MACHINE LEARNING

VolverVolver

Resultados 124 resultados LastUpdate Última actualización 28/05/2020 [03:43:00] pdf PDF xls XLS

Solicitudes publicadas en los últimos 60 días / Applications published in the last 60 days



Página1 de 5 nextPage   por página


DISCOVERING GENOMES TO USE IN MACHINE LEARNING TECHNIQUES

NºPublicación: EP3655894A1 27/05/2020

Solicitante:

ANALYTICS FOR LIFE INC [CA]

CN_111095232_A

Resumen de: WO2019016608A1

A facility for identifying combinations of feature and machine learning algorithm parameters, where each combination can be combined with one or more machine learning algorithms to train a model, is disclosed. The facility evaluates each genome based on the ability of a model trained using that genome and a machine learning algorithm to produce accurate results when applied to a validation data set by, for example, generating a fitness or validation score for the trained model and the corresponding genome used to train the model. Genomes that produce fitness scores that exceed a fitness threshold are selected for mutation, mutated, and the process is repeated. These trained models can then be applied to new data to generate predictions for the underlying subject matter.

traducir

DETECTING A TRANSACTION VOLUME ANOMALY

NºPublicación: WO2020102241A1 22/05/2020

Solicitante:

CAPITAL ONE SERVICES LLC [US]

US_2020151728_A1

Resumen de: WO2020102241A1

A server device obtains historical transaction data regarding transactions involving a network service, obtains historical calendar data regarding static date information for a historical time period that corresponds with the historical transaction data, and processes the historical transaction data and historical calendar data to train a machine learning model using a gradient boosting machine learning technique to predict a normal transaction volume for a period of time and confidence bands associated with the normal transaction volume. The server device generates the normal transaction volume for the period of time and confidence bands using the machine learning model, obtains real-time data concerning a transaction volume during the period of time, detects a transaction volume anomaly based on comparing the real-time data and normal transaction volume and confidence bands, and sends an alert, based on the transaction volume anomaly, to cause a remote device to display the alert and perform an action.

traducir

LEARNING TO GENERATE SYNTHETIC DATASETS FOR TRAINING NEURAL NETWORKS

NºPublicación: WO2020102733A1 22/05/2020

Solicitante:

NVIDIA CORP [US]

US_2020160178_A1

Resumen de: WO2020102733A1

In various examples, a generative model is used to synthesize datasets for use in training a downstream machine learning model to perform an associated task. The synthesized datasets may be generated by sampling a scene graph from a scene grammar - such as a probabilistic grammar - and applying the scene graph to the generative model to compute updated scene graphs more representative of object attribute distributions of real-world datasets. The downstream machine learning model may be validated against a real-world validation dataset, and the performance of the model on the real-world validation dataset may be used as an additional factor in further training or fine-tuning the generative model for generating the synthesized datasets specific to the task of the downstream machine learning model.

traducir

EXTRACTING PROGRAM FEATURES FOR ASSISTING SOFTWARE DEVELOPMENT

NºPublicación: US2020159505A1 21/05/2020

Solicitante:

MICROSOFT TECHNOLOGY LICENSING LLC [US]

Resumen de: US2020159505A1

Improving the results and process of machine learning service in computer program development. A client's codebase is accessed. A set of features are extracted from the client's codebase. One or more features from the set of features are then selected. Thereafter, at least one of the selected features is sent to a machine learning service that uses the received feature(s) to build custom model(s) for the client's computer system.

traducir

SYSTEM AND METHOD FOR MONITORING LAB PROCESSES AND PREDICTING THEIR OUTCOMES

NºPublicación: US2020160214A1 21/05/2020

Solicitante:

COGNIZANT TECH SOLUTIONS INDIA PVT LTD [IN]

Resumen de: US2020160214A1

A system for monitoring one or more lab processes and predicting their outcomes is provided. The system comprises a data acquisition module configured to acquire at least one of: ambient data and experimental data in real time from one or more lab resources and instruments. The system further comprises a process setup and monitoring module configured to receive the acquired data and facilitate setting-up and monitoring of one or more processes in real time utilizing the received data. The system furthermore comprises an experiment prediction module that is configured to obtain data from the data acquisition module and process setup and monitoring module. The experiment prediction module is further configured to employ one or more machine learning techniques on the obtained data to generate one or more patterns to predict outcomes of the one or more processes conducted in the lab in real time.

traducir

MOBILE DEVICE WITH PREDICTIVE ROUTING ENGINE

NºPublicación: US2020160223A1 21/05/2020

Solicitante:

APPLE INC [US]

US_2016212229_A1

Resumen de: US2020160223A1

A mobile device with a route prediction engine is provided that can predict current/future destinations or routes to destinations for the user, and can relay prediction information to the user. The engine includes a machine-learning engine that facilitates the formulation of predicted future destinations and/or future routes to destinations based on user-specific data. The user-specific data includes data about (1) previous destinations traveled, (2) previous routes taken, (3) locations of calendared events, (4) locations of events for which the user has electronic tickets, and/or (5) addresses parsed from e-mails and/or messages. The prediction engine relies on one or more of user-specific data stored on the device and data stored outside of the device by external devices/servers.

traducir

METHOD FOR DETECTION AND DIAGNOSIS OF LUNG AND PANCREATIC CANCERS FROM IMAGING SCANS

NºPublicación: US2020160997A1 21/05/2020

Solicitante:

UNIV CENTRAL FLORIDA RES FOUND INC [US]

Resumen de: US2020160997A1

A method of detecting and diagnosing cancers characterized by the presence of at least one nodule/neoplasm from an imaging scan is presented. To detect nodules in an imaging scan, a 3D CNN using a single feed forward pass of a single network is used. After detection, risk stratification is performed using a supervised or an unsupervised deep learning method to assist in characterizing the detected nodule/neoplasm as benign or malignant. The supervised learning method relies on a 3D CNN used with transfer learning and a graph regularized sparse MTL to determine malignancy. The unsupervised learning method uses clustering to generate labels after which label proportions are used with a novel algorithm to classify malignancy. The method assists radiologists in improving detection rates of lung nodules to facilitate early detection and minimizing errors in diagnosis.

traducir

High recall additive pattern recognition for image and other applications

NºPublicación: US2020160035A1 21/05/2020

Solicitante:

SHUTTERFLY LLC [US]

US_2019244009_A1

Resumen de: US2020160035A1

A computer-implemented method includes selecting a kernel and kernel parameters for a first Support Vector Machine (SVM) model, testing the first SVM model on a feature matrix T of n feature vectors of length m to produce false positive (FP) data set and false negative (FN) data set by a computer processor, wherein n and m are integer numbers, automatically removing feature vectors corresponding to the FP data set from the feature matrix T by the computer processor to produce a feature matrix T_best, retraining the first SVM model on the feature matrix T_best to produce a second SVM model, and checking if a ratio (T_best sample number)/(SVM support vector number) is above a threshold for the second SVM model on T_best. If the ratio is above the threshold, SVM predictions are performed using the second SVM model on the feature matrix T_best.

traducir

SYSTEM AND METHOD FOR A CONVOLUTIONAL NEURAL NETWORK FOR MULTI-LABEL CLASSIFICATION WITH PARTIAL ANNOTATIONS

NºPublicación: US2020160177A1 21/05/2020

Solicitante:

ROYAL BANK OF CANADA [CA]

Resumen de: US2020160177A1

Effectively training machine learning systems with incomplete/partial labels is a practical, technical problem that solutions described herein attempt to overcome. In particular, an approach to modify loss functions on a proportionality basis is noted in some embodiments. In other embodiments, a graph neural network is provided to help identify correlations/causations as between categories. In another set of embodiments, a prediction approach is described to, based on originally provided labels, predict labels for unlabelled training samples such that the proportion of labelled labels relative to all labels is increased.

traducir

MACHINE LEARNING CLASSIFICATION AND PREDICTION SYSTEM

NºPublicación: AU2020202909A1 21/05/2020

Solicitante:

ACCENTURE GLOBAL SOLUTIONS LTD [IE]

AU_2018271385_A1

Resumen de: AU2020202909A1

A machine learning and predictive analytics system, including one or more data stores to store and manage data within a network, one or more servers to facilitate operations using information from the one or more data stores, and a processing system using machine learning and predictive analytics, the processing system including a data access interface to receive data associated with a subject, wherein the data is received from a data source including an internal data source and an external data source, wherein the internal data source includes a financial database of a financial institution associated with the subject, and the external data source includes a public database and a web feed associated with the subject, the public database associated with a census database and including population data, and the web feed including data from social media, RSS, syndication, aggregators, and web scraping, and a processor to execute machine-readable instructions stored on at least one non-transitory computer readable medium, the processor analyzing, based on a clustering technique, the data associated with the subject to predict a future life event, the clustering technique including at least one of agglomerative hierarchical clustering, Bayesian hierarchical clustering, K-means clustering, mean-shift clustering, density-based special clustering of applications with noise (DBSCAN), expectation-maximization (EM) based clustering or Gaussian Mixture Model (GMM) based clustering, calcu

traducir

INTENT-ORIENTED INTERNET BROWSING

NºPublicación: US2020159790A1 21/05/2020

Solicitante:

BARBOSA NATA [BR]
WANG YANG [US]
UNIV SYRACUSE [US]

Resumen de: US2020159790A1

A system that provides intent-oriented browsing powered by machine learning and crowdsourcing. The system allows users to enter their intents, which are then assigned to target pages via supervised learning models based on hyperlinks and contributions made by other users. The system has a prediction server that is programmed to receive hyperlinks from a website and return target hyperlinks based on known intent, a user interface for inputting user intent, and a browser programmed to connect to the intent repository and to the prediction server via a user script. The list of supported intents can grow over time based on correct page marks for intent-page mappings as well as via continuous training of machine learning models.

traducir

MACHINE LEARNING APPROACH FOR QUERY RESOLUTION VIA A DYNAMIC DETERMINATION AND ALLOCATION OF EXPERT RESOURCES

NºPublicación: US2020160224A1 21/05/2020

Solicitante:

STARMIND AG [CH]

US_2020125993_A1

Resumen de: US2020160224A1

The systems and methods described herein relate to mapping and identifying expert resources. The systems and methods described herein may provide a set of technologies, that work together as one solution, to effectively and efficiently resolve user questions. A cognitive engine may autonomously learn which experts have the knowledge to quickly solve a question or whether a previous question is similar enough to provide a solution instantly. Using machine learning, a know-how map may be created, linking all of the users of the system with their areas of expertise. Expert resources among the users may be mapped by determining connections between topics (and their corresponding tags) and calculating an expert score related to each topic for each user. These connections and expert scores are subsequently used during expert routing for each new question, to find those users with the expertise to give the best possible solution.

traducir

LEARNING TO GENERATE SYNTHETIC DATASETS FOR TRANING NEURAL NETWORKS

NºPublicación: US2020160178A1 21/05/2020

Solicitante:

NVIDIA CORP [US]

Resumen de: US2020160178A1

In various examples, a generative model is used to synthesize datasets for use in training a downstream machine learning model to perform an associated task. The synthesized datasets may be generated by sampling a scene graph from a scene grammar—such as a probabilistic grammar—and applying the scene graph to the generative model to compute updated scene graphs more representative of object attribute distributions of real-world datasets. The downstream machine learning model may be validated against a real-world validation dataset, and the performance of the model on the real-world validation dataset may be used as an additional factor in further training or fine-tuning the generative model for generating the synthesized datasets specific to the task of the downstream machine learning model.

traducir

METHOD AND SYSTEM FOR PREDICTING A MOTION TRAJECTORY OF A ROBOT MOVING BETWEEN A GIVEN PAIR OF ROBOTIC LOCATIONS

NºPublicación: US2020160210A1 21/05/2020

Solicitante:

SIEMENS IND SOFTWARE LTD [IL]

EP_3656513_A1

Resumen de: US2020160210A1

Systems and a method for predicting a motion trajectory of a robot moving between a given pair of robotic locations. Training data of motion trajectories of the robot are received for a plurality of robotic location pairs. The training data are processed so as to obtain x tuples and y tuples for machine learning purposes; wherein the x tuples describe the robotic location pair and the y tuples describe one or more intermediate robotic locations at specific time stamps during the motion of the robot between the locations of the location pair. From the processed data, a function is learned for mapping the x tuples into the y tuples so as to generate a motion prediction module for the robot. For a given robotic location pair, the robotic motion between the given pair is predicted by obtaining the corresponding intermediate locations resulting from the motion prediction module.

traducir

SYSTEMS AND METHODS FOR IMPLEMENTING AN INTELLIGENT APPLICATION PROGRAM INTERFACE FOR AN INTELLIGENT OPTIMIZATION PLATFORM

NºPublicación: US2020151029A1 14/05/2020

Solicitante:

SIGOPT INC [US]

US_2019391859_A1

Resumen de: US2020151029A1

Systems and methods for implementing an application programming interface (API) that controls operations of a machine learning tuning service for tuning a machine learning model for improved accuracy and computational performance includes an API that is in control communication the tuning service that: executes a first API call function that includes an optimization work request that sets tuning parameters for tuning hyperparameters of a machine learning model; and initializes an operation of distinct tuning worker instances of the service that each execute distinct tuning tasks for tuning the hyperparameters; executes a second API call function that identifies raw values for the hyperparameters; and generates suggestions comprising proposed hyperparameter values selected from the plurality of raw values for each of the hyperparameters; and executes a third API call function that returns performance metrics relating to a real-world performance of the subscriber machine learning model executed with the proposed hyperparameter values.

traducir

Applied Artificial Intelligence Technology for Processing Trade Data to Detect Patterns Indicative of Potential Trade Spoofing

NºPublicación: US2020151565A1 14/05/2020

Solicitante:

TRADING TECHNOLOGIES INT INC [US]

US_10552735_B1

Resumen de: US2020151565A1

Various techniques are described for using machine-learning artificial intelligence to improve how trading data can be processed to detect improper trading behaviors such as trade spoofing. In an example embodiment, semi-supervised machine learning is applied to positively labeled and unlabeled training data to develop a classification model that distinguishes between trading behavior likely to qualify as trade spoofing and trading behavior not likely to qualify as trade spoofing. Also, clustering techniques can be employed to segment larger sets of training data and trading data into bursts of trading activities that are to be assessed for potential trade spoofing status.

traducir

INFORMATION EXTRACTION FROM DOCUMENTS

NºPublicación: US2020151591A1 14/05/2020

Solicitante:

MOCSY INC [CA]

CA_3052113_A1

Resumen de: US2020151591A1

There is provided a method including sending a first document to a GUI, and receiving at a classification and extraction engine (CEE) from the GUI an input indicating first document data for the first document. The input forms a portion of a dataset. A prediction is generated at the CEE of second document data for a second document using a machine learning model (MLM) configured to receive an input and generate a predicted output. The MLM is trained using the dataset, the input includes one or more tokens corresponding to the second document. The output includes the prediction of the second document data. The prediction is sent to the GUI, and feedback on the prediction is received at the CEE from the GUI, to form a reviewed prediction. The reviewed prediction is added to the dataset to form an enlarged dataset, and the MLM is trained using the enlarged dataset.

traducir

AUTOMATED TRAINING AND EXERCISE ADJUSTMENTS BASED ON SENSOR-DETECTED EXERCISE FORM AND PHYSIOLOGICAL ACTIVATION

NºPublicación: US2020151595A1 14/05/2020

Solicitante:

MAD APPAREL INC [US]

Resumen de: US2020151595A1

The invention(s) described are configured to process sensor data in order to optimize or otherwise improve training of users for achievement of goals in relation to performing an activity. The invention(s) can also iteratively adapt training in a personalized manner, with assessment of training results and subsequent modification of training regimens, in order to provide improved alignment between users and their goals. Such iteration can drive interventions provided to users throughout the course of training, and allow the system to iteratively develop better and more precise interventions (e.g., through manual means, through machine learning models with generated training and test data). Such iteration, with large datasets applied to populations of users can also increase the breadth of user states that the can be addressed, with respect to provided interventions, and improve rates at which interventions are provided.

traducir

CONTEXT-DEPENDENT TIMEOUT FOR REMOTE SECURITY SERVICES

NºPublicación: US2020153849A1 14/05/2020

Solicitante:

SOPHOS LTD [GB]

US_2019342312_PA

Resumen de: US2020153849A1

A threat management facility that remotely stores global reputation information for network content can be used in combination with a recognition engine such as a machine learning classifier that is locally deployed on endpoints within an enterprise network. More specifically, the recognition engine can locally evaluate reputation for a network address being accessed by an endpoint, and this reputation information can be used to dynamically establish a timeout for a request from the endpoint to the threat management facility for corresponding global reputation information.

traducir

DETECTING A TRANSACTION VOLUME ANOMALY

NºPublicación: US2020151728A1 14/05/2020

Solicitante:

CAPITAL ONE SERVICES LLC [US]

US_10445738_B1

Resumen de: US2020151728A1

A server device obtains historical transaction data regarding transactions involving a network service, obtains historical calendar data regarding static date information for a historical time period that corresponds with the historical transaction data, and processes the historical transaction data and historical calendar data to train a machine learning model using a gradient boosting machine learning technique to predict a normal transaction volume for a period of time and confidence bands associated with the normal transaction volume. The server device generates the normal transaction volume for the period of time and confidence bands using the machine learning model, obtains real-time data concerning a transaction volume during the period of time, detects a transaction volume anomaly based on comparing the real-time data and normal transaction volume and confidence bands, and sends an alert, based on the transaction volume anomaly, to cause a remote device to display the alert and perform an action.

traducir

Automated Extraction, Inference and Normalization of Structured Attributes for Product Data

NºPublicación: US2020151201A1 14/05/2020

Solicitante:

SEMANTICS3 INC [US]

Resumen de: US2020151201A1

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for automated extraction, inference and normalization of structured attributes for a Product Category Normalizer to access product records from external data sources. The Product Category Normalizer defines a product-description taxonomy of product categories represented by a classification tree. The Product Category Normalizer employs product attribute data and machine learning techniques to analyze the product data of an input product record. Based on the product data of the input product record, the Product Category Normalizer extracts and infers appropriate product data for a relevant product category in the classification tree for the item described by the input product record. The Product Category Normalizer normalizes the product data of the input product record. The Product Category Normalizer provides an output normalized product record related to a product category and product attributes of the classification tree.

traducir

METHODS AND SYSTEMS FOR DATA COLLECTION, LEARNING, AND STREAMING OF MACHINE SIGNALS FOR ANALYTICS AND MAINTENANCE USING THE INDUSTRIAL INTERNET OF THINGS

NºPublicación: US2020150643A1 14/05/2020

Solicitante:

STRONG FORCE IOT PORTFOLIO 2016 LLC [US]

US_2020150644_A1

Resumen de: US2020150643A1

An industrial machine predictive maintenance system may include an industrial machine data analysis facility that generates streams of industrial machine health monitoring data by applying machine learning to data representative of conditions of portions of industrial machines received via a data collection network. The system may include an industrial machine predictive maintenance facility that produces industrial machine service recommendations responsive to the health monitoring data by applying machine fault detection and classification algorithms thereto. The system may perform a method of predicting a service event from vibration data captured data from at least one vibration sensor disposed to capture vibration of a portion of an industrial machine. A signal in a predictive maintenance circuit for executing a maintenance action on the portion of the industrial machine can be generated based on a severity unit calculated for the captured vibration.

traducir

METHOD AND SYSTEM FOR IMPLEMENTING A CLOUD MACHINE LEARNING ENVIRONMENT

NºPublicación: US2020151346A1 14/05/2020

Solicitante:

JPMORGAN CHASE BANK NA [US]

Resumen de: US2020151346A1

An embodiment of the present invention is directed to leveraging GPU farms for machine learning where the selection of data is self-service. The data may be cleansed based on a classification and automatically transferred to a cloud services platform. This allows an entity to leverage the commoditization of the GPU farms in the public cloud without exposing data into that cloud. Also, an entire creation of a ML instance may be fully managed by a business analyst, data scientist and/or other users and teams.

traducir

SYSTEM AND METHOD FOR IMPLEMENTING AN ARTIFICIALLY INTELLIGENT VIRTUAL ASSISTANT USING MACHINE LEARNING

NºPublicación: US2020151566A1 14/05/2020

Solicitante:

CLINC INC [US]

US_2019156198_PA

Resumen de: US2020151566A1

Systems and methods for implementing an artificially intelligent virtual assistant includes collecting a user query; using a competency classification machine learning model to generate a competency label for the user query; using a slot identification machine learning model to segment the text of the query and label each of the slots of the query; generating a slot value for each of the slots of the query; generating a handler for each of the slot values; and using the slot values to: identify an external data source relevant to the user query, fetch user data from the external data source, and apply one or more operations to the query to generate response data; and using the response data, to generate a response to the user query.

traducir

ANALYZING VIEWER BEHAVIOR IN REAL TIME

Nº publicación: US2020151587A1 14/05/2020

Solicitante:

DISNEY ENTPR INC [US]

CN_111181916_A

Resumen de: US2020151587A1

Systems, methods and articles of manufacture for are provided for analyzing user behavior in real time by ingesting telemetry data related to a streaming media application; feeding the telemetry data to a machine learning model (MLM) that produces a User Experience (UX) command based on the telemetry data and prior telemetry data received from the content streaming application; selecting content items to provide to the client device based on the telemetry data; determining, based on the telemetry data, whether the client device has sufficient free resources to receive the UX command and the content items in a current time window while providing a predefined level of service; when client device has sufficient free resources to receive the UX command and the content items, encapsulating the UX command with the content items in a content stream; and transmitting the content stream to the client device.

traducir

Página1 de 5 nextPage por página

punteroimgVolver