176 results about "Stochastic gradient descent" patented technology

The invention provides an electromechanical equipment fault prediction method and system based on multi-source information fusion, and the method comprises the steps: collecting operation data, including vibration data, temperature data and current data, during the operation of electromechanical equipment; performing feature extraction on the operation data based on a principal component analysis algorithm to obtain a fusion feature vector; inputting the fusion feature vector into a fault prediction model based on a deep belief network, and outputting a prediction result; wherein the deep belief network adopts a small-batch stochastic gradient descent algorithm combined with an adaptive learning rate adjustment strategy during training; and judging whether the electromechanical equipment has a fault hidden danger or not according to the prediction result. According to the method, the relevance between different types of data is mined, and the defect of low prediction precision is overcome.

The invention discloses a high-elasticity antibacterial yarn production control method and system, and relates to the technical field of textile manufacturing. The method comprises the following steps: acquiring tension, temperature, antibacterial agent distribution and other multi-dimensional state information, and generating a comprehensive performance evaluation index based on a feature projection and gating residual fusion model; the index is compared with target performance, and key influence parameters such as fiber arrangement unevenness and antibacterial agent application distribution density are identified; calling a process response model to generate a parameter adjusting strategy, and driving an adjusting device to adjust process variables such as tension and temperature through a control instruction; and finally, based on a stochastic gradient descent algorithm and in combination with an expert knowledge base, adjusting rules are periodically updated, and performance self-adaptive control is achieved. According to the method, the intelligence and robustness of regulation and control of the elasticity and the antibacterial performance of the yarn are improved, and the method is suitable for industrial production of high-end textiles such as medical yarn and intelligent wearing fabric.

The invention discloses a road crack deep learning segmentation method for a complex scene, and belongs to the technical field of image processing. Firstly, multi-illumination and multi-material road surface images are acquired at high altitude through carrying multi-spectral equipment by an unmanned aerial vehicle, and generalization is improved by adopting adaptive threshold graying, CLAHE illumination equalization and GAN data enhancement. Secondly, deformable convolution, a self-adaptive space attention mechanism and an object context representation module are introduced into the HRNet backbone network, and the problems of irregular fracture shapes and background interference are solved; and finally, class imbalance is relieved by adopting a focus loss function, and robustness is improved by combining stochastic gradient descent and a verification set dynamic weight storage strategy. In the test stage, edge equipment deployment is carried out, a pixel-level segmentation result is output, crack parameters are quantified, and decision support is provided for road maintenance. The method can significantly improve the crack segmentation precision in a complex scene, and especially has an engineering practical advantage in a fine crack and noise interference scene.

The invention discloses a machine olfaction system drift compensation method based on dynamic domain adversarial learning. The method comprises the following steps: step 1, collecting sample data through a machine olfaction system; step 2, constructing a DRDAN, and inputting the sample data into the DRDAN to obtain a predicted gas category and a domain classification label of the sample data; the DRDAN comprises a feature extractor, an integrated gas classifier and a domain discriminator, the integrated gas classifier is connected with the feature extractor, the integrated gas classifier outputs samples and finally predicts gas categories, the domain discriminator is connected with the feature extractor through a gradient inversion layer, and the domain discriminator outputs domain classification labels of sample data; and obtaining an optimal model parameter by minimizing a DRDAN learning objective function, and performing gradient updating through stochastic gradient descent. The method has the advantages that cross-domain joint distribution alignment is achieved, and class distinguishability is improved.

The invention discloses a lumbar disc herniation postoperative recurrence prediction system based on a multi-modal medical image, and belongs to the field of medical images. The lumbar disc herniation postoperative recurrence prediction model based on the multi-modal image is trained by using the lumbar vertebra image set, the feature true value corresponding to each image and the recurrence prediction label corresponding to each patient, and in the training process, model parameters are updated by using a stochastic gradient descent algorithm; and a trained lumbar disc herniation postoperative recurrence prediction model based on the multi-modal image is obtained. According to the method and the system, due to rich image features provided by the multi-modal image, the prediction network trained based on the multi-modal data shows higher accuracy in postoperative recurrence prediction of the lumbar disc herniation.

This specification relates to privacy-preserving model training on tabular data. In some aspects, a method includes receiving, by one or more computing devices, tabular data; serializing the tabular data into a natural language string in a natural language format; combining the natural language string and a prompt as an input to a pretrained large language model (LLM) to generate a predicted result, wherein a set of learned vectors are added into the pretrained LLM for fine-tuning the pre-trained LLM; fine-tuning the pretrained LLM using a differential privacy stochastic gradient descent (SGD) process, wherein fine-tuning the pretrained LLM comprises: determining values of the learned vectors that minimize a difference between the predicted result and the ground truth; receiving a request including test tabular data for a predication task; and generating, in response to the request for the prediction task, a prediction result for the test tabular data using the fine-tuned LLM.

The invention provides a structured feedback risk constraint LQR solving method based on optimal control optimization, and belongs to the technical field of control optimization, and the method comprises the steps: obtaining an initial feedback gain matrix meeting a microgrid communication topology sparsity constraint; a zero-order strategy gradient method is adopted, through an outer layer iteration optimization step and an inner layer sampling estimation sub-step, a gradient direction is estimated by utilizing observation change of a target function value; according to the distributed frequency control method, strategy updating is carried out on the basis of an optimal control algorithm, a sparse feedback gain matrix obtained after N rounds of iteration is output, the sparse feedback gain matrix is directly deployed to a local controller of the micro-grid, and distributed frequency control meeting the risk constraint is achieved. Compared with a classical stochastic gradient descent method, the OCP algorithm obtains a satisfactory optimality gap, the convergence speed is higher, and the stability is also improved through dual redescription of maximum and minimum problems.

Methods, systems, and apparatuses, including computer programs encoded on computer storage media, for training a neural network using differentially private stochastic gradient descent (DP-SGD) with correlated noise. In some implementations, a system determines a correlation matrix by performing an optimization to improve a utility metric that is dependent on a noise multiplier. The system can then train the neural network using the optimized correlation matrix and a privacy-amplifying batching scheme to produce a neural network with high utility while satisfying a data security criterion.

The invention provides a discrete manufacturing production line process decision and optimization method and system based on digital twinning, and relates to the field of production intellectualization and digitalization, and the method mainly comprises the steps: constructing a high-fidelity digital twinning model corresponding to a physical production line through the combination of mechanism modeling and data-driven modeling; establishing a virtual-real consistency evaluation index system, and realizing deviation identification and dynamic consistency maintenance of the digital twinborn model; production disturbance, equipment state change and process deviation information are sensed in real time; a part-process-equipment-quality multi-dimensional correlation model is constructed; an improved stochastic gradient descent algorithm is introduced to carry out dynamic updating and convergence control on intelligent agent strategy network parameters, and a knowledge base self-evolution updating mechanism is constructed; according to the method, dynamic updating and consistency maintaining of the twinborn model are achieved, the dynamic response capability of the digital twinborn model under the dynamic operation condition is remarkably improved, and the systematicness and reusability level of process knowledge are effectively improved.

The invention discloses a semi-supervised radar target identification method based on a hybrid expert network and pseudo label filtering. The method comprises the following steps: S1, carrying out data preprocessing on radar target echoes; s2, constructing a data set X1 with labels and a data set Xu without labels; s3, constructing a hybrid expert network model; s4, constructing a fusion loss function; s5, constructing a semi-supervised model training framework; s6, performing iterative optimization on the fusion loss function of the semi-supervised deep neural network model by using a stochastic gradient descent method in combination with the mixed data set, and finally generating a new semi-supervised deep recognition model Mb; and S7, classifying the test sample set X *: inputting the test sample set X * into the trained semi-supervised depth recognition model to obtain a prediction label to evaluate the performance of the model, and inputting an unknown sample into the model to obtain a prediction result so as to realize automatic classification of radar target echoes.

A computer-implemented method and a distributed computer system for privacy-preserving distributed training of a global neural network model on distributed datasets. The system has data providers communicatively coupled with each having a respective local training dataset and a vector of output labels for training the global model. Further, it has a cryptographic distributed secret key and a corresponding collective cryptographic public key of a multiparty fully homomorphic encryption scheme, with the weights of the global model being encrypted with the collective public key. Each data provider computes and aggregates, for each layer of the global model, encrypted local gradients using the respective local training dataset and output labels, with forward pass and backpropagation using stochastic gradient descent. One data provider homomorphically combines the current local gradients of the data providers into combined local gradients, and updates the weights of the current global model based on the combined local gradients.

A computer-implemented method for training a machine learning model (27) using a training dataset (28) having a set of distributional parameters θ is disclosed. The method comprises selecting (S205) stochastically a subset (28a) from the training dataset (28), calculating a gradient of the subset (28a) by encoding (S210) a cost function representative of the gradient into a quantum circuit, amplifying (S220) the amplitude of the quantum circuit, constructing a likelihood function (S230), and minimising the cost function in a variational quantum circuit to optimise the distributional parameters, extracting the optimised distributional parameters, and entering the optimised distributional parameters into the machine learning model (27).

The invention provides a method and system for detecting small target defects in a paper cup based on deep learning, and relates to the technical field of computer vision, and the method comprises the steps: obtaining a surface image of a to-be-detected paper cup; constructing a paper cup small target defect detection model based on a deep learning algorithm; constructing a loss function of the paper cup small target defect detection model; with minimization of the function value of the loss function as a target, optimizing the small target defect detection model in the paper cup in combination with a back propagation algorithm and an SGD stochastic gradient descent method; and inputting the surface image into the optimized small target defect detection model in the paper cup for detection, and outputting a target defect detection result of the to-be-detected paper cup. According to the invention, all products can be detected in time, the phenomena of missing detection and false detection are avoided, and the production efficiency and the product quality are improved.

The invention discloses an unmanned aerial vehicle small sample target recognition method based on spatial information mining, and aims to solve the problems that an existing small sample method does not fully utilize an image structure in a scene, ignores a semantic relationship between support and query samples and is limited in recognition precision. The core is a query-support transformer framework for unified modeling of global and local structural relationships of samples, the framework comprises a cross-scale interactive feature extractor, a sample transformer and a block transformer module, a task-type mechanism is adopted in the training stage, enhanced features are generated by images through the extractor, the sample transformer constructs a global semantic relationship, and the overall semantic relationship is obtained. The method comprises the following steps: realizing local block-level matching by a block transformer, performing weighted summation on similarity of the two to obtain a matching score, combining weighted sum of comparison loss and cross entropy loss, updating parameters by using momentum stochastic gradient descent, constructing a task based on a trained model in a test stage, extracting features, and fusing global and local similarity to complete classification. And the unmanned aerial vehicle image small sample classification performance is effectively improved.

The invention discloses a federated learning method and system for heterogeneous data of the Internet of Vehicles, and relates to the technical field of intelligent transportation. The method comprises the following steps: a roadside unit sends a current global model and a global control variable to a vehicle participating in training; the vehicle executes local training combined with a client drift correction mechanism through local data and a differential privacy stochastic gradient descent algorithm, and generates local model update; the vehicle calculates a noise multiplier of the next round of training through a personalized self-adaptive differential privacy strategy according to the loss value of the current round of training; the vehicle judges whether the current round of model updating is effective or not based on selective uploading; and if the update is valid, the vehicle uploads the model increment and the local control variable increment to the roadside unit, and the roadside unit updates the global model and the global control variable after aggregation. According to the invention, systematic innovation is carried out from three levels of privacy protection, model optimization and communication strategies, and a solution is provided for constructing efficient, safe and reliable federal learning in an Internet of Vehicles scene.

The invention provides a federal learning optimization method and system based on knowledge distillation and a computer readable storage medium, and the optimization method comprises the following steps: S1, a server initializes model parameters and issues the model parameters to at least two clients; the client receives model parameters and initializes a local model; s2, training a local model by the client through local data, calculating and combining experience loss and distillation loss of the local data, obtaining updated model parameters through stochastic gradient descent, and uploading the updated model parameters to the server for aggregation; wherein the step of calculating the distillation loss comprises setting different distillation corrections for each sample category; and S3, the server side aggregates the model until the model converges. According to the method, the data heterogeneous property of federal learning in practical application is considered, global knowledge is transmitted to the client by utilizing knowledge distillation, the distillation intensity is adaptively adjusted in combination with data distribution of the client, and the problem of global knowledge forgetting caused by data missing is relieved, so that the model precision is effectively improved.

This invention discloses a sub-aperture stitching interferometric measurement device and method for optical freeform surfaces. The device includes a laser interferometer, a variable phase compensator, and a multi-axis motion stage for motion control of the mirror under test. The variable phase compensator consists of two freeform surface mirrors and two wedges, used to achieve phase compensation with a large dynamic range for each sub-aperture. The system automatically adjusts the compensation phase of the sub-apertures using a weighted stochastic gradient descent algorithm and performs in-situ measurement of the compensation phase using a micro-translation misalignment measurement method. The system can realize three measurement modes: full aperture coverage stitching measurement, sub-aperture coverage stitching measurement, and comprehensive measurement. This invention enables high-precision measurement of flexible, complex optical freeform surfaces (such as gull-wing surfaces).

The invention discloses a collaborative filtering recommendation method based on user article scores fused with multi-dimensional evaluation indexes, and the method comprises the following steps: a score data preprocessing stage: inputting a score matrix, optimizing a loss function of BiasSVD by using a stochastic gradient descent method, obtaining parameters required by a BiasSVD score calculation formula, and calculating the score of the user article scores according to the parameters required by the BiasSVD score calculation formula; outputting a complete score data table with enhanced robustness; in the multi-dimensional evaluation index establishment stage, three key indexes are calculated, and the indexes are subjected to normalization calculation to form a multi-dimensional novelty evaluation framework; in the recommendation generation stage, according to the algorithm, a post-processing weighted sorting mode is combined with a multi-dimensional novelty index and user article score data, the user similarity is calculated through cosine similarity, scores of the users on the articles are predicted through a weighted summation method, and a comprehensive recommendation list is generated, so that the problem of data sparsity of a traditional collaborative filtering algorithm is effectively solved; the problems of recommendation result homogenization, insufficient novelty and long tail effect are solved.

The application discloses a kind of multi-camera automatic layout method in multi-vision measurement system, it includes: step S1: initialization camera layout parameter;According to the CAD model information of workpiece to be detected, the initial position of camera is obtained, and then the initial parameters of all cameras are obtained;Step S2: optimization camera initial layout based on simulated annealing algorithm;After obtaining the initial parameters of all cameras, iterative optimization is carried out using simulated annealing algorithm, and the optimal solution satisfying the constraint condition is obtained;Step S3: based on the differentiable adjustment promotion, the measurement accuracy and robustness of three-dimensional reconstruction under the above simulated annealing camera layout are improved.Based on the optimal layout obtained based on simulated annealing, the error back propagation algorithm based on stochastic gradient descent is used, and the Euclidean distance between reconstructed three-dimensional coordinates and CAD model coordinates is used as a loss function to optimize, to obtain a camera layout with better reconstruction robustness.The application has the advantages of high automation, strong layout practicality, good accuracy and robustness of three-dimensional reconstruction, etc.

The application discloses a lining cloth dyeing control method and system based on artificial intelligence, and is used for the control field, and the method comprises the following steps: real-time monitoring of multi-source data in the lining cloth dye vat, capturing the video stream inside the lining cloth dye vat; using a Gaussian mixture variational autoencoder model to extract features from the multi-source data, obtaining multi-source feature data; obtaining the changing moment of the fabric state in the video stream, and extracting the fabric state change feature data according to the observed fabric color change and the heterogeneity of the dye distribution in the video stream; fusion of multi-source feature data and fabric state change feature data; introducing a model predictive control layer, predicting the result to adjust the dyeing parameters in real time; establishing an intelligent feedback mechanism. The Gaussian mixture variational autoencoder model is trained and optimized through the small-batch stochastic gradient descent and back propagation algorithm, important features are learned and captured from the data.

Methods, systems, and apparatus, including computer programs encoded on computer storage media for training a machine learning model. The method includes obtaining a training data set comprising a plurality of training examples; determining i) a stochastic gradient descent step size schedule, ii) a stochastic gradient descent noise schedule, and iii) a stochastic gradient descent batch size schedule, wherein the stochastic gradient descent batch size schedule comprises a sequence of varying batch sizes; and training a machine learning model on the training data set, comprising performing stochastic gradient descent according to the i) stochastic gradient descent step size schedule, ii) stochastic gradient descent noise schedule, and iii) stochastic gradient descent batch size schedule to adjust a machine learning model loss function.

System that features the following: a processing unit that is functionally connected to a memory; an AI (Artificial Intelligence) platform that exchanges data with the processing unit, wherein the AI ​​platform is designed to train a machine learning (ML) model, wherein the AI ​​platform has the following features: a registration manager to register participating entities in a cooperative relationship, to arrange the registered entities in a topology, and to establish a topological data transmission protocol; an encryption manager to generate a public additive homomorphic encryption key, AHE key, and distribute it to each registered entity; an entity manager to control direct local encryption of machine learning model weights of local entities on registered entities using a distributed public AHE key, to selectively aggregate the encrypted local machine learning model weights including distributing the aggregated encrypted weights to one or more other participating entities in the topology, or to support local aggregation on the registered entities according to the topological data transmission protocol; where the encryption manager decrypts an aggregated sum of the encrypted local machine learning model weights with a corresponding private AHE key, and distributes the decrypted aggregated sum to each entity in the topology.

The invention discloses a semi-supervised domain self-adaptive deep forgery detection method, relates to the technical field of forgery detection, and solves the technical problem that a model cannot fully adapt to data distribution of a new domain due to the fact that a small amount of annotated data and a large amount of unannotated data in a target domain are generally difficult to use at the same time in an existing method. The method comprises the following steps: performing multi-batch training on a deep neural network model by adopting samples, wherein each batch of samples comprise a source domain labeled sample, a target domain labeled sample and a target domain unlabeled sample; in the training process, a joint loss function is optimized by adopting stochastic gradient descent, network parameters are iteratively trained, any input image is detected by using a trained Xception model, and the probability that the image is real or forged is output; according to the method, a semi-supervised field adaptive framework is introduced, so that the feature distribution difference between a source domain and a target domain is effectively reduced, and the cross-domain generalization ability is remarkably enhanced.

A trajectory end point prediction method based on double-branch road network pre-training representation comprises the following steps: firstly, processing initial road feature data to obtain features of roads and road connections; and then constructing a road network graph structure, a hypergraph structure and road time dynamic characteristics. Firstly, a multi-hop weighted road network embedded vector is calculated, then a graph node embedded vector is calculated to be adjacent to a hypergraph node embedded vector, and a comparative learning mode is adopted to carry out stochastic gradient descent to optimize parameters; meanwhile, a time dynamic embedding vector is calculated through a Transform structure, and time dynamic prediction and classification loss function optimization model parameters are calculated; and inputting the initial features into the trained graph model, hypergraph model and Transform model to obtain enhanced road network representation, and finally applying the enhanced road network representation to a trajectory end point prediction task. The invention further comprises a system of the track end point prediction method based on the double-branch road network pre-training representation.

The application discloses a kind of based on clustering unsupervised fine-grained image classification model training method and classification method, training method includes: obtaining fine-grained image data;Extract the feature of fine-grained image and carry out normalization processing;Using predetermined clustering method, the normalized feature is clustered, and according to clustering result, corresponding image data is assigned pseudo label;Using the image data with pseudo label, fine-grained image classification model is trained, and the parameter in model is updated using batch stochastic gradient descent algorithm, and the feature center of each cluster is updated with momentum;Clustering and training process are repeated, and the unsupervised fine-grained image classification model of training completion is obtained.The present application can solve the learning degradation and non-convergence problem existing when the existing unsupervised learning method is applied to fine-grained image classification task, and fill the blank of unsupervised fine-grained image classification without available method.

This specification relates to privacy-preserving model training on tabular data. In some aspects, a method includes receiving, by one or more computing devices, tabular data; serializing the tabular data into a natural language string in a natural language format; combining the natural language string and a prompt as an input to a pretrained large language model (LLM) to generate a predicted result, wherein a set of learned vectors are added into the pretrained LLM for fine-tuning the pre-trained LLM; fine-tuning the pretrained LLM using a differential privacy stochastic gradient descent (SGD) process, wherein fine-tuning the pretrained LLM comprises: determining values of the learned vectors that minimize a difference between the predicted result and the ground truth; receiving a request including test tabular data for a predication task; and generating, in response to the request for the prediction task, a prediction result for the test tabular data using the fine-tuned LLM.

This application discloses a design method for an optoelectronic imaging system with laser protection and privacy protection functions, relating to the field of optoelectronic imaging. The method includes: determining an optimized point spread function based on preset point spread distribution characteristics, target energy divergence, and point spread radius using an optical-algorithm joint optimization framework; determining an initial phase distribution based on imaging parameters using the Gerchberg-Saxton algorithm; adjusting the initial phase distribution using a stochastic gradient descent algorithm, guided by the difference in energy divergence of the point spread function, to determine the optimized phase distribution corresponding to the optimized point spread function; and using the optimized phase distribution to load the phase modulation component of the optoelectronic imaging system. This application can achieve high-quality optoelectronic imaging with laser protection and privacy protection capabilities.

The application provides a tire flaw detection domain self-adaptive method based on a migratable Swin Transformer.In the model training stage, after the tire X-ray image is cropped, it is input into the migratable Swin Transformer feature extractor, then the domain discriminator is used for region-level alignment, and the region-based attention weight is provided for sub-domain self-adaption, then the flaw detection result is obtained through the tire flaw detection classifier, and the model is trained by using the stochastic gradient descent method; in the flaw detection stage, the image obtained by the target X-ray machine is first cropped, and then input into the feature extractor and the tire flaw detection classifier obtained in the model training stage, so that the flaw detection result is obtained.The application can solve the field deviation problem existing in the tire flaw detection and improve the flaw detection efficiency.

This invention discloses a production control method and system for high-elasticity antibacterial yarn, relating to the field of textile manufacturing technology. The method includes: collecting multi-dimensional state information such as tension, temperature, and antibacterial agent distribution; generating a comprehensive performance evaluation index based on a feature projection and gated residual fusion model; comparing this index with the target performance to identify key influencing parameters such as fiber arrangement unevenness and antibacterial agent application distribution density; calling a process response model to generate parameter adjustment strategies; driving the adjustment device to adjust process variables such as tension and temperature through control commands; dynamically collecting feedback and correcting the strategy; and finally, periodically updating the adjustment rules based on a stochastic gradient descent algorithm combined with an expert knowledge base to achieve adaptive performance control. This invention improves the intelligence and robustness of yarn elasticity and antibacterial performance regulation, and is suitable for the industrial production of high-end textiles such as medical yarns and smart wearable fabrics.

The invention relates to an interpretable CNN (Convolutional Neural Network) training method and device based on Bernoulli sampling and a medium, and the method comprises the following steps: inputting a picture into a CNN, and obtaining a response feature map of a filter; performing Bernoulli sampling on the response feature map to obtain a binary distribution matrix; calculating a filter average weight matrix of each picture category according to the binarization distribution matrix, and calculating the sum of pairwise differences; calculating the Hadamard product of the distribution vector of the binary distribution matrix and the response feature map to obtain a mask feature map; respectively inputting the response feature map and the mask feature map into a CNN full connection layer to respectively obtain classification prediction probability vectors, and respectively calculating cross entropy loss with a real label; and according to the sum of the pairwise differences and the cross entropy loss, using a stochastic gradient descent method to realize network training, and obtaining an interpretable CNN for image classification. Compared with the prior art, the method has the advantages of high adaptability, high interpretability and the like.