6289 results about "Training data sets" patented technology

A system, computer readable storage medium, and computer-implemented method presents video search results responsive to a user keyword query. The video hosting system uses a machine learning process to learn a feature-keyword model associating features of media content from a labeled training dataset with keywords descriptive of their content. The system uses the learned model to provide video search results relevant to a keyword query based on features found in the videos. Furthermore, the system determines and presents one or more thumbnail images representative of the video using the learned model.

A system and method for monitoring an apparatus or process asset including partitioning an unpartitioned training data set into a plurality of training data subsets each having an operating mode associated thereto; creating a process model comprised of a plurality of process submodels each trained as a function of at least one of the training data subsets; acquiring a current set of observed signal data values from the asset; determining an operating mode of the asset for the current set of observed signal data values; selecting a process submodel from the process model as a function of the determined operating mode of the asset; calculating a current set of estimated signal data values from the selected process submodel for the determined operating mode; and outputting the calculated current set of estimated signal data values for providing asset surveillance and/or control.

A human assisted method of debugging training data used to train a machine learning classifier is provided. The method includes obtaining a classifier training data set. The training data set is then debugged using an integrated debugging tool configured to implement a debugging loop to obtain a debugged data set. The debugging tool can be configured to perform an estimation and simplification step to reduce data noise in the training data set prior to further analysis. The debugging tool also runs a panel of prediction-centric diagnostic metrics on the training data set, and provides the user prediction based listings of the results of the panel of prediction-centric diagnostic metrics.

A 1D-CNN-based ((one-dimensional convolutional neural network)-based) distributed optical fiber sensing signal feature learning and classification method is provided, which solves a problem that an existing distributed optical fiber sensing system has poor adaptive ability to a complex and changing environment and consumes time and effort due to adoption of manually extracted distinguishable event features, The method includes steps of: segmenting time sequences of distributed optical fiber sensing acoustic and vibration signals acquired at all spatial points, and building a typical event signal dataset; constructing a 1D-CNN model, conducting iterative update training of the network through typical event signals in a training dataset to obtain optimal network parameters, and learning and extracting 1D-CNN distinguishable features of different types of events through an optimal network to obtain typical event signal feature sets; and after training different types of classifiers through the typical event signal feature sets, screening out an optimal classifier.

The invention discloses a remote sensing image semantic segmentation method based on attention multi-scale feature fusion, and the method comprises the steps: establishing a semantic segmentation network based on attention multi-scale feature fusion, building a training data set, and carrying out the network parameter training through employing the training data set. And performing semantic segmentation on to-be-tested data by using the trained network during testing. And the network is a lightweight encoder-decoder structure. Wherein the idea of an image cascade network is introduced; meanwhile, coding features and decoding features are optimized by using an attention mechanism, a multi-scale attention optimization module, a multi-scale feature fusion module and a boundary enhancement module are constructed, feature maps of different scales are extracted and fused, training is guided by using multi-scale semantic tags and boundary tags, and semantic segmentation of remote sensing images can be effectively carried out.

A method of detecting an intrusion in the operation of a computer system based on a plurality of events. A rule set is determined for a training set of data comprising a set of features having associated costs. For each of a plurality of events, the set of features is computed and a class is predicted for the features with a rule of the rule set. For each event predicted as an intrusion, a response cost and a damage cost are determined, wherein the damage cost is determined based on such factors as the technique of the intrusion, the criticality of the component of the computer system subject to the intrusion, and a measure of progress of the intrusion. If the damage cost is greater than or equal to the response cost, a response to the event.

The invention is directed to a method for training at least one learning-capable system comprising the steps of providing a predetermined training data set corresponding to a predetermined number of subjects comprising a predetermined input data set and a predetermined outcome data set, augmenting the input data set and/or the outcome data set, and training each learning-capable system using the augmented input data set and/or the augmented outcome data set.

The invention discloses a CT image pulmonary nodule detection system based on 3D full-connection convolution neural network. The detection system comprises the following five steps: constructing a training set data; performing 3D convolution neural network classification network training; performing 3D convolution neural network segmentation network training; carrying out false-positive suppression in which the trained segmentation network and the false-positive are utilized to inhibit the network; and detecting the pulmonary nodule. The technical schemes of the invention can realize the full automatic detection without any human intervention. At the same time, the recall rate of pulmonary nodule detection can be increased effectively; the false-positive focus of infection is reduced considerably; and a pixel level positioning quantitative and qualitative result for the focus-of-infection area of the pulmonary nodule can be obtained.

The invention is a computer implemented technique for id entifying anomalous data in a data set. The method uses cascaded k-Means clustering and the ID3 decision tree learning methods to characterize a training data set having data points with known characterization. The k-Means clustering method first partitions the training instances into k clusters using Euclidean distance similarity. On each training cluster, representing a density region of normal or anomaly instances, the invention builds an ID3 decision tree. The decision tree on each cluster refines the decision boundaries by learning the sub-groups within the cluster. A test data point is then subjected to the clustering and decision trees constructed form the training instances. To obtain a final decision on classification, the decisions of the k-Means and ID3 methods are combined using rules: (1) the Nearest-neighbor rule, and (2) the Nearest-consensus rule.

The invention relates to the field of computer vision recognition and transfer learning, and provides a small sample and zero sample image classification method based on metric learning and meta-learning, which comprises the following steps of: constructing a training data set and a target task data set; selecting a support set and a test set from the training data set; respectively inputting samples of the test set and the support set into a feature extraction network to obtain feature vectors; sequentially inputting the feature vectors of the test set and the support set into a feature attention module and a distance measurement module, calculating the category similarity of the test set sample and the support set sample, and updating the parameters of each module by utilizing a loss function; repeating the above steps until the parameters of the networks of the modules converge, and completing the training of the modules; and enabling the to-be-tested picture and the training picture in the target task data set to sequentially pass through a feature extraction network, a feature attention module and a distance measurement module, and outputting a category label with the highestcategory similarity with the test set to obtain a classification result of the to-be-tested picture.

A traffic classifier has a plurality of binary classifiers, each associated with one of a plurality of calibrators. Each calibrator trained to translate an output score of the associated binary classifier into an estimated class probability value using a fitted logistic curve, each estimated class probability value indicating a probability that the packet flow on which the output score is based belongs to the traffic class associated with the binary classifier associated with the calibrator. The classifier training system configured to generate a training data based on network information gained using flow and packet sampling methods. In some embodiments, the classifier training system configured to generate reduced training data sets, one for each traffic class, reducing the training data related to traffic not associated with the traffic class.

A computing device receives a training data set that includes a plurality of positive examples of sensitive data and a plurality of negative examples of sensitive data via a user interface. The computing device analyzes the training data set using machine learning to generate a machine learning-based detection (MLD) profile that can be used to classify new data as sensitive data or as non-sensitive data. The computing device displays a quality metric for the MLD profile in the user interface.

Disclosed herein are systems, methods, and devices for classifying ophthalmic images according to disease type, state, and stage. The disclosed invention details systems, methods, and devices to perform the aforementioned classification based on weighted-linkage of an ensemble of machine learning models. In some parts, each model is trained on a training data set and tested on a test dataset. In other parts, the models are ranked based on classification performance, and model weights are assigned based on model rank. To classify an ophthalmic image, that image is presented to each model of the ensemble for classification, yielding a probabilistic classification score—of each model. Using the model weights, a weighted-average of the individual model-generated probabilistic scores is computed and used for the classification.

The invention provides a full convolution network based facial feature positioning and distinguishing method and system. The method specifically comprises steps as follows: collecting facial images and marking facial features to form a training data set; designing a full convolution neural network; training the full convolution neural network according to the training data set; performing facial feature positioning and marking on the facial images according to the trained full convolution neural network. According to an image segmentation mode adopting the full convolution network, a predication category of each point of an input face can be obtained, so that the accurate facial feature positions can be obtained, and the problems that the number of key points is insufficient and the key points are not stable enough on the basis of the facial key points are solved.

A system and method for defining and tracking a deformable shape of a candidate anatomical structure wall in a three dimensional (3D) image is disclosed. The shape of the candidate anatomical structure is represented by a plurality of labeled 3D landmark points. At least one 3D landmark point of the deformable shape in an image frame is defined. A 3D cuboid is defined around the detected 3D landmark point. For each landmark point associated with the anatomical structure, its location and location uncertainty matrix is estimated in subsequent frames relative to the reference anatomical structures. A shape model is generated to represent dynamics of the deformable shape in subsequent image frames. The shape model includes statistical information from a training data set of 3D images of representative anatomical structures. The shape model is aligned to the deformable shape of the candidate anatomical structure. The shape model is fused with the deformable shape. A current shape of the candidate anatomical structure is estimated.

An anomaly detector for a Controller Area Network (CAN) bus performs state space classification on a per-message basis of messages on the CAN bus to label messages as normal or anomalous, and performs temporal pattern analysis as a function of time to label unexpected temporal patterns as anomalous. The anomaly detector issues an alert if an alert criterion is met that is based on the outputs of the state space classification and the temporal pattern analysis. The temporal pattern analysis may compare statistics of messages having analyzed arbitration IDs with statistics for messages having those analyzed arbitration IDs in a training dataset of CAN bus messages, and a temporal pattern is anomalous if there is a statistically significant deviation from the training dataset. The anomaly detector may be implemented on a vehicle Electronic Control Unit (ECU) communicating via a vehicle CAN bus. The anomaly detector does not rely on an database of messages and their periodicity from manufacturers (dbc files) and in that sense is truly a zero knowledge detector.

Provide are systems methods and devices for diagnosing disease in medical images. In certain aspects, disclosed is a method for training a neural network to detect features in a retinal image including the steps of: a) extracting one or more features images from a Train_0 set, a Test_0 set, a Train_1 set and a Test_1 set; b) combining and randomizing the feature images from Train_0 and Train_1 into a Training data set; c) combining and randomizing the feature images from Test_0 and Test_1 into a testing dataset; d) training a plurality of neural networks having different architectures using a subset of the training dataset while testing on a subset of the testing dataset; e) identifying the best neural network based on each of the plurality of neural networks performance on the testing data set; f) inputting images from Test_0, Train_1, Train_0 and Test_1 to the best neural network and identifying a limited number of false positives and false negative and adding the false positives and false negatives to the training dataset and testing dataset; and g) repeating steps d)-g) until an objective performance threshold is reached.

An automated license plate recognition (ALPR) system and method using a human-in-the-loop based adaptive learning approach. One or more images with respect to an automotive vehicle can be segmented in order to determine a license plate of the automotive vehicle within a scene. An optical character recognition (OCR) engine loaded with an OCR algorithm can be further adapted to determine a character sequence of the license plate based on a training data set. A confidence level with respect to the images can be generated in order to route a low confidence image to an operator for obtaining a human interpreted image. The parameters with respect to the OCR algorithm can be adjusted based on the human interpreted image and the actual image of the license plate. A license plate design can be then incorporated into the OCR engine in order to automate the process of recognizing the license plate with respect to the automotive vehicle in a wide range of transportation related applications.

The invention relates to the technical field of traffic image processing, and discloses a driving scene target detection method based on deep learning and multi-layer feature fusion. The method comprises the following steps of 1) collecting a video image to serve as a training data set, and performing preprocessing; 2) building a training network; 3) initializing the training network to obtain a pre-training model; 4) performing training on the training data set by using the pre-training model obtained in the step 3), thereby obtaining a training model; 5) collecting a front image by using a vehicle-mounted camera, and inputting the image into the training model obtained in the step 4), thereby obtaining a detection result. The multi-layer feature fusion method based on a feature pyramid is adopted to enhance semantic information of a low-layer feature graph, so that the feature extraction quality of the network is improved, and higher detection precision is obtained.

In a method of generating an anomaly detection model for classifying activities of a computer system, using a training set of data corresponding to activity on the computer system, the training set comprising a plurality of instances of data having features, and wherein each feature in said plurality of features has a plurality of values. For a selected feature and a selected value of the selected feature, a quantity is determined which corresponds to the relative sparsity of such value. The quantity may correspond to the difference between the number occurrences of the selected value and the number of occurrences of the most frequently occurring value. These instances are classified as anomaly and added to the training set of normal data to generate a rule set or other detection model.

A method for training a deep neural network (DNN) to perform a specified task with respect to images captured by a target camera, including: using an image captured by the target camera as a style target image, training a style transformer network to perform a style transformation that transforms any photorealistic input image into a transformed image that has contents of the input image, maintains photorealistic quality of the input image, and has a style that matches a style of the style target image; using the trained style transformer network to transform training image of an original training dataset into transformed training images; labeling the transformed training images with the training labels of the corresponding training image of the original training dataset, to form an augmented training dataset; and using the augmented training dataset to train the DNN to perform the specified task.

A dialog state tracking system. One aspect of the system is the use of multiple utterance decoders and/or multiple spoken language understanding (SLU) engines generating competing results that improve the likelihood that the correct dialog state is available to the system and provide additional features for scoring dialog state hypotheses. An additional aspect is training a SLU engine and a dialog state scorer/ranker DSR engine using different subsets from a single annotated training data set. A further aspect is training multiple SLU/DSR engine pairs from inverted subsets of the annotated training data set. Another aspect is web-style dialog state ranking based on dialog state features using discriminative models with automatically generated feature conjunctions. Yet another aspect is using multiple parameter sets with each ranking engine and averaging the rankings. Each aspect independently improves dialog state tracking accuracy and may be combined in various combinations for greater improvement.

The present invention discloses a prediction model-building method for computer-aided medical diagnosis. It utilizes the medical symptom detection equipment to obtain the symptom of object to be diagnosed to form symptomatic vector, then utilizes the prediction model to make treatment so as to can obtain prediction result. It also provides its concrete steps for implementing said invented prediction model-building method.