2778 results about "Supervised learning" patented technology

A method for operating a sleep phase actigraphy synchronized alarm clock that communicates with a remote sleep database, such as an internet server database, and compares user physiological parameters, sleep settings, and actigraphy data with a large database that may include data collected from a large number of other users with similar physiological parameters, sleep settings, and actigraphy data. The remote server may use “black box” analysis approach by running supervised learning algorithms to analyze the database, producing sleep phase correction data which can be uploaded to the alarm clock, and be used by the alarm clock to further improve its REM sleep phase prediction accuracy.

It is an object to highly accurately perform semantic relationship extraction from text data by performing supervised learning of multiple classes using an existing thesaurus as a correct answer. Concerning any pair of words in a text, a plurality of kinds of similarities are calculated and a feature vector including the similarities as elements is generated. A label indicating a classification of a semantic relationship is given to pairs of words on the basis of the thesaurus. Data for semantic relationship identification is learned as an identification problem of multiple classes from the feature vector and the label. Identification of an inter-semantic relationship of two words is performed according to the data for semantic relationship identification.

An apparatus and method predict and detect network attacks by using a diverse set of indicators to measure aspects of the traffic and by encoding traffic characteristics using these indicators of potential attacks or anomalous behavior. The set of indicators is analyzed by supervised learning to automatically learn a decision rule which examines the temporal patterns in the coded values of the set of indicators to accurately detect and predict network attacks. The rules automatically evolve in response to new attacks as the system updates its rules periodically by analyzing new data and feedback signals about attacks associated with that data. To assist human operators, the system also provides human interpretable explanations of detection and prediction rules by pointing to indicators whose values contribute to a decision that there is an existing network attack or an imminent network attack. When such indictors are detected, an operator can take remediation actions.

The technology disclosed relates to machine learning based anomaly detection. In particular, it relates to constructing activity models on per-tenant and per-user basis using an online streaming machine learner that transforms an unsupervised learning problem into a supervised learning problem by fixing a target label and learning a regressor without a constant or intercept. Further, it relates to detecting anomalies in near real-time streams of security-related events of one or more tenants by transforming the events in categorized features and requiring a loss function analyzer to correlate, essentially through an origin, the categorized features with a target feature artificially labeled as a constant. It further includes determining an anomaly score for a production event based on calculated likelihood coefficients of categorized feature-value pairs and a prevalencist probability value of the production event comprising the coded features-value pairs.

The disclosure provides a method, an electronic apparatus, and a computer readable medium of constructing a classifier for disease detection. The method includes the following steps. A codebook of representative features is constructed based on a plurality of disease-irrelevant data. Transfer-learned disease features are extracted from disease-relevant bio-signals according to the codebook without any medical domain knowledge, where both the disease-irrelevant data and the disease-relevant bio-signals are time-series data. Supervised learning is performed based on the transfer-learned disease features to train the classifier for disease detection.

Framework may be implemented for transferring knowledge from an external agent to a robotic controller. In an obstacle avoidance / target approach application, the controller may be configured to determine a teaching signal based on a sensory input, the teaching signal conveying information associated with target action consistent with the sensory input, the sensory input being indicative of the target / obstacle. The controller may be configured to determine a control signal based on the sensory input, the control signal conveying information associated with target approach / avoidance action. The controller may determine a predicted control signal based on the sensory input and the teaching signal, the predicted control conveying information associated with the target action. The control signal may be combined with the predicted control in order to cause the robotic apparatus to execute the target action.

The invention relates to the technical field of image information processing, in particular to a multiclass image classification method based on active learning and semi-supervised learning. The method comprises five steps: initial sample selection and classifier model training, BvSB active learning sample selection, CST semi-supervised learning, training sample set and classifier model updating and assorting process iteration. Through the operations of BvSB active learning sample selection, CST semi-supervised learning and SVM classification, the invention has efficient image classification effect under the condition of less manual tagging, does not increase overmuch computation burden, can quickly provide classification effects and also can take consideration of the demand of a classification system on the computation complexity.

Techniques for allocating individually executable portions of executable code for execution in an Elastic computing environment are disclosed. In an Elastic computing environment, scalable and dynamic external computing resources can be used in order to effectively extend the computing capabilities beyond that which can be provided by internal computing resources of a computing system or environment. Machine learning can be used to automatically determine whether to allocate each individual portion of executable code (e.g., a Weblet) for execution to either internal computing resources of a computing system (e.g., a computing device) or external resources of an dynamically scalable computing resource (e.g., a Cloud). By way of example, status and preference data can be used to train a supervised learning mechanism to allow a computing device to automatically allocate executable code to internal and external computing resources of an Elastic computing environment.

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 discloses a semi-supervised image classification method based on a generative adversarial network, which mainly solves the problems that the existing unsupervised learning classificationprecision is low and semi-supervised learning needs a large number of accurate labels, and comprises the following implementation steps of: 1) selecting and downloading a standard image training sample and a test sample; 2) setting relevant parameters of network supervised learning, and establishing a generative adversarial network consisting of a generator network, a discriminator network and anauxiliary classifier in parallel; 3) training the generative adversarial network by using a random gradient descent method; and 4) inputting the test sample to be classified into the trained generative adversarial network model, and outputting the category of the image to be detected. The method improves the image classification precision of unsupervised learning, can obtain a very good image classification effect on a sample set only containing a small amount of accurate annotation samples, and can be used for target classification in an actual scene.

The spectral kernel machine combines kernel functions and spectral graph theory for solving problems of machine learning. The data points in the dataset are placed in the form of a matrix known as a kernel matrix, or Gram matrix, containing all pairwise kernels between the data points. The dataset is regarded as nodes of a fully connected graph. A weight equal to the kernel between the two nodes is assigned to each edge of the graph. The adjacency matrix of the graph is equivalent to the kernel matrix, also known as the Gram matrix. The eigenvectors and their corresponding eigenvalues provide information about the properties of the graph, and thus, the dataset. The second eigenvector can be thresholded to approximate the class assignment of graph nodes. Eigenvectors of the kernel matrix may be used to assign unlabeled data to clusters, merge information from labeled and unlabeled data by transduction, provide model selection information for other kernels, detect novelties or anomalies and / or clean data, and perform supervised learning tasks such as classification.

The invention discloses a zero sample image classification method based on combination of a variational autocoder and an adversarial network. Samples of a known category are input during model training; category mapping of samples of a training set serves as a condition for guidance; the network is subjected to back propagation of optimization parameters through five loss functions of reconstruction loss, generation loss, discrimination loss, divergence loss and classification loss; pseudo-samples of a corresponding unknown category are generated through guidance of category mapping of the unknown category; and a pseudo-sample training classifier is used for testing on the samples of the unknown category. The high-quality samples beneficial to image classification are generated through theguidance of the category mapping, so that the problem of lack of the training samples of the unknown category in a zero sample scene is solved; and zero sample learning is converted into supervised learning in traditional machine learning, so that the classification accuracy of traditional zero sample learning is improved, the classification accuracy is obviously improved in generalized zero sample learning, and an idea for efficiently generating the samples to improve the classification accuracy is provided for the zero sample learning.

The invention provides a semi-supervised X-ray automatic labeling method based on a generative adversarial network. A traditional training method is improved on the basis of an existing generative adversarial network method, and a semi-supervised training method combining supervised loss and unsupervised loss is used for carrying out image classification recognition based on a small number of labeled samples. The problem of data scarcity annotation of the X-ray image is studied. The method comprises: firstly, on the basis of a traditional unsupervised generative adversarial network, using a softmax for replacing a final output layer; expanding the X-ray image into a semi-supervised generative adversarial network, defining additional category label guide training for the generated sample, optimizing network parameters by adopting the semi-supervised training, and finally, automatically labeling the X-ray image by adopting a trained discriminant network. Compared with traditional supervised learning and other semi-supervised learning algorithms, the method has the advantage that in the aspect of medical X-ray image automatic labeling, the performance is improved.

A face descriptor generating method and apparatus and face recognition method and apparatus using extended local binary pattern (LBP) are provided.Since LBP features are selected by performing a supervised learning process on the extended LBP features and the selected extended LBP features are used in face recognition, it is possible to reduce errors in face recognition or identity verification and to increase face recognition efficiency. In addition, the extended LBP features are used so that it is possible to overcome the problem of time-consumption of the process.

A system and method for inferring informational goals and preferred level of details in answers in response to questions posed to computer-based information retrieval or question-answering systems is provided. The system includes a query subsystem that can receive an input query and extrinsic data associated with the query and which can output an answer to the query, and / or rephrased queries or sample queries. The query subsystem accesses an inference model to retrieve conditional probabilities that certain informational goals are present. One application of the system includes determining a user's likely informational goals and then accessing a knowledge data store to retrieve responsive information. The system includes a natural language processor that parses queries into observable linguistic features and embedded semantic components that can be employed to retrieve the conditional probabilities from the inference model. The inference model is built by employing supervised learning and statistical analysis on a set of queries suitable to be presented to a question-answering system. Such a set of queries can be manipulated to produce different inference models based on demographic and / or localized linguistic data.

A computer system may receive, from an acoustic transducer and / or a portable electronic device, information specifying one or more desired operations that are to be performed. This information may include natural language describing the one or more desired operations. In response, the computer system may transform the natural language into the one or more desired operations, and may identify a subset of the electronic devices based on the one or more desired operations and a predetermined supervised learning model that relates desired operations and the electronic devices. Next, the computer system may determine a set of commands based on the one or more desired operations and the subset of the electronic devices, and the computer system may provide the set of commands to the identified subset of the electronic devices, which may perform the one or more desired operations.

A supervised learning processing (SLP) system and non-transitory, computer program product provides cooperative operation of a network of supervised learning processors to concurrently distribute supervised learning processor training, generate predictions, and provide prediction driven responses to input objects, such as NL statements. The SLP system includes SLP stages that are distributed across multiple SLP subsystems. Concurrently training SLP's provides accurate predictions of input objects and responses thereto, the SLP system and non-transitory, computer program product enhance the network by providing high quality value predictions and responses and avoiding potential training and operational delays. The SLP system can enhance the network of SLP subsystems by providing flexibility to incorporate multiple SLP models into the network and train at least a proper subset of the SLP models while concurrently using the SLP system and non-transitory, computer program product in commercial operation.

The invention discloses an image classification method and device based on semi-supervised deep learning and a storage medium. The method includes: acquiring label training image samples and non-labeltraining image samples, and obtaining a label training set; combining deep learning and semi-supervised learning to carry out training of a convolutional neural network (CNN) on the label training set, and establishing a unified model of semi-supervised deep learning and unlabeled-sample class estimation; and carrying out image recognition / classification on the basis of the model of semi-supervised deep learning and unlabeled sample class estimation. According to the method, distinguishing information hidden in non-label training data can be utilized, high separability of current deep features can also be utilized at the same time, the unlabeled samples can be more efficiently and accurately utilized, and thus better image recognition performance can be obtained.

The invention discloses an automatic diagnosis method for electrocardiographic abnormality and relates to the technical field of automatic diagnosis of electrocardiographic abnormality. The learning capacity of an RNN neural network to a time sequence and the learning capability of CNN to spatial features are combined to learn features of the electrocardiographic biological signal, and abnormal electrocardiographs of different types are automatically characterized. Then, a deep neural network based classifier is constructed, which is trained using an electrocardiograph with type annotations to improve the accuracy of classification, and automatic classification of different arrhythmia types is achieved. According to the invention, the process of manually extracting features is avoided; then, time sequence features and spatial features of the electrocardiographs are learned using RNN and CNN to form the classifier, and the classifier is trained through supervised learning so that the classifier can automatically diagnose abnormal electrocardiographs. As a result, the accuracy of automatic diagnosis and classification of electrocardiographic abnormality is improved.

State-dependent supervised learning framework in artificial neuron networks may be implemented. A framework may be used to describe plasticity updates of neuron connections based on a connection state term and a neuron state term. Connection states may be updated based on inputs and outputs to and / or from neurons. The input connections of a neuron may be updated using input traces comprising a time-history of inputs provided via the connection. Weight of the connection may be updated and connection state may be time varying. The updated weights may be determined using a rate of change of the input trace and a term comprising a product of a per-neuron contribution and a per-connection contribution configured to account for the state time-dependency. Using event-dependent connection change components, connection updates may be executed on a per neuron basis, as opposed to a per-connection basis.

A method for classification of image regions by probabilistic merging of a class probability map and a cluster probability map includes the steps of a) extracting one or more features from an input image composed of image pixels; b) performing unsupervised learning based on the extracted features to obtain a cluster probability map of the image pixels; c) performing supervised learning based on the extracted features to obtain a class probability map of the image pixels; and d) combining the cluster probability map from unsupervised learning and the class probability map from supervised learning to generate a modified class probability map to determine the semantic class of the image regions. In one embodiment the extracted features include color and textual features.

The invention relates to a fine granularity vehicle multi-property recognition method based on a convolutional neural network and belongs to the technical field of computer visual recognition. The method comprises the steps that a neural network structure is designed, including a convolution layer, a pooling layer and a full-connection layer, wherein the convolution layer and the pooling layer areresponsible for feature extraction, and a classification result is output by calculating an objective loss function on the last full-connection layer; a fine granularity vehicle dataset and a tag dataset are utilized to train the neural network, the training mode is supervised learning, and a stochastic gradient descent algorithm is utilized to adjust a weight matrix and offset; and a trained neural network model is used for performing vehicle property recognition. The method can be applied to multi-property recognition of a vehicle, the fine granularity vehicle dataset and the multi-propertytag dataset are utilized to obtain more abstract high-level expression of the vehicle through the convolutional neural network, invisible characteristics reflecting the nature of the to-be-recognizedvehicle are learnt from a large quantity of training samples, therefore, extensibility is higher, and recognition precision is higher.

A system and method are disclosed for providing semi-supervised learning for a spoken language understanding module using semantic role labeling. The method embodiment relates to a method of generating a spoken language understanding module. Steps in the method comprise selecting at least one predicate / argument pair as an intent from a set of the most frequent predicate / argument pairs for a domain, labeling training data using mapping rules associated with the selected at least one predicate / argument pair, training a call-type classification model using the labeled training data, re-labeling the training data using the call-type classification model and iteratively several of the above steps until training set labels converge.

The invention discloses a network traffic protocol recognition method based on deep learning. The similarity of network traffic data and images is utilized, the work of traffic feature value selectionand extraction is skipped and the network traffic data directly act as the input of a convolutional neural network to perform supervised learning and train a network traffic protocol recognition model so that the function of network traffic protocol recognition can be realized. According to the method, only a network traffic protocol sample to be recognized is provided for training of the convolutional neural network so that the features favorable for the classification task can be automatically extracted without spending energy on protocol feature extraction and selection; and the method haslearning and extending capacity and can be used for recognizing the new unknown protocol and can be extended to be applied to recognition of the network traffic including malicious codes and recognition of the corresponding program traffic.

Disclosed herein are a method and system for training a big data machine to defend, retrieve log lines belonging to log line parameters of a system's data source and from incoming data traffic, compute features from the log lines, apply an adaptive rules model with identified threat labels produce a features matrix, identify statistical outliers from execution of statistical outlier detection methods, and may generate an outlier scores matrix. Embodiments may combine a top scores model and a probability model to create a single top scores vector. The single top scores vector and the adaptive rules model may be displayed on a GUI for labeling of malicious or non-malicious scores. Labeled output may be transformed into a labeled features matrix to create a supervised learning module for detecting new threats in real time and reducing the time elapsed between threat detection of the enterprise or e-commerce system.

The invention belongs to the technical field of computers, and discloses a machine translation method and system based on a generative adversarial neural network. The method comprises the following steps that: on the basis of an original machine translation generation network, a discrimination network which generates network countermeasure with the original machine translation generation network is imported; a translation used for judging a target language is from a training parallel corpus and is a network machine translation result of the original machine translation generation network; and the discrimination network adopts a multi-layer sensor feedforward neural network model to realize binary classification. The system comprises the discrimination network, a generation network, a mono-lingual corpus and a parallel corpus. While manually annotated bilingual parallel corpus resources are fully utilized, and mono-lingual corpus resources also can be fully utilized to carry out semi-supervised learning; and the mono-lingual corpus resources are very rich and can be easily obtained, and the problem that required training corpora required by the neural network machine translation model are not sufficient is solved.

The invention relates to a traveling domain knowledge map construction method and system, and belongs to the field of Web mining and intelligent information processing. Travelling domain knowledge map construction tasks include an entity attribute knowledge expansion subtask and an entity attribute value fusion subtask. By adopting a mixed entity attribute knowledge expansion method, an entity attribute knowledge expansion algorithm based on a lexical field, supervised learning, pattern matching and search engine questions and answers is integrated. For the entity attribute knowledge expansion subtask, a multi-value attribute value fusion method based on source credibility, a fixed pattern single-value attribute value fusion method based on content credibility and a non-fixed pattern attribute value fusion method based on learning ranking are adopted. The structured travelling domain entity knowledge base is constructed, traveling domain entity attribute and attribute value knowledge is accurately expressed, the traveling domain knowledge obtaining efficiency is improved, and the wide application prospect is achieved.

The present teaching relates to method system, and medium for generating knowledge for a chat bot. Training data are used to learn and generating knowledge and are received with at least some labeled training seeds and unlabeled conversation data. The training data are parsed and various linguistic elements are extracted therefrom. Such linguistic elements are then used to perform automated learning in accordance with at least one label used in labeling the training seeds. Based on the automated learning, at least one model associated with the at least one label is generated from the training data.