60 results about "Reservoir computing" patented technology

The invention relates to an AI processor and method based on storage and calculation integration, three-dimensional integration and operator separation. The AI processor comprises a storage layer; the calculation layer and the storage layer are stacked in the vertical direction through a three-dimensional integrated connection structure, and a three-dimensional integrated high-speed channel is generated and used for executing calculation tasks in a large language model; the standardized memory interface is used for being connected with an external main control chip; the calculation task comprises a pre-filling stage and a decoding stage; the scheduling module configures the main control chip to interact data with the storage layer through the standardized memory interface so as to execute the pre-filling stage; the scheduling module configures the computing layer to interact data with the storage layer through the three-dimensional integrated high-speed channel so as to execute the decoding stage, the pre-filling stage is processed by utilizing the large computing power advantage of a main control chip, and the decoding stage is processed by utilizing the three-dimensional stacked high-bandwidth advantage, so that accurate matching of the computing power and the bandwidth is realized; and the large model reasoning efficiency is obviously improved.

The invention belongs to the technical field of reservoir calculation, and relates to a multi-dimensional pulse reservoir calculation method and system based on a semiconductor laser. The multi-dimensional pulse reservoir calculation method comprises the following steps: encoding a signal to be processed to generate an original optical signal; injecting the original optical signal into a semiconductor laser, and collecting a spike pulse optical signal containing to-be-processed signal feature information generated by the semiconductor laser under excitation of the original optical signal; performing photoelectric conversion on the spike pulse optical signal to obtain a time domain signal; amplitude features, quantity features and time position features of spike pulses in the time domain signals are extracted, and amplitude feature virtual nodes, quantity feature virtual nodes and time position feature virtual nodes are constructed; splicing the amplitude feature virtual node, the quantity feature virtual node and the time position feature virtual node to obtain a reserve pool state vector of an extended dimension; and obtaining an output signal of the multi-dimensional pulse reservoir calculation system based on the reservoir state vector of the extended dimension.

Quantum reservoir computation is provided. A first feature vector is determined from input data. A plurality of qubits is configured in an initial configuration according to the first feature vector, wherein a detuning, Rabi frequency, phase, and / or position of each of the plurality of qubits is determined by a respective one of the values of the first feature vector. The plurality of qubits is evolved for a first time. The plurality of qubits is measured to obtain first measurements after the first time. The plurality of qubits is returned to the initial configuration. The plurality of qubits is evolved for a second time. The plurality of qubits is measured to obtain second measurements after the second time. A second feature vector is determined from the first and second measurements. The second feature vector is provided to a decoder and a characteristic of the input data is obtained therefrom.

The invention belongs to the technical field of Internet of Things. The invention provides a large-scale infrastructure network link dynamic prediction method based on nonlinear reserve pool calculation. According to the embodiment of the invention, by combining nonlinear reserve pool calculation and regularization regression technologies, the dynamic, efficient and accurate prediction of a complex network link is realized, and the method is particularly suitable for state inference and stability analysis of a key link in an infrastructure network. A reserve pool calculation framework is adopted, and the core advantage of the method is that only the linear weight of an output layer needs to be trained, and the internal connection of a huge reserve pool is kept random and fixed. A large amount of iterative computation and GPU resources required by back propagation are avoided, and the training complexity and the time cost are remarkably reduced. A Tikhonov regularization item is introduced, so that the overfitting problem under limited training data or noise interference is effectively prevented, and the generalization ability and prediction stability of the model are improved.

A method for manufacturing a reservoir computing apparatus, related to artificial intelligence. The method comprises: step a), providing a bottom electrode layer, a dielectric layer, a resistive switching layer, and a top electrode layer based on the above-listed sequence on a substrate to obtain a to-be-annealed reservoir computing apparatus; and step b), annealing the to-be-annealed reservoir computing apparatus to obtain the reservoir computing apparatus, where a temperature of the annealing ranges from 300° C. to 700° C., and duration of the annealing duration ranges from 30s to 100s. The manufactured reservoir computing apparatus is subject to rapid annealing, which redistributes defects, forms a more stable film, and introduces a ferroelectric O-phase into the film. The rapid annealing reduces power consumption and improves computing accuracy effectively.

Disclosed in the present application are a reservoir computing network optimization method and a related apparatus. The method comprises: sampling an input signal to obtain a sampling signal; performing quantization processing on the sampling signal by means of at least two kinds of quantization modes, so as to obtain at least two kinds of digital signals, values of elements in different digital signals being different; inputting voltage pulses corresponding to the elements in the different digital signals into reservoirs constructed by different quantities of virtual nodes, so as to extract signal features of the input signal in different quantization modes by the different reservoirs. By quantizing signals in different modes and inputting same into reservoirs constructed by different quantities of virtual nodes, the richness of internal states of the reservoirs can be improved, thereby further improving the signal identification accuracy of a reservoir system.

The invention discloses a time delay reserve pool calculation method based on dispersion orthogonal polarized light feedback VCSEL. An adopted time delay RC system comprises a tunable laser, a Mach-Zehnder modulator, a VCSEL, an optical isolator, an optical coupler, a polarization controller, a variable optical attenuator, a chirp fiber Bragg grating and a photoelectric detector. A signal of the input layer is modulated by a Mach-Zehnder modulator and then is injected into an X polarization component of the VCSEL of the reserve pool layer; emitted light of the VCSEL is divided into two paths after passing through the optical circulator, one path is reflected back to the VCSEL by the chirp fiber bragg grating after being subjected to cross-polarization rotation through the polarization controller, and a reserve pool layer of the time delay RC system is constructed; one path is transmitted to the output layer and is converted into an electric signal through a photoelectric detector. According to the method, the time delay characteristic can be further inhibited, so that generation of harmful resonance is further inhibited, and the method has stronger nonlinear characteristic and better calculation performance.

This associative memory device comprises: a classification vector input data setting unit (1) that sets the same classification vector in a fixed time length as a first input vector; a time-series signal output data setting unit (2) that sets a vector composed of values at each time of a time-series signal in the time length as a first output vector; a first reservoir learning / calculation unit (3) that performs learning by reservoir computing in which a specific classification vector among a plurality of different classification vectors is associated with a specific time-series signal among a plurality of different time-series signals such that the classification vector becomes an input and the time-series signal becomes an output, and calculates a first recursive neural circuit that associates the first input vector with the first output vector; and a first reservoir circuit storage unit (4) that stores the first recursive neural circuit.

In reservoir computing, this enables calculations based on more past input information. [Solution] An information processing device that trains a model to estimate the correct output based on input has a model that includes three layers: an input layer, an intermediate layer that outputs an output value corresponding to the input value input from the input layer based on its internal state, and an output layer that outputs a value based on the output value output from the intermediate layer. In the intermediate layer, a reservoir layer, which is a collection of multiple nonlinear nodes that each perform nonlinear operations, and a linear node layer, which is a collection of multiple linear nodes that each perform linear operations, are connected in parallel to the input layer.

The application belongs to the technical field of reservoir computing, and relates to a multi-dimensional pulse reservoir computing method and system based on a semiconductor laser. The multi-dimensional pulse reservoir computing method comprises the following steps: encoding a to-be-processed signal to generate an original optical signal; injecting the original optical signal into a semiconductor laser, and collecting a spike pulse optical signal containing characteristic information of the to-be-processed signal generated by the semiconductor laser under the excitation of the original optical signal; photoelectrically converting the spike pulse optical signal to obtain a time-domain signal; extracting amplitude characteristics, quantity characteristics and time position characteristics of the spike pulse in the time-domain signal, and constructing amplitude characteristic virtual nodes, quantity characteristic virtual nodes and time position characteristic virtual nodes; splicing the amplitude characteristic virtual nodes, the quantity characteristic virtual nodes and the time position characteristic virtual nodes to obtain an extended-dimension reservoir state vector; and obtaining an output signal of the multi-dimensional pulse reservoir computing system based on the extended-dimension reservoir state vector.

The invention relates to a signal recovery method, system and device based on a space-time interconnection photoelectric reservoir computing architecture and a medium, and the method comprises the steps: constructing a photoelectric reservoir network based on small time delay feedback: introducing one path of a modulation optical signal into a time delay feedback loop, and forming a photoelectric oscillator; the total delay of the time delay feedback loop is divided into a plurality of time slots at equal intervals, each time slot serves as a virtual node, and a time division multiplexing reservoir state matrix is constructed in a time domain; sampling an output signal of the photoelectric oscillator, and performing serial-parallel conversion to output K paths of spatial parallel optical signals; inputting the spatial parallel optical signals into an integrated space photon processing platform, and performing product operation of a reservoir state matrix and an output weight matrix; and receiving the optical signal output by the integrated space photon processing platform in parallel and converting the optical signal into an electric signal to obtain a prediction output result of the target signal. Compared with the prior art, the system has the advantages of high speed, low power consumption and high expansibility.

The invention provides a reservoir calculation method based on rare earth doped nanocrystals. The reservoir calculation method comprises the following steps: acquiring an original digital image and converting the original digital image into a binary vector set; modulating the binary vector set into a pulse sequence set through time multiplexing coding; inputting the pulse sequence into a reservoir formed by three layers of core-shell-shell structure rare earth doped nanocrystals, and generating a corresponding luminescence response curve set through nonlinear dynamic interaction of the three layers of core-shell-shell structure rare earth doped nanocrystals; extracting features based on the curve set to form a reservoir state vector set; and finally, training and classifying the state vector set through a linear layer to obtain an image classification result. According to the reservoir calculation method based on the rare earth doped nanocrystals, through the synergistic effect of the physical characteristics of the rare earth doped nanocrystals and time multiplexing coding, a single reservoir replaces a traditional complex electronic network, coding, calculation and feature extraction are completed in an optical domain, the algorithm complexity and the training cost are remarkably reduced, and the calculation efficiency is improved. And efficient image classification is realized.

The application relates to a discrete dislocation dynamics acceleration simulation method based on reservoir computing, which effectively reduces the high computing cost caused by the global time step limit and the long-range interaction of dislocation elastic force in traditional dislocation dynamics simulation by replacing the node motion speed calculation in discrete dislocation dynamics with a trained reservoir computing model. The virtual node mechanism is innovatively proposed to solve the dimension mismatch problem caused by the dynamic change of the number of nodes in the dislocation topology evolution process, and adaptive discretization prediction is realized. The prediction error accumulation is prevented by regularly inserting the real traditional dislocation dynamics simulation calculation result in the prediction sequence, and the stability of long-term simulation is ensured. The acceleration scheme significantly reduces the computing time complexity from exponential to linear while maintaining the physical accuracy, providing a feasible technical path for efficient simulation of large-scale three-dimensional complex dislocation network evolution.

The invention relates to a database operation method and device for function calculation, computer equipment, a computer readable storage medium and a computer program product. The method applied to any function computing node in a function computing cluster comprises the steps that a computing layer in a current function computing node receives a function computing request, wherein the function computing request comprises an object identifier and a function identifier; if the data of the object identifier is stored in the storage layer of the other function computing node, the computing layer forwards the function computing request to the other function computing node; if the data is stored in the storage layer of the current function calculation node, the calculation layer starts the database transaction, the function instance is executed based on the data of the object identifier, and when the function is executed, reading operation is performed on the distributed storage database provided by the storage layer through the database transaction, and data required by writing operation on the distributed storage database is cached; and after the function execution is finished, the database transaction is closed, the cached data is submitted to a storage layer for write operation, and the communication overhead is reduced.

The application belongs to the technical field of neuromorphic computing devices, and particularly relates to a temperature programmable neuromorphic device based on lead sulfide colloidal quantum dots and application. The device comprises an insulating substrate, a planar gap electrode, a lead sulfide colloidal quantum dot photosensitive film and a temperature control module. By setting the working temperature to control the release kinetics of the trap state charge in the photosensitive film, the device has different photocurrent decay characteristics at different temperatures, realizing reversible switching of the fast detection and long-term storage modes. The device can be used for reservoir computing, and realizes time sequence information processing through the historical dependence response to time sequence light pulses. The application solves the problem of fixed and unadjustable response time scale of the existing device, and has the advantages of simple structure, good process compatibility and wide response dynamic range.

The invention relates to a discrete dislocation dynamics acceleration simulation method based on reservoir calculation, and the method comprises the steps: replacing the node movement speed calculation in discrete dislocation dynamics with a trained reservoir calculation model; the high calculation cost caused by global time step length limitation and dislocation elastic force long-range interaction in traditional dislocation dynamics simulation is effectively reduced. A virtual node mechanism is innovatively provided, the problem of dimension mismatching caused by dynamic change of the number of nodes in the dislocation topology evolution process is solved, and self-adaptive discretization prediction is achieved. And real traditional dislocation dynamics simulation calculation results are periodically inserted into the prediction sequence, so that prediction error accumulation is prevented, and the stability of long-term simulation is ensured. According to the acceleration scheme, while the physical accuracy is kept, the calculation is obviously reduced from the index time complexity to the linear time complexity, and a feasible technical path is provided for efficient simulation of large-scale three-dimensional complex dislocation network evolution.

The invention discloses a method for realizing reserve pool calculation based on organoid, which comprises the following steps: acquiring an audio signal, and converting the acquired audio signal into a photoelectric stimulation pulse signal; acquiring a fluorescence signal responding to the photoelectric stimulation pulse signal through the organ-like device; according to the obtained fluorescence signals, high-dimensional feature data are obtained through calculation by using a storage pool; and decoding the high-dimensional feature data to complete identification processing of the audio signal. According to the method, a biological organoid is adopted as a core of a reserve pool, energy consumption is extremely low when the organoid executes perception and cognition tasks depending on the natural storage and calculation fusion characteristic of a biological neural network, organic fusion of data storage and processing is achieved through neural synapses, a large amount of energy consumption of CPU and memory data transmission in a traditional von Neumann architecture is avoided, and the reliability of the von Neumann architecture is improved. And the development requirement of low-power AI hardware is better met, and a thought is provided for developing an efficient and low-cost neuromorphic chip.

The invention particularly relates to a physical reservoir for a magnetic reservoir computing device. The physical reservoir includes a ferromagnetic film including a two-dimensional arrangement of point deformations. The point deformations are dimensioned to function as pinning sites of magnetic domains of the ferromagnetic film. The invention also relates to a magnetic reservoir computing device comprising such a physical reservoir, and methods of operating and manufacturing such a reservoir computing device. The proposed method results in a low power consumption physical reserve that is easy to manufacture.

Disclosed is a synaptic device, a reservoir computing device using the synaptic device, and a reservoir computing method using the reservoir computing device. The synaptic device includes a substrate and a plurality of units cells on the substrate, wherein the unit cells each include a channel layer and a first electrode and second electrode intersecting the channel layer, wherein the first electrode and the second electrode are spaced apart from each other, and define a gap region exposing a portion of the channel layer, and the channel layer includes a 2-dimensional semiconductor material or a 2-dimensional ferroelectric material.

This invention provides a depth-scalable inversion method and system for 3D ground-penetrating radar (GPR) data. The method includes: spatially mapping the 3D GPR volume data of the area to be inverted point by point according to spatial coordinate points based on a 3D reservoir computing network to obtain waveform dynamic features characterizing the electromagnetic response variation law of the underground medium; extracting global spatial features of the 3D GPR volume data based on a convolutional neural network; predicting the target category of the 3D GPR volume data based on the waveform dynamic features and global spatial features; determining the inversion network depth based on the target category; constructing an encoder-decoder inversion network with corresponding layers based on the inversion network depth; using the encoder-decoder inversion network to extract multi-scale spatial features and texture structure features of the 3D GPR volume data; and predicting the 3D distribution of the underground dielectric constant corresponding to the 3D GPR volume data based on the multi-scale spatial features and texture structure features.

The present disclosure provides a reservoir computing system based on memcapacitors. The reservoir computing system based on memcapacitors comprises: an input mask module comprising a mask unit, the mask unit being configured to modulate an amplitude of an input signal and determine a voltage signal proportional to the amplitude of the input signal; a reservoir module comprising reservoir units, each reservoir unit comprising a memcapacitor, each memcapacitor being configured to construct a perisach model based on the memcapacitor, an output end of each perisach model based on the memcapacitor outputting a polarization intensity of the memcapacitor, and the perisach model based on the memcapacitor serving as a node of a reservoir network; and an output module configured to obtain output weights of the reservoir network in a training stage of the reservoir network, multiply the polarization intensity of the memcapacitor with the output weights of the reservoir network in a test stage of the reservoir network, and output a prediction result. By the present disclosure, the reservoir network is constructed by using the memcapacitors, thereby improving the working efficiency of the reservoir computing system and reducing the static power consumption.

The present application belongs to the technical field of reservoir computing, and particularly relates to a method for implementing a large-scale optoelectronic reservoir computing system. The method comprises: performing matrix sparsification connection to form a sparse connection matrix in the form of a lower triangular matrix composed of basic matrix calculation units A and B; then performing rank reduction operation on the sparse connection matrix, so that the product of the original sparse matrix and the input signal is converted into the product form of each basic matrix unit after splitting and the input signal after splitting, and the dimension of each subunit is reduced to 1 / 2 of the original dimension; the above splitting operation is repeated until the splitting reaches the scale supported by the optical chip unit; then the reservoir is trained and tested to obtain a weight matrix calculation prediction value. The multiplication operation shares the same chip, and the multiplication and accumulation operation of a matrix of any scale can be completed by multiplexing the basic scale optical computing chip. The present application achieves ideal effects in the application of communication signal post-equalization, signal recognition, etc.

The invention relates to a reserve pool calculation system and method based on a spin torque nanometer oscillator and a medium, belongs to the field of neuromorphic calculation and hardware acceleration, and adopts the inherent non-linear current-voltage characteristic of the spin torque nanometer oscillator to directly generate a non-linear signal from a linear signal. The generation of a nonlinear part of a feature vector in next-generation reserve pool calculation is realized, and the three problems of feature dimension combination explosion in NG-RC, high calculation overhead caused by a large amount of matrix operation and insufficient multi-scale dynamics capture capability are effectively solved by replacing a traditional polynomial algorithm with a physical law. Self-adaptive frequency domain response is achieved on the hardware level, complex reconfiguration is not needed, and the time sequence processing efficiency can be improved on the premise that the hardware cost is not remarkably increased in combination with low calculation overhead of simulation domain processing.

The application discloses an optical reservoir computing system and method. The system comprises K input layer nonlinear optical elements, J energy storage layer tunable filters, L output layer nonlinear optical elements, S feedback layer tunable filters and R computing logic control units. Nonlinear optical effects are generated under the action of N incident pump light signals, and the properties of the pump light signals, input light signals and feedback light signals are adjusted. The signals are combined and emitted as probe light signals, which are converted into probe electrical signals. Therefore, after the nonlinear optical elements and tunable filters are introduced into the optical reservoir computing network, the basic requirements of the system functions of each layer can be achieved by using a small number of devices. As long as the devices can achieve the functions of the layers, the optical RC network can be realized by using fewer components, thereby improving the utilization degree of each component and the computing performance of the optical RC network.

A reservoir computing system comprises an input system configured to generate an input signal, an optical reservoir configured to receive the input signal from the input system, and an output system configured to generate an output signal based on light received from the optical reservoir. The optical reservoir comprises a plurality of reservoir lasers configured for injection-locked operation and a reservoir randomization element configured to randomly distribute light output by the plurality of reservoir lasers among the plurality of reservoir lasers to contribute to injection locking of the plurality of reservoir lasers.

A reservoir calculation device (10) has: an input layer (11); a reservoir layer (12) that outputs a signal reflecting the signal provided from the input layer (11); and an output layer (13) that derives an output value from a signal output from the reservoir layer (12), in which the input layer (11) has a plurality of nodes (A) (nodes 14-14f) to which a signal reflecting a signal output from another node (A) in one step is supplied, and in a subsequent step, a signal reflecting the supplied signal is supplied to the reservoir layer.

The present application relates to the field of reservoir computing, and particularly relates to a multi-modal dynamic physical reservoir node based on 2T0C single-gate transistor and application thereof. The reservoir node comprises two N-type thin film transistors WT and RT. The drain of WT is connected to a write bit line; the gate of WT is connected to a write word line; the source of WT is connected to the gate of RT and forms a storage node; the source of RT is connected to a read word line; and the drain of RT is connected to a read bit line. The active layer adopts IGZO as a semiconductor material for forming a channel; and a light receiving window corresponding to the active area is provided. In the write-in stage, the illumination time of the light receiving window and the pulse width of the pulse signal input at the gate end are respectively used to represent input data of different dimensions; in the read-out stage, the read-out current output by RBL is used to represent output data. The present application realizes multi-modal feature coupling in a single device, improves the power consumption and delay of the device, overcomes the shortcomings of existing devices, and helps to promote the development of reservoir computing.

The invention relates to the technical field of neuromorphic calculation and brain-like information processing, in particular to a liquid reservoir calculation system with distributed and globally adjustable dynamics, which comprises a liquid storage module, a plurality of reservoir nodes, an input signal application module, an output signal acquisition module, a liquid state regulation and control module and a readout layer module. A plurality of reserve pool nodes are simultaneously located in the same electrolyte liquid environment, the input signal applying module applies a time change electric signal to excite each node to generate a dynamic response, and the output signal acquisition module acquires a dynamic response signal of each node. Because the dynamic response time constants of the nodes are different, the system forms distributed dynamics with multi-time scale characteristics. And the liquid state regulation and control module realizes the adjustability and reconstruction of the overall dynamic behavior of the system under the condition of not changing the physical structure of the node by regulating and controlling the overall parameters of the electrolyte liquid. And the readout layer module processes the dynamic response signal and is used for tasks such as time sequence prediction, pattern recognition or dynamic signal modeling.

This system provides an anomaly detection system that enables non-contact monitoring of internal conditions, is less susceptible to environmental influences, and can identify the location of anomalies in real time. [Solution] An anomaly detection system using electromagnetic wave radar, comprising: a radar signal processing unit that applies range FFT and Doppler FFT to a received IQ signal to generate a range Doppler image; a time series signal generation unit that divides the range Doppler image into a grid and applies an inverse Fourier transform (iFFT) to the signal in each grid region to generate time series waveform data; a feature extraction unit that applies filter bank processing and extracts features using a dynamic time series model including reservoir computing; and an anomaly detection unit that detects anomalies based on the reconstruction error obtained by applying principal component analysis (PCA) to the features.