98 results about "Training time" patented technology

This invention relates to an intelligent database performance evaluation method, belonging to the field of database performance evaluation. It addresses the problems of low accuracy, long training times, and inefficient model construction in existing database performance evaluation methods. In the early stages of model training, this invention categorizes multiple variables into frequent and infrequent variables. A linear regression model is used to learn the impact of infrequent variables on database performance. The system parameters of the linear regression model are then input into a second-stage hierarchical machine learning model. Frequent variables are directly input into this model to learn their impact on database performance. The trained hierarchical machine learning model is then used as the database performance evaluation model. This invention is primarily used for evaluating database performance.

The application discloses a model training process-oriented computing power chip hardware Trojan design method, and relates to the field of integrated circuit security.The method is designed in view of the computing architecture of a GPU, and contains a flip-flop, a finite state machine and a load circuit.The flip-flop identifies the typical characteristics of deep learning training by monitoring the arithmetic instruction intensity and the Warp concurrent activity of the GPU runtime; when the characteristics meet a preset threshold, the finite state machine is triggered, so that the hardware Trojan enters an activated state.The load circuit has two types of designs: the first type is a gradient flipping circuit which interferes with the gradient update direction by modifying the sign bit output by a floating point calculation unit, so that the model cannot converge; the second type is a redundant calculation circuit which consumes computing resources by inserting invalid floating point operations, thereby prolonging the training time.The application designs and triggers the hardware Trojan by utilizing the architecture characteristics of the GPU, has high concealment, and can effectively destroy the accuracy and efficiency of a deep learning training task.

This invention provides an energy efficiency optimization method for the large-scale deployment of ultra-reliable low-latency (URLLC) devices, comprising: Step 1: Calculating the short packet collision probability and short packet reception failure probability of a single device, and calculating the packet loss rate of the device based on the calculated short packet collision probability and short packet reception failure probability; Step 2: Calculating the packet loss rate of each device, and grouping devices with similar communication environments into one category based on the calculated packet loss rate; Step 3: Optimizing the energy efficiency of all devices categorized in Step 2 using a deep reinforcement learning method. The beneficial effects of this invention are: 1. The method can effectively reduce the transmission power of sensing devices sending short packets and the number of times the same short packets are repeatedly sent, significantly improving the communication energy efficiency of URLLC devices and extending their battery life; 2. The method of this invention uses a classification method, which significantly shortens the training time of deep reinforcement learning.

The application provides a communication method, device and equipment and a storage medium. The method comprises the following steps: a network device sends a training time delay constraint instruction to a terminal device participating in federated learning; the terminal device receives the training time delay constraint instruction from the network device; and the training time delay constraint instruction is used to indicate the reporting deadline of a model training result. Since the network device can send the training time delay constraint instruction to the terminal device participating in the federated learning, the training time delay constraint instruction is used to indicate the reporting deadline of the model training result, so that in the case that there are two or more terminal devices participating in the federated learning, different terminal devices can upload the model training result according to the training time delay constraint instruction, so as to reduce the time difference of the model training result uploaded by different terminal devices participating in the federated learning, thereby ensuring the overall training time delay of the federated learning, reducing the possibility of late reporting of the terminal device, and helping to reduce the waste of network resources.

The application designs a resource and batch size collaborative configuration method for distributed deep model training tasks based on public cloud. First, the training process of different training modes is analyzed, and the training time is expressed by using parameters such as resources and batch size to establish a training time prediction model. Secondly, considering the influence of resources and batch size on the training loss value and the characteristic that the loss value curve can be approximated as an inverse proportional function, the method uses an inverse proportional function to approximate the loss value convergence curve, and uses resources, batch size and other features that affect the training loss value convergence as input to predict the parameters in the inverse proportional function using a machine learning model to establish a training loss value prediction model. Finally, the method uses the two prediction models above as the constraint conditions for the search to find the resource and batch size collaborative configuration solution that can minimize the training cost. The application can effectively reduce the training cost on the basis of reaching the specified loss value within a limited time.

This paper presents a graph neural network node classification method that integrates meta-learning and mini-batch training, belonging to the field of information technology. First, the method utilizes the METIS algorithm to divide the original large-scale graph data into multiple non-overlapping connected subgraphs. Then, by constructing a hybrid selection mechanism based on label coverage and label entropy, subgraphs with high information content and strong representativeness are selected from the subgraph pool as the meta-learning task. Subsequently, iterative training is performed on the selected subgraphs using the meta-learning framework to capture the general prior features of the graph structure, thereby obtaining a set of initial parameters for the model with rapid adaptability. Finally, these optimized initial parameters are transferred to the mini-batch training stage on the full dataset, guiding the model to achieve rapid convergence through high-quality initialization. On large-scale benchmark datasets, this method significantly reduces the number of iterations required by the model while maintaining the same classification accuracy as current mainstream graph neural network models, thus greatly shortening the overall training time.

This invention discloses a lightweight adaptive optimization method for high-dimensional hyperparameters of convolutional neural networks (CNNs) for non-stationary time-series signal classification. It aims to address the technical challenges of performance degradation in time-series signal classification models and the reliance on expensive real-world evaluations for hyperparameter configuration under non-stationary perturbation scenarios. This method uses a deep convolutional neural network as the core classification carrier, treating the hyperparameter combinations within the deep convolutional neural network as decision variables to be optimized. With robust classification error rate, computational complexity, and training time as core optimization objectives, it constructs a closed-loop collaborative optimization mechanism of "perception-evaluation-decision" and utilizes a meta-learning dual-branch convolutional polynomial surrogate-assisted evolutionary algorithm (MetaDCP-SAEA) to achieve efficient configuration. This method requires no manual intervention; the convolutional neural network used for classifying non-stationary time-series signals can automatically search for the optimal hyperparameter combination. In simulated non-stationary noise environments, the reduction in classification accuracy can be controlled within 9.17%. It is suitable for robust classification scenarios of non-stationary time-series signals such as industrial IoT monitoring and medical signal diagnosis. It helps to lower the engineering threshold of artificial intelligence technology, promotes the large-scale application of automatic machine learning in complex environments, and has broad market prospects and application value.

This application provides a method, apparatus, device, and storage medium for estimating model training time, relating to the field of computer technology. The method includes: determining an operator stream of the model to be trained based on its architecture; the operator stream includes multiple computation operators; each computation operator has its own parameter configuration indicating computational cost; determining multiple communication operators located in the operator stream based on the parallel strategy of the model to be trained; each communication operator has its own parameter configuration indicating communication cost; and determining the computational time of each computation operator and the communication time of each communication operator in each training round in the operator stream through simulation, based on the hardware configuration of the cluster running the model to be trained and the amount of sample data of the model to be trained, thereby obtaining the training time of the model to be trained. Using the above method, the training time of the model to be trained is accurately estimated based on the computational and communication times, improving the accuracy of model training time estimation.

The application discloses a federated continual learning cross-layer optimization method for a UAV relay network, and aims at the problems of easy occurrence of catastrophic forgetting of a model and high system time delay in a streaming task training scene.The application constructs a system architecture comprising a base station, a UAV and a plurality of ground clients; a task stability index is obtained by calculating the gradient similarity between a current task and a historical task of a client, and a system efficiency index is obtained by combining the client computing time delay and the communication time delay, so as to jointly select a target client participating in aggregation; in order to anchor historical knowledge, local compensation updating is performed at the client side based on the historical task gradient, and post-aggregation compensation correction is performed at the base station side based on the historical global gradient; and a cross-layer optimization model about the client computing frequency, bandwidth allocation, UAV trajectory and relay strategy is further established to minimize the maximum completion time delay of the system. The application can improve the model learning precision, reduce catastrophic forgetting and reduce the training time delay.

Embodiments of the present disclosure provide a method, apparatus and electronic device for training a recommendation model. The method can include, in response to receiving a data deletion request of a user, determining data requested to be deleted in original data. The method can also include obtaining remaining data for the user based on the data requested to be deleted. Furthermore, the method can further include training the recommendation model using the remaining data. Through the technical solutions of the embodiments of the present disclosure, the long model training time and large amount of computing overhead caused by retraining the recommendation model can be avoided, and the model updating time is shortened. In addition, since the training of the recommendation model forgets the data expected to be deleted by the user, the performance of the recommendation model is improved, the recommendation result is more likely to hit the user's preference, and thus the user experience is improved.

The application discloses a visual rich-text page restoration method based on an attention network, which comprises the following steps: inputting a document image into a trained document image rotation angle classification network to obtain the angle at which the document image needs to be rotated and correct the document image, and then using a projection correction algorithm to perform secondary correction on the document image; performing element detection on the document image through a page analysis network and performing corresponding processing to obtain element content corresponding to each element; using a plurality of deep learning algorithm network models connected in series to restore the document image into an editable document; and adding a contrast denoising training strategy in the page analysis network training to improve the accuracy of page analysis, because the plurality of network models are connected in series, according to the rule of the weakest link, the effect of page restoration will be affected by the page analysis model, therefore, the addition of the contrast denoising strategy can improve the accuracy of the network, promote the convergence of the network and shorten the training time.

Systems and methods are provided for performing anomaly detection. An example method includes, in a training phase, performing time series decomposition on training time series data to extract residuals of the training time series data, the residuals including a plurality of data points of the training time series data, using unsupervised anomaly detection models, identifying and labeling anomalous data points from among the plurality of data points contained in the residuals, based on outputs from the ensemble of unsupervised models including the labeled anomalous data points, obtaining a combined output indicating the labeled anomalous data points, and, using the combined output, training supervised anomaly detection models to detect anomalies in inference time series data In an inference phase, the method includes, using the trained ensemble of supervised anomaly detection models, on real-time, inference time series data.

Systems and methods for a deep learning reconstruction network with computationally light and efficient CNN architecture and a training strategy tailored to image reconstruction of dynamic multi-coil GRASP MRI. The configuration of the size of the network used in training time may be adjusted, which allows for higher accelerations and different hardware constraints.

The present application relates to a kind of image classification methods based on separable convolution block and spatial reduction attention mechanism, belong to image classification field.Crossover depth separable convolution and improved spatial reduction attention mechanism are added to PVT model, reduce model training time, and while reducing attention calculation, the original information of feature map is not lost basically at the same time amount of calculation.Crossover depth separable convolution block embedding and spatial reduction attention mechanism based network model is built, including block embedding module, linear projection module, position information embedding module and spatial reduction attention mechanism module;Image classification is carried out to improve the calculation rate when image classification and preserve original boundary information, so as to achieve the overall improvement effect.The present application effectively improves the problems such as huge model calculation and image boundary information loss, reduces the amount of calculation of model and improves the model classification performance.

A bearing device includes a bearing and a vibration sensor for measuring the vibration of the bearing, the bearing having an inner ring and an outer ring capable of rotating concentrically relative to each other. The bearing device further includes: - a first determining component (10) for determining the value of at least a first statistical parameter equal to the Hjorth complexity parameters (P1, P2, P3, P4, P5, P6); - a modeling component (11) for modeling the value of at least the first statistical parameter using a normal distribution; - a second determining component (12) for determining a detection threshold (Sd) at least based on a normal distribution during a training period; - a third determining component (13) for determining a score (Sc) during normal operation of the machine (1) at least based on the first value of the Hjorth complexity parameter and the normal distribution modeled on the value of the first statistical parameter; and a comparison component (14) for determining a failure of the bearing (4) based on the detection threshold (Sd) and the score (Sc).

This invention relates to the field of scene text segmentation, specifically a scene text segmentation method based on an improved SAM visual segmentation large model. Based on the SAM visual large model, this invention extracts text content perception features through an image content perception module and text edge perception features through a text edge perception module. Furthermore, the text feature fusion module extracts and calculates text edge perception feature maps, which are then added to the vectors requiring attention calculation before each self-attention calculation in the SAM encoder. This improves the accuracy of SAM in text segmentation and shortens the model training time while maintaining generalization.

The application discloses a photovoltaic panel damage detection method and system based on an open vocabulary, and a medium, solves the problems of high model training cost and long training time in the prior art, has the beneficial effects of reducing training cost and improving recognition accuracy, and the specific scheme is as follows: a photovoltaic panel damage detection method based on an open vocabulary, comprising constructing a training data set; performing knowledge distillation pre-training, using the pre-trained open vocabulary target detection model as the teacher model, using the detection model to be trained as the student model, distilling the intermediate layer features and class prediction distribution of the teacher model respectively, and the student model learns basic semantic understanding ability through the first pre-training data set; freezing the knowledge distillation module of the student model, collecting images of photovoltaic panels to be detected and preprocessing, and inputting the fused multi-scale feature map and the updated text embedding vector into the detection output module.

The application discloses a kind of based on instance image label's correctable package level classification model training method and equipment, the steps of this method are as follows: obtaining panoramic pathology scanning image and corresponding package level label;Image pre-processing and instance image segmentation are carried out to panoramic pathology scanning image;Instance feature package is obtained by using self-supervised learning model to instance image feature extraction;Package level classification model is trained by the package level label and instance feature package obtained;High contribution degree instance image training instance image classifier is screened;The prediction result of package level classification model is corrected using the output result of instance image classifier.The application is suitable for a variety of formats panoramic pathology scanning image classification tasks, can reduce package level classification model repeated training time and instance image level classification error, improve the accuracy and robustness of package level classification model.

This application provides a training method, apparatus, device, storage medium, and computer program product for a conversion prediction model, applicable to various conversion prediction scenarios such as cloud technology, artificial intelligence, smart transportation, and vehicle-mounted systems. The method includes: acquiring recommended information samples with a conversion waiting time of a first duration up to the current training time and conversion tags for the recommended information samples; extracting first sample features of the recommended information samples based on the conversion prediction model to be trained, and extracting second sample features of the recommended information samples based on a second feature extraction module in an auxiliary training model, wherein the auxiliary training model is trained with a second duration shorter than the first duration; predicting a first predicted conversion probability corresponding to the sample fusion feature of the first and second sample features based on the conversion prediction model to be trained; and training the conversion prediction model to be trained based on the difference between the first predicted conversion probability and the conversion tag, thereby obtaining the conversion prediction model. This application can improve the accuracy of the model.

Large training times incurred during the process of self-learning of ML models in digital twins are debilitating and can adversely affect the functioning of industrial plants. Embodiments of the present disclosure provide a method and system for accelerated self-learning using application agnostic meta learner trained using optimal set of meta features selected from classification meta features, regression meta features, and domain meta features based on a domain-meta-feature-taxonomy created for a plurality of industrial plants across a plurality of domains. Optimal feature selection is enabled using ML, DL that provides static feature selection, while Q-learning based approach is disclosed that enables dynamic feature selection. Q-learning based approach has two implementations, static and dynamic reward. In the dynamic reward based approach the reward of choosing an action depends on current state (selected meta features), and reward for selecting the next meta feature, depends on the meta features that have already been selected.

This invention discloses a pipelined parallel training method for multimodal models on heterogeneous edge devices. The method includes: constructing a pipelined parallel training architecture for multimodal models on heterogeneous edge devices and addressing the optimization problem of training multimodal models on heterogeneous edge devices; performing modality grouping and device grouping based on an improved genetic algorithm to obtain the optimal modality and device grouping scheme; performing stage division based on a dynamic programming algorithm and calculating the training time of modality grouping as a chromosome fitness evaluation in the genetic algorithm; allocating fusion stages according to the stage division scheme of each modality and adaptively selecting training micro-batches, ultimately obtaining a parallel training scheme for multimodal models on heterogeneous edge devices with the minimum overall training time. This method can fully utilize the parallel branching structure of multimodal models to achieve efficient training of multimodal models on heterogeneous edge devices and optimize the overall training time.

The application provides a node detection method, device, equipment, storage medium and computer program product; the method comprises: for each physical node used for executing a distributed training task, acquiring a logical comparison group corresponding to the physical node, the logical comparison group comprising a plurality of first training nodes; for each training step, collecting the training time consumption of each first training node at the training step, and calculating a first average value based on the training time consumption at the training step; based on the training time consumption of each first training node at the training step, screening at least one second training node from the plurality of first training nodes; based on the training time consumption of the at least one second training node at the training step, calculating a second average value, and performing a difference operation on the first average value and the second average value to obtain a difference index of the training step; based on the difference indexes of a plurality of training steps, detecting the type of the second training node to obtain the node type of the second training node.

This invention discloses an automatic parallel optimization method for large-scale model training in hybrid heterogeneous clusters. This invention requires only real-time collection of a small number of system performance parameters to achieve efficient prediction of training time costs in hybrid heterogeneous cluster environments, while comprehensively considering factors such as GPU performance differences, communication overhead, and resource allocation. This invention formalizes the parallel strategy and parameter optimization problem for large-scale model training in hybrid heterogeneous clusters into a constrained optimization problem and establishes a bandwidth-aware training cost estimation model based on a theoretical model. It decomposes and estimates the time cost during training item by item, achieving rapid and accurate prediction of training costs under different heterogeneous configurations. This invention also designs a parallel strategy search and parameter optimization method based on intelligent optimization algorithms, which significantly reduces the traditional search space size while ensuring near-optimal solutions, improving search efficiency and reducing additional overhead.

This invention provides a model update method and apparatus, belonging to the field of machine learning technology. The model update method includes: after training a product recognition model using a first training dataset, calculating the uncertainty and typical representativeness of each sample data in the first training dataset, wherein the typical representativeness is the cosine distance between the sample data and a first vector, and the first vector is the standard vector corresponding to the category to which the sample data belongs; selecting a first dataset from the first training dataset based on the uncertainty and typical representativeness of each sample data; obtaining a second training dataset; and retraining the product recognition model using the first dataset and the second training dataset. The technical solution of this invention can reduce the training time for model updates.

The application proposes an efficient communication privacy-enhanced federated edge learning method based on device probability access, aiming to protect user sensitive data while improving the communication and training efficiency of the federated edge learning system. Specifically, the method considers a privacy federated edge learning framework based on device probability access in a wireless digital communication scenario, and characterizes the influence of device probability access and differential privacy noise on the convergence of the federated edge learning system and the enhancement effect on differential privacy protection through theoretical analysis method. On this basis, the application proposes a system overall training time minimization problem containing differential privacy restriction, and jointly optimizes the design of device access probability and differential privacy noise to reduce the dependence of the federated edge learning system on differential privacy noise, while accelerating the training process of the federated edge learning system.

A computer-implemented method for training a machine learning system (60), wherein the method includes the following steps: a. obtaining data from multiple training time series (x... j The first training time series (x) of the input signal is determined in ) j ) and the first training time series (x) j The expected training output signal (t) corresponds to j ), wherein the desired training output signal (t) j ) represents the first training time series (x) i a. Determine the expected classification and / or expected regression results; b. Determine the first adversarial example (x i ), wherein the first adversarial example (x) i ) is the first training time series (x) j The superposition of the first adversarial perturbation and the determined first adversarial perturbation, wherein the first noise value of the first adversarial perturbation is not greater than a pre-given threshold, wherein the pre-given threshold is based on the training time series (x). i c. The noise value determined by the machine learning system (60); i Determine the training output signal (y) i ); d. Adapt at least one parameter of the machine learning system (60) according to the gradient of the loss value, wherein the loss value characterizes the desired training output signal (t). j ) and the determined training output signal (y i () deviation.