18 results about "Reservoir computing" patented technology

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 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 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.

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 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.

A reservoir computing method (700) and related system (100) are disclosed. The reservoir computing system includes at least one non-linear computing node (103) with a computing node MOSFET (113), a drive circuit (110) coupled with the at least one non-linear computing node (103), and a readout unit (104) for acquiring an output sequence associated with the at least one non-linear computing node (103). The MOSFET has charge trapping sites positioned in a gate dielectric that exhibit a bias temperature instability when subjected to a voltage stress and exhibit a threshold voltage recovery after removal of the voltage stress. The drive circuit is configured to apply an input pulse and a readout pulse to a gate of the MOSFET. The readout unit (104) is configured to detect a current flowing through a channel region of the MOSFET when the drive circuit is applying the readout pulse. The readout pulse has a smaller voltage amplitude than the input pulse.

The application relates to a memristor reserve pool computing circuit and a prediction method for real-time epilepsy prediction, and belongs to the technical field of electroencephalogram signal processing. The circuit comprises a plurality of levels of series-connected reserve pool computing architectures. Each level of architecture is used for receiving a multichannel EEG signal or a multichannel binary coded signal, and after high-dimensional feature mapping, nonlinear time feature extraction and feature fusion are sequentially performed on the multichannel EEG signal or the multichannel binary coded signal by a mask circuit, a reserve pool module based on a volatile memristor and a multiply-accumulate circuit comprising a cross array based on a non-volatile memristor in the architecture, the parallel output road fusion signal is output to a feature binaryzation circuit in the architecture, signal binaryzation processing is performed on the parallel output road fusion signal, a multichannel binary coded signal is output in parallel as an input of a next level of architecture, and finally, a binary coded signal output by a last level of architecture is output as an epilepsy prediction result. The application provides a hardware efficient solution for real-time low-power epilepsy seizure prediction.

A reservoir computing method and related system. The method comprises providing a pulse wave representation of a reservoir input and a MOSFET-based compute node of a reservoir computing system. A body terminal of the MOSFET is configured to apply a bias signal to the body region. The MOSFET is operable in floating mode in the absence of the bias signal. The MOSFET displays a history-dependent threshold voltage when driven by input pulses in floating mode. The method further includes removing the bias signal from the body terminal; applying input pulses to a gate terminal of the MOSFET, thus causing history-dependent variations in the threshold voltage; and acquiring an output sequence related to the compute node while the MOSFET threshold voltage is varying, by repeatedly applying readout pulses to the gate terminal of the MOSFET and simultaneously detecting a current through a channel region of the MOSFET.

This invention discloses a room-temperature mode-selective physical reservoir computation method, belonging to the field of neuromorphic computing. The method is based on an artificially synthesized antiferromagnetic skyrmion spring oscillator, which electrically selects different intrinsic dynamic modes to adapt to different computational tasks: an in-plane alternating current drives a large-amplitude oscillation mode, providing strong nonlinearity to optimize signal conversion tasks; an out-of-plane alternating magnetic field drives a breathing mode, providing strong short-term memory to optimize time series prediction tasks. The device integrates fully electrically driven, multi-channel parallel readout, voltage-controlled magnetic anisotropy stabilization, and planar microcoil excitation units, achieving full on-chip integration of mode selection, signal processing, and stability control. This invention solves the problems of nonlinearity and memory coupling, poor task adaptability, and insufficient room-temperature stability in physical reservoirs, achieving fast, high-precision, and reconfigurable processing of multiple tasks at room temperature using a single device.

This invention discloses a centrifugal heat pump control method based on machine self-learning, belonging to the field of machine learning technology. The method includes the following steps: Step 1, synchronously sampling the output signals of multiple dynamic pressure sensors evenly distributed circumferentially at the inlet of the centrifugal heat pump compressor; Step 2, sending the input observation vector into the reservoir computing network of the edge controller, which consists of an input mapping layer, a reservoir layer, and an output mapping layer, to obtain the surge margin change rate prediction value by performing a first-order difference on the surge margin prediction values ​​of adjacent control cycles; Step 3, under the constraint of the feasible range of guide vane angle limited by the surge margin setpoint, determining the guide vane angle command value of the current control cycle by combining the pre-stored centrifugal heat pump efficiency characteristic diagram, and outputting it to the guide vane actuator. This invention improves the overall operational stability and economic efficiency of the centrifugal heat pump over a wide operating range.

Finger angle information is estimated from electromyographic data with less computation. [Solution] The finger angle estimation system 1 comprises an electromyographic signal acquisition unit 11 attached to the surface of the skin to acquire electromyographic signals, a finger angle information acquisition unit 12 that acquires finger joint angle information, and an estimation unit 13 that performs machine learning using the electromyographic signals acquired by the electromyographic signal acquisition unit 11 and the finger joint angle information acquired by the finger angle information acquisition unit 12 as training data to generate a model that estimates the finger joint angle when new electromyographic information is provided. The estimation unit 13 performs machine learning using RC (reservoir computing).

The application discloses a human motion rapid recognition method based on parallel time delay optical reserve pool calculation, and specifically comprises the following steps: after data compression preprocessing, the feature data of 5 to 7 key frames is extracted from the preprocessed data by combining sampling and key frame screening technology, and the splicing mode of the state sequence is adjusted from different regions of a static image to different frames of a related video; subsequently, multiple reserve pools are introduced to realize the parallel input of multiple frames of data, and a parallel semiconductor laser array is introduced inside a single reserve pool; in the output layer, all virtual node states of the reserve pool laser are combined for training and testing, and the output weight is calculated by a ridge regression algorithm. While maintaining the high bandwidth advantage of optical calculation, the application significantly improves the system calculation efficiency, and provides a new solution for real-time image recognition, dynamic visual tasks and the like.

An example operation includes one or more of receiving sensor data from at least one sensor installed on a vehicle, generating a plurality of sequences of data points corresponding to a plurality of different attributes associated with the vehicle, respectively, based on execution of a reservoir computing model on an iteration of sensor data, determining an attribute associated with the vehicle which is a priority based on execution of an artificial intelligence (AI) model on the plurality of sequences of data points, and adjusting a state of the reservoir computing model to prioritize sensor data of the attribute when generating subsequent sequences of data points

This invention relates to a reconfigurable gadolinium oxide memristor based on electrode engineering, its fabrication method, and a reservoir computing system. The reconfigurable gadolinium oxide memristor comprises a bottom electrode, a gadolinium oxide layer, and a top electrode stacked sequentially. In this invention, gadolinium oxide is used as the resistive switching material, which possesses both excellent ion migration capabilities and spontaneous relaxation characteristics. Therefore, a reconfigurable gadolinium oxide memristor with both volatile and non-volatile properties is developed based on electrode engineering to meet the functional requirements of the reservoir and readout layers in reservoir computing. In reservoir computing, the volatile Al / Gd₂O₃ / Pt memristor acts as the physical reservoir to achieve nonlinear mapping of the input signal; the non-volatile Ta / Gd₂O₃ / Pt memristor serves as the readout network, enabling parallel computation and identification, effectively solving the problems of slow data processing speed, poor real-time performance, and high integration difficulty in existing memristor-based reservoir computing systems.

This invention discloses a high-speed optical reservoir computing system and testing method for time-series signal processing, belonging to the field of optical reservoir computing technology. The method includes the following steps: filtering and denoising the dataset using a computer, signal normalization, feature enhancement, time window extraction, data segmentation, and data balancing; importing the processed data into an arbitrary waveform generator; the signal from the arbitrary waveform generator is led out by wires, passes through a T-bias, and is input into the saturable absorption region through a GSG probe; the pulse signal is then amplified through the gain region; the output surface of the gain region is connected to a photodetector via fiber optic coupling, converting the optical signal into an electrical signal which is then imported into an oscilloscope; and the output weight matrix between the output vector and the corresponding label vectors of the input vector is fitted using linear regression methods such as ridge regression. This invention enables ultra-high-speed processing of large-volume time-series signals, such as electrocardiogram signals, significantly reducing the energy consumption of existing processing systems and increasing processing speed.