94 results about "Unlabelled data" patented technology

One embodiment of the present invention sets forth a technique for curating a data sample set. The technique includes determining one or more data sampling criteria based on a sampling objective for a data sample set associated with the machine learning model. The technique also includes selecting, from a set of unlabeled data samples, at least one data sample to be labeled and added to a data sample set associated with the machine learning model based on the one or more data sampling criteria. The technique also includes, for each selected data sample, supplementing the data sample set with the selected data sample and at least one association with a label.

Methods and systems for training a reinforcement learning model using training data generated using an unsupervised model. In some aspects, the system processes a first unlabeled dataset using an unsupervised model to generate a first set of labels associated with statistical properties of the first unlabeled dataset. The system generates a labeled training dataset using the first set of labels and the first unlabeled dataset. The system uses the labeled training dataset to train a reinforcement learning model to identify abnormalities and changes to statistical distributions within data. The system uses the reinforcement learning model to process a second unlabeled dataset to generate a second set of labels associated with statistical properties of the second unlabeled dataset.

Broadly speaking, the present techniques provide an automatic way of classifying data items within an environment (e.g. a business, workplace, organisation, etc.). This is advantageous over existing techniques which require manual classification of data items, which is time consuming in environments where hundreds of new data items may be generated in a day or week. The present techniques use an embedding machine learning, ML, model and an LLM to automatically determine the relevant classification label(s) for an unlabelled data item.

Apparatuses, systems, and techniques generating one or more cluster performance evaluation metrics that allow for evaluation of the performance of an unsupervised natural language processing clustering algorithms to be used with unlabeled data. At least one embodiment pertains to methods of generating one or more cluster performance evaluation metrics based, at least in part, on one or more vectors generated by one or more neural networks to indicate a relationship among members of one or more clusters of data generated using the one or more data clustering algorithms, according to various novel techniques described herein.

In some implementations, the techniques may include receiving an accuracy target for one or more machine learning models. In addition, the techniques may include training the models on a labeled training set of labeled data. The techniques may include, until the accuracy of the models satisfies the accuracy target: sampling, a set of unlabeled data to obtain a random training set of unlabeled data; labeling the random training set of unlabeled data using the models to produce a pseudo labeled training set; correcting the labels on a random subset of the pseudo labeled training set; training the models on the labeled training set, the corrected random subset, and the pseudo labeled training set; and evaluating the accuracy of the models using an evaluation set of labeled data. The one or more models can be deployed based at least in part on the models satisfying the accuracy target.

The invention is suitable for the technical field of medical image segmentation, and provides a semi-supervised segmentation method based on multi-modal teacher-student consistency learning, which comprises the following steps: constructing a teacher-double student model framework which comprises a multi-modal teacher model and two independent single-modal student models with different learning conditions, the two student models use segmentation networks of the same structure to respectively process images of two different modalities; in the data input and training stage, data with labels train a student model through real labels, and data without labels are trained through false labels generated by a teacher model; in the training process, the consistency prediction between the teacher model and the student model and between the two student models is ensured. According to the method, the problem of overfitting caused by insufficient annotation data is effectively relieved. In an actual medical scene with limited annotation data, the method can achieve a reliable segmentation result only by means of fewer labels, so as to relieve the pressure of medical conditions.

The invention discloses an uncertain knowledge graph reasoning method based on semi-supervised confidence distribution learning. The method comprises the following steps: converting triple confidence in uncertain knowledge graph training data into confidence distribution; learning embedding of the uncertainty knowledge graph on the marked data and the pseudo-marked data generated by the pseudo-marked data generator at the same time by using a relation learner based on confidence distribution learning; generating a high-quality pseudo-confidence distribution label for the unmarked data by using a pseudo-marked data generator; iteratively training a relation learner based on confidence distribution learning and a pseudo-mark data generator by utilizing element self-training until the relation learner and the pseudo-mark data generator converge; and transmitting data to be complemented into the trained relationship learner based on confidence distribution learning for reasoning to realize uncertainty knowledge graph complementation. According to the method, the supervision information of a small amount of confidence or no confidence in the marked data can be captured, and the method is suitable for the scene of unbalanced confidence distribution of the triple of the uncertainty knowledge graph.

The invention relates to an Internet of Vehicles intrusion detection method, system and device based on a federal auto-encoder. The method comprises the following steps: performing format conversion on received CAN data through a client to obtain a grayscale image; and marking the grayscale image according to the timestamp of the grayscale image and the attack mode, uploading the marked data block as a training sample data set to a server, inputting the unmarked data block to a convolutional auto-encoder model of a corresponding client, carrying out a plurality of rounds of local unsupervised learning training, and updating the model. And quantifying the weight of the model after updating the model, so that the server inputs the training sample data set into the model for global aggregation by adopting a FedAvg algorithm. And updating the aggregated convolutional auto-encoder model to reconstruct a supervised learning system so as to detect the intrusion of CAN data in different clients in the Internet of vehicles. By adopting the method, the Internet of Vehicles intrusion detection precision can be improved, and the communication overhead can be greatly reduced.

A method for automatically identifying emission sources in a source apportionment process of pollutants is provided, which relates to the field of air pollution prevention and control. The method includes: integrating measured source spectrum data and factor spectrum data to generate a labeled data set and an unlabeled data set, respectively; preprocessing the labeled data set to generate a continuous labeled data set; constructing a tree classification model based on the continuous labeled data set; optimizing the tree classification model to determine the optimized tree classification model; coupling the optimized tree classification model and a pseudo-labeling algorithm to generate an integrated model based on the unlabeled data set to automatically identify factor profiles in the unlabeled data set; and determining types of the emission sources based on the factor profiles. The factor profiles can be automatically identified, so that types of emission sources can be quickly determined.

The present teaching relates to content categorization. Supervised training data and unlabeled data clusters are used to generate augmented training data. Each unlabeled data cluster includes data samples with varying features. Weakly labeled training data is created based on supervised training data and the unlabeled data clusters with data samples therein with cluster labels via consistent self-training so that a labeled data sample in the supervised training data and a data sample in the weakly labeled training data with the same label have varying characteristics. Augmented training data is created from the supervised and the weakly labeled training data and is used to train a robust content categorization model via machine learning.

Embodiments of the present disclosure relate to artificial intelligence (AI) / machine learning (ML) model updating. In an aspect, a network device receives an AI / ML model and a first dataset. The first dataset comprises a first set of data samples associated with a first set of labels. The network device obtains a second dataset based on a plurality of unlabeled data samples, the AI / ML model, and a ratio of a number of labels indicative of a line of sight (LOS) path to a number of labels indicative of a non-line of sight (NLOS) path among the first set of labels. The network device updates at least one model parameter of the AI / ML model based on the second dataset. As provided in the present disclosure, a higher LOS / NLOS classification accuracy can be provided by the updated AI / ML model.

A non-transitory computer-readable recording medium stores an active learning program for causing a computer to execute a process including: predicting, based on a second machine learning model trained by using a set of a plurality of pieces of data and a prediction error of a first machine learning model for each of the plurality of pieces of data as training data, a prediction error of the first machine learning model for each of a plurality of pieces of unlabeled data; generating labeled data by assigning a correct answer label to unlabeled data selected from the plurality of pieces of unlabeled data, based on the predicted prediction error; and retraining the first machine learning model by using the generated labeled data.

Broadly speaking, the present techniques provide an automatic way of classifying data items within an environment (e.g. a business, workplace, organisation, etc.), and applying data management policies based on the classifications. This is advantageous over existing techniques which require manual classification of data items, which is time consuming in environments where hundreds of new data items may be generated in a day or week. The present techniques use an embedding machine learning, ML, model to automatically determine the relevant classification label(s) for an unlabelled data item, which is then used to select and apply the relevant data management policy(ies).

The method is oriented to actual scenes of rolling bearings with scarce marks in cross-equipment and cross-working conditions, and solves the problems of instable precision and negative migration caused by domain migration under small sample and semi-supervised conditions. The invention provides a cross-domain transfer learning method of domain sensing data-meta initialization-teacher and student semi-supervision-curriculum type alignment-physical consistency-online updating. According to the method, order resampling, event anchoring slicing and robust scaling are matched with a self-supervision health index and order-preserving calibration to generate a soft / interval weak label; unlabeled is absorbed through consistency learning and uncertainty gating, and domain invariant representation is obtained according to low / middle / high level step-by-step alignment; negative migration is inhibited by combining monotone / integral consistency of the non-negative degradation rate with time deformation and spectrum keeping consistency, and rapid adaptation is realized by matching meta-learning and online small-step fine tuning; the resulting generic characterization and reusable initialization can be used for health grading, phase identification, and life-related estimation.

Embodiments of the disclosed technology include a representation learning model for classification of natural language text. In embodiments, a classification model comprises a feature model and a classifier. The feature model may be hierarchical in nature: data may pass through a series of representations, decreasing in specificity and increasing in generality. Intermediate levels of representation may then be used as automatically learned features to train a statistical classifier. Specifically, the feature model may be based on a hierarchical Pitman-Yor process. In embodiments, once the feature model has been expressed as a Bayesian Belief Network and some aspect of the feature model has been selected for prediction, the feature model may be attached to the classifier. In embodiments, after training, potentially using a mix of labeled and unlabeled data, the classification model can be used to classify documents such as call transcripts based on topics of conversation represented in the transcripts.

Provided is a computer-implemented method for training a machine learning (ML) model using labelled and unlabelled data, the method comprising obtaining a set or training data comprising a set of labelled data items and a set of unlabelled data items, training a loss module of the ML model using labels in the set of labelled data items, to generate a trained loss module capable of estimating a likelihood of a label for a data item, and training a task module of the ML model using the loss module, the set of labelled data items, and the set of unlabelled data items, to generate a trained task module capable of making a prediction of a label for input data.

The invention discloses an image restoration method, system and device, a medium and a product, and belongs to the field of power grids, and the method comprises the steps: obtaining a to-be-restored image of a power scene under an extreme weather condition, inputting the to-be-restored image to an image restoration model, and obtaining a target image, the image restoration model is obtained by guiding an initial restoration model under a semi-supervised framework through an evaluation model to carry out iterative training, in each iteration, the label-free data is input into the first restoration model to obtain a restoration result, the restoration result is input into the evaluation model to carry out quality evaluation to obtain an evaluation signal, and the evaluation signal is sent to the semi-supervised framework; dynamically adjusting model parameters of a current second repair model based on the evaluation signal to guide the current second repair model to learn key features of the power equipment under extreme weather conditions, the evaluation model being obtained by performing all-parameter supervision fine tuning training on a multi-modal large language model based on power scene data; therefore, the generalization ability and the repairing effect of the repairing model can be improved by implementing the method and the device.

The application discloses a kind of semi-supervised identity recognition method and system based on millimeter wave radar, method includes: obtaining the point cloud data and range-velocity diagram data of millimeter wave radar;Point cloud data and range-velocity diagram data are preprocessed;The point cloud identity recognition model and range-velocity diagram identity recognition model designed are collaboratively trained using the point cloud data and range-velocity diagram data after preprocessing, the prediction probability of point cloud identity recognition model and the prediction probability of range-velocity diagram identity recognition model are obtained;The prediction probability of point cloud identity recognition model and the prediction probability of range-velocity diagram identity recognition model are fused.The application is trained by the method of semi-supervised collaboration to point cloud identity recognition model and range-velocity diagram identity recognition model, each other guide uses unlabelled data, improves model performance;Meanwhile, the prediction of two kinds of identity recognition models is fused, and higher identity recognition accuracy is realized.

The application discloses an uncertainty knowledge graph reasoning method based on semi-supervised confidence distribution learning, comprising the following steps: converting the triple confidence in the uncertainty knowledge graph training data into a confidence distribution; simultaneously learning the embedding of the uncertainty knowledge graph on the labeled data and the pseudo-labeled data generated by a pseudo-labeled data generator by using a relation learner based on confidence distribution learning; generating high-quality pseudo-confidence distribution labels for unlabeled data by using the pseudo-labeled data generator; iteratively training the relation learner based on confidence distribution learning and the pseudo-labeled data generator by using meta-self-training until the two converge; and inputting the data to be completed into the trained relation learner based on confidence distribution learning to perform reasoning, thereby achieving the completion of the uncertainty knowledge graph. The application can capture the supervision information of a small number of confidence or unseen confidence in the labeled data and is suitable for the scene where the triple confidence distribution of the uncertainty knowledge graph is unbalanced.

Systems, methods, and apparatuses, including network interface controllers and computer-readable media, for traffic shaping offload. A network computing device can receive data packets for transmission and implement a traffic policy that includes transmitting at least some data packets without delay to their intended destination. Confirmation tokens for non-delayed packets can be queued in a time-indexed data structure and dequeued according to a traffic shaping policy. Confirmation tokens can be generated and stored independent of the time at which corresponding packets for the tokens are transmitted. Dequeued confirmation tokens can cause the network computing device to receive additional packets for transmission. The device can flag at least some packets for transmission without delay according to aspects of the disclosure, while un-flagged packets can be shaped according to a different traffic shaping policy.

Continual learning and managing data related to continual learning in a computing network is disclosed. A central server trains and distributes a model to nodes in the computing network. When a model on a node detects a new domain, that node adapts its model to the new domain. Adapting the model includes requesting data from the new domain from other nodes. When the data from the other nodes is received, the model is retrained using the data from the other nodes and the unlabeled data at the node. The node may then label the unlabeled data.

The invention relates to the technical field of computers, and discloses an equipment fault diagnosis method and device, a model training method, equipment and a medium. Firstly, target waveform data of to-be-detected equipment is acquired; next, feature extraction is carried out on the target waveform data through the equipment fault diagnosis model, and time domain features and frequency domain features are obtained; wherein the equipment fault diagnosis model comprises a semi-supervised learning module. The parameters of the equipment fault diagnosis model are updated through the semi-supervised learning module by using the unlabeled data and the labeled data, the dynamic change of the equipment state is adapted, the dependence on data labeling is effectively reduced, the training cost is reduced, and the generalization performance of the model is improved; and the equipment fault diagnosis model performs equipment fault diagnosis based on the time domain feature, the frequency domain feature, the time domain threshold range and the frequency domain threshold range to obtain an equipment diagnosis result. By realizing automatic and intelligent fault diagnosis, the accuracy and efficiency of a diagnosis result are improved.

A cross-modality knowledge transfer system is provided for adapting one or more source model networks to one or more target model networks. The system is configured to perform steps of providing the TI paired datasets through the source feature encoders of the one or more source model networks, extracting TI source features and TI source moments from the TI paired data by the BN layers of the one or more source model networks, providing the TI paired datasets and the unlabeled TR datasets through the one or more target model networks to extract TI target features and TR target moments, training jointly all the feature encoders of the one or more target model networks by matching the extracted TI target features and TR target moments with the TI source features and TI source moments along with mixing weights, and forming a final target model network by combining the trained one or more target model networks.

Various aspects of the present disclosure relate to quantizing learning model parameters. The parameters of a trained learning model are quantized taking into account the sensitivity or the tolerance range of the parameters of the learning model so that the prediction or inference performance of the learning model after quantizing its parameters does not degrade beyond a given threshold from its intended (e.g., as trained) prediction or inference performance. The sensitivity or tolerance range of the parameters of the learning model can be determined based on a set of unlabeled data samples, and without having access to the training data or labeled data used to train the learning model. Forward error protection can also be used to provide error protection at different levels based on the sensitivity of parameters of the learning model when communicating the quantized model parameters (e.g., to another device or entity).

In one embodiment, the present disclosure provides a computer-implemented method comprising: receiving a first labeled training dataset comprising a first plurality of images each associated with a set of labels; programmatically training a machine learning neural Teacher model on the first labeled training dataset; programmatically applying a machine learning model trained for NLP to an unlabeled dataset comprising a digital electronic representation of natural language text summaries of a second plurality of images, thereby generating a second labeled training dataset comprising the second plurality of images; programmatically generating soft pseudo-labels using the machine learning neural Teacher model; programmatically generating derived labels using the soft pseudo-labels; training one or more machine learning neural Student models using the derived labels; receiving a target image; applying an ensemble of the one or more Student models to output one or more classifications of the target image.

Broadly speaking, the present techniques provide an automatic way of classifying data items within an environment (e.g. a business, workplace, organisation, etc.), and applying data management policies based on the classifications. This is advantageous over existing techniques which require manual classification of data items, which is time consuming in environments where hundreds of new data items may be generated in a day or week. The present techniques use an embedding machine learning, ML, model to automatically determine the relevant classification label(s) for an unlabelled data item, which is then used to select and apply the relevant data management policy(ies).

The invention discloses an optic disc and optic cup segmentation method based on semi-supervised learning, belongs to the field of image processing and artificial intelligence, and aims to solve the problems of instability of an optic disc and optic cup segmentation model caused by few labeled eye fundus images and poor precision caused by noise pollution. In the first stage, a double-branch improved DeepLab v3 + model is constructed to complete optic disc segmentation, after full supervision and anti-noise training are carried out by utilizing an annotated fundus image, the double-branch model is used for processing an unannotated fundus image, the anti-noise capability of the model is evaluated by counting the consistency of pseudo-label pixels before and after noise, and the model with strong anti-noise performance is used for supervising the training of the other model; in the second stage, a SegFormer model is constructed and trained to complete optic cup segmentation; and finally connecting the two models in series to realize two-stage segmentation of the optic disc and the optic cup. According to the method, unlabeled data is fully utilized for semi-supervised training, the noise immunity and segmentation precision of the model are improved, and technical support is provided for glaucoma screening work.

The application discloses a kind of training method, device, electronic equipment and storage medium of image segmentation model.The method comprises: obtaining multiple groups of training sample data, and training sample data includes sample image;In the iterative training process of image segmentation model, sample image is input to the encoder in image segmentation model, and the encoding feature image is obtained, the encoding feature image is input to the decoder in image segmentation model, and the first reconstruction image is obtained, the encoding feature image is input to the variational autoencoder in image segmentation model, and the second reconstruction image is obtained;Determine segmentation model loss based on the first reconstruction image, the second reconstruction image and sample image, adjust the parameter of current image segmentation model based on segmentation model loss, and obtain target image segmentation model.The above technical solution realizes self-supervised learning by increasing variational autoencoder, realizes unlabelled data training, reduces dependence on labeled data, and reduces data labeling cost.

The invention discloses a gait identity recognition method based on a generative self-supervised visual pre-training model BEiT and DAS technology. The method comprises the following steps: firstly, carrying out scene construction and data preparation, collecting label-free data and label data, extracting data signals for signal preprocessing, and constructing a time frequency characteristic data set; constructing a pre-training image reconstruction network of a self-supervised visual pre-training model BEiT, performing feature extraction on an input image, constructing a deep learning network based on the self-supervised visual pre-training model BEiT as a feature extractor, and training the deep learning network by using unlabeled spatio-temporal data in an experimental scene to obtain weight parameters; and constructing a downstream classification task network, performing classification learning of downstream tasks by using a small amount of data with labels to obtain a new weight, and completing identification and classification of non-label data by using the obtained new weight. According to the method, the demand quantity of the tagged data is reduced, and the accuracy is ensured.

The application discloses a wall heat flow prediction method considering material ablation response under a semi-supervised learning framework, and relates to the field of aerospace. The method comprises the following steps: constructing a data set; building a neural network model and introducing an ablation physical information loss term into a loss function of the neural network model; pre-training the neural network model; predicting unlabelled data through the pre-trained neural network model to generate pseudo labels; mixing labelled data and unlabelled data to semi-supervise and train the pre-trained neural network model to obtain a final neural network model; and predicting wall heat flow of material ablation response through the final neural network model. The method reduces the demand of the model on the labelled data set, enhances the model generalization ability under the condition of small sample training, increases the physical interpretability of the network model, and improves the wall heat flow prediction precision.