize the faces and fingerprints information.In optical operation mode,the device exhibits low energy consumption of 41.2 pJ,long retention time of 3×10^(4)s,high endurance of 10^(4)switching cycles,and multifunctional sensing-memory-computing visual simulations.The light intensity-dependent optical sensing and multilevel optical storage properties are exploited to achieve sunburned eye simulation and image memory functions.These nonlinear,multi-state,short-term storage,and long-term memory characteristics make MoTe_(2)/BaTiO_(3)optical synapses a suitable reservoir layer and readout layer,with short-term properties to project complicated input features into high-dimensional output features,and long-term properties to be used as a readout layer,thus further building an in-sensor RC system for face and fingerprint recognition.Under the 40%Gaussian noise environment,the system achieves 91.73%recognition accuracy for face and 97.50%for fingerprint images,and experimental verification is carried out,which shows potential in practical applications.These results provide a strategy for constructing a high-performance in-sensor RC system for high-accuracy biometric identification.
基金supported in part by the National Research Foundation of Korea(NRF)grant funded by the Ministry of Science and ICT(RS-2024-00356939 and RS-2024-00405691).
文摘In this study,TiN/NbO_(x)/Pt memristor devices with short-term memory(STM)and self-rectifying characteristics are used for reservoir computing.The STM characteristics of the device are detected using direct current sweep and pulse transients.The self-rectifying characteristics of the device can be explained by the work function differences between the TiN and Pt electrodes.Furthermore,neural network simulations were conducted for pattern recognition accuracy when the conductance was used as the synaptic weight.The emulation of synaptic memory and forgetfulness by short-term memory effects are demonstrated using paired-pulse facilitation and excitatory postsynaptic potential.The efficient training reservoir computing consisted of all 16 states(4-bit)in the memristor device as a physical reservoir and the artificial neural network simulation as a readout layer and yielded a pattern recognition accuracy of 92.34%for the modified National Institute of Standards and Technology dataset.Finally,it is found that STM and long-term memory in the device coexist by adjusting the intensity of pulse stimulation.
基金supported by USDA/NIFA Award 2022-38821-37338(Project No.TEXXQRD9908).
文摘In this study,we examined plant health prediction through the Normalized Difference Vegetation Index(NDVI)calculated from satellite image derived reflectance values in the near-infrared and red spectra.The problem is formulated as a temporal data prediction problem.Using MODIS/Terra Vegetation Indices 16-Day L3 Global 250 m SIN Grid V061 dataset,we designed and implemented Reservoir Computing(RC)models and transformer-based models including pretrained language model,and compared the prediction performance of these models to traditional machine learning and deep learning methods such as Nonlinear Regression,Decision Tree,Convolutional Neural Network(CNN),Long Short-Term Memory(LSTM)network,and DLinear.It is observed that the DLinear/LSTM model showed exceptional predictive accuracy,while the pretrained RC model significantly enhanced traditional RC model forecasts.Additionally,Frozen Pretrained Transformer(FPT),a pretrained language model,showed superior performance in predicting specific NDVI values(most often peak or lowest NDVI),suggesting its effectiveness in precise temporal predictions.Furthermore,transformer-based models,specifically PatchTST and FPT,demonstrated substantial mean squared error reductions,particularly in limited data scenarios(1%,5%,15%and 50%sample sizes),indicating their robustness in precise NDVI temporal predictions when data is limited.The findings in this study demonstrated the effectiveness of emerging machine learning techniques such as reservoir computing and pretrained language model for remote sensing and their contributions in precision agriculture.
基金supported by National Natural Science Foundation of China(No.12272230)Shanghai Pilot Program for Basic Research-Shanghai Jiao Tong University(No.21TQ1400202).
文摘Real-time prediction of ship motions is crucial for ensuring the safety of offshore activities.In this study,we investigate the performance of the reservoir computing(RC)model in predicting the motions of a ship sailing in irregular waves,comparing it with the long short-term memory(LSTM),bidirectional LSTM(BiLSTM),and gated recurrent unit(GRU)networks.The model tests are carried out in a towing tank to generate the datasets for training and testing the machine learning models.First,we explore the performance of machine learning models trained solely on motion data.It is found that the RC model outperforms the L STM,BiL STM,and GRU networks in both accuracy and efficiency for predicting ship motions.Besides,we investigate the performance of the RC model trained using the historical motion and wave elevation data.It is shown that,compared with the RC model trained solely on motion data,the RC model trained on the motion and wave elevation data can significantly improve the motion prediction accuracy.This study validates the effectiveness and efficiency of the RC model in ship motion prediction during sailing and highlights the utility of wave elevation data in enhancing the RC model’s prediction accuracy.
基金supported by the National Natural Science Foundation of China(Grant Nos.11574057 and 12172093)the Guangdong Basic and Applied Basic Research Foundation(Grant No.2021A1515012607).
文摘Recently, with the emergence of ChatGPT, the field of artificial intelligence has garnered widespread attention from various sectors of society. Reservoir Computing (RC) is a neuromorphic computing algorithm used to analyze time-series data. Unlike traditional artificial neural networks that require the weight values of all nodes in the trained network, RC only needs to train the readout layer. This makes the training process faster and more efficient, and it has been used in various applications, including speech recognition, image classification, and control systems. Its flexibility and efficiency make it a popular choice for processing large amounts of complex data. A recent research trend is to develop physical RC, which utilizes the nonlinear dynamic and short-term memory properties of physical systems (photonic modules, spintronic devices, memristors, etc.) to construct a fixed random neural network structure for processing input data to reduce computing time and energy. In this paper, we introduced the recent development of memristors and demonstrated the remarkable data processing capability of RC systems based on memristors. Not only do they possess excellent data processing ability comparable to digital RC systems, but they also have lower energy consumption and greater robustness. Finally, we discussed the development prospects and challenges faced by memristors-based RC systems.
基金supported by Guangdong Basic and Applied Basic Research Foundation(No.2022A1515011272)the National Natural Science Foundation of China(Nos.61904208,62104091,52273246)+2 种基金Guangdong Natural Science Foundation(No.2022A1515011064)Young Innovative Talent Project Research Program(No.2021KQNCX077)Shenzhen Science and Technology Program(Nos.JCYJ20190807155411277,JCYJ20220530115204009).
文摘Reservoir computing(RC)is an energy-efficient computational framework with low training cost and high efficiency in processing spatiotemporal information.The state-of-the-art fully memristor-based hardware RC system suffers from bottlenecks in the computation efficiencies and accuracy due to the limited temporal tunability in the volatile memristor for the reservoir layer and the nonlinearity in the nonvolatile memristor for the readout layer.Additionally,integrating different types of memristors brings fabrication and integration complexities.To overcome the challenges,a multifunctional multi-terminal electrolyte-gated transistor(MTEGT)that combines both electrostatic and electrochemical doping mechanisms is proposed in this work,integrating both widely tunable volatile dynamics with high temporal tunable range of 10^(2) and nonvolatile memory properties with high long-term potentiation/long-term depression(LTP/LTD)linearity into a single device.An ion-controlled physical RC system fully implemented with only one type of MTEGT is constructed for image recognition using the volatile dynamics for the reservoir and nonvolatility for the readout layer.Moreover,an ultralow normalized mean square error of 0.002 is achieved in a time series prediction task.It is believed that the MTEGT would underlie next-generation neuromorphic computing systems with low hardware costs and high computational performance.
基金National Natural Science Foundation of China(62171305,62405206,62004135,62001317,62111530301)Natural Science Foundation of Jiangsu Province(BK20240778,BK20241917)+3 种基金State Key Laboratory of Advanced Optical Communication Systems and Networks,China(2023GZKF08)China Postdoctoral Science Foundation(2024M752314)Postdoctoral Fellowship Program of CPSF(GZC20231883)Innovative and Entrepreneurial Talent Program of Jiangsu Province(JSSCRC2021527).
文摘Photonic platforms are gradually emerging as a promising option to encounter the ever-growing demand for artificial intelligence,among which photonic time-delay reservoir computing(TDRC)is widely anticipated.While such a computing paradigm can only employ a single photonic device as the nonlinear node for data processing,the performance highly relies on the fading memory provided by the delay feedback loop(FL),which sets a restriction on the extensibility of physical implementation,especially for highly integrated chips.Here,we present a simplified photonic scheme for more flexible parameter configurations leveraging the designed quasi-convolution coding(QC),which completely gets rid of the dependence on FL.Unlike delay-based TDRC,encoded data in QC-based RC(QRC)enables temporal feature extraction,facilitating augmented memory capabilities.Thus,our proposed QRC is enabled to deal with time-related tasks or sequential data without the implementation of FL.Furthermore,we can implement this hardware with a low-power,easily integrable vertical-cavity surface-emitting laser for high-performance parallel processing.We illustrate the concept validation through simulation and experimental comparison of QRC and TDRC,wherein the simpler-structured QRC outperforms across various benchmark tasks.Our results may underscore an auspicious solution for the hardware implementation of deep neural networks.
