Full text data for US,EP,CN
Legal Validity
Legal Status
Filing Date
Publication Date
Click to expand
Claims Number
Figures Number
Citation Number of Times
Assignee Number
No. Publication Number Title Publication/Patent Number Publication/Patent Number Publication Date Publication Date
Application Number Application Number Filing Date Filing Date
Inventor Inventor Assignee Assignee IPC IPC
Dataset augmentation based on occlusion and inpainting
Publication/Patent Number: US11017311B2 Publication Date: 2021-05-25 Application Number: 14/318,871 Filing Date: 2014-06-30 Inventor: Chandler, Benjamin Orth   Assignee: Hewlett Packard Enterprise Development LP   IPC: G06F15/18 Abstract: Augmenting a dataset in a machine learning classifier is disclosed. One example is a system including a training dataset with at least one training data, and a label preserving transformation including an occluder, and an inpainter. The occluder occludes a selected portion of the at least one training data. The inpainter inpaints the occluded portion of the at least one training data, where the inpainting is based on data from a portion different from the occluded portion. In one example, the augmented dataset is deployed to train a machine learning classifier.
Method and apparatus for decision making in a neural model including semantic, episodic, and procedural memory components
Publication/Patent Number: US10984314B1 Publication Date: 2021-04-20 Application Number: 14/750,402 Filing Date: 2015-06-25 Inventor: Chelian, Suhas E.   Ascoli, Giorgio A.   Benvenuto, James   Howard, Michael D.   Bhattacharyya, Rajan   Assignee: HRL Laboratories, LLC   IPC: G06F15/18 Abstract: Described is a system for selecting among intelligence elements of a neural model. An intelligence element is selected from a set of intelligence elements which change group attack probability estimates and processed via multiple operations. A semantic memory component learns group probability distributions and rules based on the group probability distributions. The rules determine which intelligence element related to the groups to select. Given an environment of new probability distributions, the semantic memory component recalls which rule to select to receive a particular intelligence element. An episodic memory component recalls a utility value for each information element A procedural memory component recalls and selects the information element considered to have the highest utility. A list of intelligence elements is published to disambiguate likely attackers.
Process monitoring based on large-scale combination of time series data
Publication/Patent Number: US11080613B1 Publication Date: 2021-08-03 Application Number: 15/141,981 Filing Date: 2016-04-29 Inventor: Camara, Mauricio Melo   Ciarlini, Angelo E. M.   Dias, Jonas F.   Maximo, André   Da, Silva Pinto José Carlos Costa   Barros, Monica   Soares, Rafael Marinho   De, Sa Feital Thiago   Assignee: EMC IP Holding Company LLC   IPC: G06F15/18 Abstract: Methods and apparatus are provided for process monitoring based on large-scale combinations of time series data. An exemplary method comprises generating a model from time series data for a given target time series; determining whether a first difference between measured values and predicted values based on the model exceeds a predefined threshold indicating a target prediction error; in response to a detected target prediction error, performing evaluations of (i) a neighborhood coherence comprising an average of variables of the model weighted by corresponding coefficients on a predefined neighborhood time window, and/or (ii) a second difference between a given value of at least one variable in the model and an average value of the at least one variable based on a training dataset; providing notifications when first predefined criteria based on the evaluations are satisfied; and updating the model when second predefined criteria based on the evaluations are satisfied.
Evolutionary techniques for computer-based optimization and artificial intelligence systems
Publication/Patent Number: US11010672B1 Publication Date: 2021-05-18 Application Number: 15/694,586 Filing Date: 2017-09-01 Inventor: Hazard, Christopher James   Assignee: Google LLC   IPC: G06F15/18 Abstract: Techniques are provided for evolutionary computer-based optimization and artificial intelligence systems, and include receiving first and second candidate executable code (with ploidy of at least two and one, respectively) each selected at least in part based on a fitness score. The first candidate executable code and the second candidate executable code are combined to produce resultant executable code of the desired ploidy. A fitness score is determined for the resultant executable code, and a determination is made whether the resultant executable code will be used as a future candidate executable code based at least in part on the third fitness score. If an exit condition is met, then the resultant executable code is used as evolved executable code.
Generic quantization of artificial neural networks
Publication/Patent Number: US11068784B2 Publication Date: 2021-07-20 Application Number: 16/258,552 Filing Date: 2019-01-26 Inventor: De, Vangel Benoit Chappet   Moutoussamy, Vincent   Larzul, Ludovic   Assignee: MIPSOLOGY SAS   IPC: G06F15/18 Abstract: Systems and methods for performing a quantization of artificial neural networks (ANNs) are provided. An example method may include receiving a description of an ANN and input data associated with the ANN, wherein the input data are represented according to a first data type; selecting a first value interval of the first data type to be mapped to a second value interval of a second data type; performing, based on the input data and the description of the ANN, the computations of one or more neurons of the ANN, wherein the computations are performed for at least one value within the second value interval, the value being a result of mapping a value of the first value interval to a value of the second value interval; determining, a measure of saturations in neurons of the ANN, and adjusting, based on the measure of saturations, the value intervals.
Machine learning model training method and device, and electronic device
Publication/Patent Number: US10943186B2 Publication Date: 2021-03-09 Application Number: 16/813,268 Filing Date: 2020-03-09 Inventor: Guo, Long   Assignee: ADVANCED NEW TECHNOLOGIES CO., LTD.   IPC: G06F15/18 Abstract: A machine learning model training method includes: classifying samples having risk labels in a training sample set as positive samples and classifying samples without risk labels in the training sample set as negative samples; training a risk model with a machine learning method based on the positive samples and the negative samples; obtaining a risk score for each of the negative samples based on the trained risk model; identifying one or more negative samples in the training sample set that have a risk score greater than a preset threshold value; re-classifying the one or more negative samples in the training sample set that have a risk score greater than the preset threshold value as re-classified positive samples to generate an updated training sample set from the training sample set; and re-training the risk model with the machine learning method based on the updated training sample set.
Synthesis of security exploits via self-amplifying deep learning
Publication/Patent Number: US11048777B2 Publication Date: 2021-06-29 Application Number: 16/658,839 Filing Date: 2019-10-21 Inventor: Chakraborty, Supriyo   Tripp, Omer   Assignee: INTERNATIONAL BUSINESS MACHINES CORPORATION   IPC: G06F15/18 Abstract: Techniques for synthesizing security exploits via self-amplifying deep learning are provided. In one example, a computer-implemented method can comprise generating, by a system operatively coupled to a processor, a probabilistic model based on an evaluation of one or more first payloads included in a first group of payloads. The computer implemented method can also comprise determining, by the system, based on the probabilistic model, that at least one first payload from the first group of payloads is invalid. Additionally, the computer implemented method can comprise, generating, by the system, a second group of payloads based on removing the at least one invalid first payload from the first group of payloads.
Multi-dimensional sensor data based human behaviour determination system and method
Publication/Patent Number: US10909462B2 Publication Date: 2021-02-02 Application Number: 15/160,440 Filing Date: 2016-05-20 Inventor: Ghose, Avik   Pal, Arpan   Pal, Arindam   Chattopadhyay, Tanushyam   Maiti, Santa   Assignee: TATA CONSULTANCY SERVICES LIMITED   IPC: G06F15/18 Abstract: A multi-dimensional sensor data analysis system and method is provided. The multi-dimensional sensor data analysis system receives indoor and outdoor location, online and physical activity, online and physical proximity and additional a plurality of inputs (specific to a user), for example, surrounding of the subject, physiological parameters of the subject and recent social status of the subject, both online and offline. The multi-dimensional sensor data analysis system processes these inputs along with the knowledge of past behavior and traditional parameters of location, proximity and activity by performing a multi-dimensional sensor data analysis fusion technique, producing one or more outputs, for example, predicting or determining a human behaviour to a given stimuli.
Machine learning with small data sets
Publication/Patent Number: US10963743B2 Publication Date: 2021-03-30 Application Number: 15/996,073 Filing Date: 2018-06-01 Inventor: Lecue, Freddy   Bouhini, Chahrazed   Assignee: Accenture Global Solutions Limited   IPC: G06F15/18 Abstract: Implementations include receiving a predicted value and confidence level from a first ML model, and determining that the confidence level is below a threshold, and in response: providing an encoding based on input data and non-textual information to the first ML model, the encoding representing characteristics of the input data relative to the predicted value, the characteristics including respective gradients of features of the input data, injecting the encoding into a textual knowledge graph that corresponds to a domain of the first ML model to provide an encoded knowledge graph, receiving supplemental data based on the encoded knowledge graph, and providing a supplemental predicted value from a second ML model based on the input data and the supplemental data, the second ML model having a higher number of features than the first ML model, and the supplemental predicted value having a supplemental confidence level that exceeds the threshold.
Method, apparatus and computer program product for determining failure regions of an electrical device
Publication/Patent Number: US11093851B2 Publication Date: 2021-08-17 Application Number: 14/029,883 Filing Date: 2013-09-18 Inventor: Dobler, Markus   Assignee: Infineon Technologies AG   IPC: G06F15/18 Abstract: One or more failure regions are determined for an electrical device by training a machine learning classifier, including analyzing data points for the device and recognizing patterns in the data points. Each data point indicates pass or fail of the device for a particular combination of factors relating to the operation of the device. The trained machine learning classifier is used to predict the pass/fail state of new data points for the electrical device. Each new data point corresponds to a new combination of the factors relating to the operation of the device not previously analyzed by the machine learning classifier. A pass/fail border region can be identified for the electrical device based on the training of the machine learning classifier, the pass/fail border region excluding data points for which the electrical device is expected to pass or fail with a high degree of certainty.
Implementing Machine Learning For Life And Health Insurance Loss Mitigation And Claims Handling
Publication/Patent Number: US2021256615A1 Publication Date: 2021-08-19 Application Number: 16/136,365 Filing Date: 2018-09-20 Inventor: Hayward, Gregory L.   Goldfarb, Meghan Sims   Christopulos, Nicholas U.   Donahue, Erik   Assignee: State Farm Mutual Automobile Insurance Company   IPC: G06Q40/08 Abstract: Techniques for implementing machine learning for insurance loss mitigation or prevention, and claims handling are disclosed. In some scenarios, the insurance loss mitigation and claims handling may be associated with a disability, worker's compensation, life or health insurance policy, and the machine-learning analytics model may be trained in accordance with data that is relevant to identifying appropriate predictions in accordance with these particular types of insurance products. For instance, the machine-learning analytics model may utilize information within a dynamic data set as training data, which may include electronically accessible information. The machine-learning analytics model may additionally be implemented to identify various predictions that are indicative of a risk of insuring an individual as well as one or more actions that, when performed, may reduce the initial calculation of risk.
Hierarchical classifiers
Publication/Patent Number: US11042815B2 Publication Date: 2021-06-22 Application Number: 15/729,362 Filing Date: 2017-10-10 Inventor: Hagen, Josiah Dede   Niemczyk, Brandon   Assignee: Trend Micro Incorporated   IPC: G06F15/18 Abstract: Examples relate to providing hierarchical classifiers. In some examples, a superclass classifier of a hierarchy of classifiers is trained with a first type of prediction threshold, where the superclass classifier classifies data into one of a number of subclasses. At this stage, a subclass classifier is trained with a second type of prediction threshold, where the subclass classifier classifies the data into one of a number of classes. The first type of prediction threshold of the superclass classifier and the second type of prediction threshold of the subclass classifier are alternatively applied to classify data segments.
Method and system for making recommendations from binary data using neighbor-score matrix and latent factors
Publication/Patent Number: US10932003B2 Publication Date: 2021-02-23 Application Number: 14/975,872 Filing Date: 2015-12-21 Inventor: Volkovs, Maksims   Poutanen, Tomi   Assignee: The Toronto-Dominion Bank   IPC: G06F15/18 Abstract: One embodiment is a method executed by a computer system that applies collaborative filtering to provide a recommendation to a user. The method includes retrieving a binary matrix that includes rows and columns of binary data for preferences of users on items; applying a neighborhood-based approach to convert the binary matrix into a neighbor-score matrix; applying a factorization to approximate the neighbor-score matrix with a product of lower rank matrices; calculating a user factor and an item factor based on the factorization; calculating scores for user-item pairs by computing a dot product between the user factor and the item factor; sorting the scores of the user-item pairs to generate the recommendation to the user; and providing the recommendation to a general-purpose computer of the user.
Cross-channel recommendation processing
Publication/Patent Number: US10997613B2 Publication Date: 2021-05-04 Application Number: 15/142,028 Filing Date: 2016-04-29 Inventor: Leung, Ronald Chiwai   Licht, Yehoshua Zvi   Tripathi, Pragya   Turner, David Allen   Assignee: NCR Corporation   IPC: G06F15/18 Abstract: Cross-channel and cross-source data are aggregated into an aggregated data store. Custom segmentation is generated from the aggregated data. A campaign is monitored for the custom segmentation with successes and failures provided as dynamic feedback to a machine learning process that dynamically adjusts the segmentation and the campaign for optimal performance. In an embodiment, a final recommendation is provided identifying a final optimal segmentation and campaign.
Recommendation system construction method and apparatus
Publication/Patent Number: US10902332B2 Publication Date: 2021-01-26 Application Number: 16/725,589 Filing Date: 2019-12-23 Inventor: Chen, Chaochao   Zhou, Jun   Assignee: Advanced New Technologies Co., Ltd.   IPC: G06F15/18 Abstract: A client device determines a local user gradient value based on a current user preference vector and a local item gradient value based on a current item feature vector. The client device updates a user preference vector by using the local user gradient value and updates an item feature vector by using the local item gradient value. The client device determines a neighboring client device based on a predetermined adjacency relationship. The local item gradient value is sent by the client device to the neighboring client device. The client device receives a neighboring item gradient value sent by the neighboring client device. The client device updates the item feature vector by using the neighboring item gradient value. In response to the client device determining that a predetermined iteration stop condition is satisfied, the client device outputs the user preference vector and the item feature vector.
Predicting API storytelling mapping
Publication/Patent Number: US10990895B2 Publication Date: 2021-04-27 Application Number: 15/399,766 Filing Date: 2017-01-06 Inventor: Deluca, Marco A.   Nigul, Leho   Assignee: International Business Machines Corporation   IPC: G06F15/18 Abstract: A first indication from a user is received. The indication includes a task to be performed using at least one application programming interface. A machine learning model is determine. At least one application programming interface is determined using the machine learning model and the request. The at least one application programming interface is provided to the user.
Computer-based systems and methods configured to utilize automating deployment of predictive models for machine learning tasks
Publication/Patent Number: US10891327B1 Publication Date: 2021-01-12 Application Number: 16/511,671 Filing Date: 2019-07-15 Inventor: Wu, Chen   Assignee: Capital One Services, LLC   IPC: G06F15/18 Abstract: A method includes obtaining feature generation code from, which is configured to determine features relating to input data. The method further includes obtaining data grouping code, which is configured to generate training data by determining a plurality of data groupings for the features relating to the input data. The method further includes obtaining modeling code, which is derived at least in part by applying one or more machine learning algorithms to the training data. The method further includes applying a model wrapper code to the feature generation code, the data grouping code, and the modeling code to generate a model wrapper and deploying the model wrapper such that the model wrapper may receive a first application programming interface (API) call including an input data value, determine a score relating to the input data value, and send a second API call including the score in response to the first API call.
Systems and techniques for predictive data analytics
Publication/Patent Number: US10984367B2 Publication Date: 2021-04-20 Application Number: 15/587,951 Filing Date: 2017-05-05 Inventor: Achin, Jeremy   Degodoy, Thomas   Owen, Timothy   Conort, Xavier   Assignee: DataRobot, Inc.   IPC: G06F15/18 Abstract: Systems and techniques for predictive data analytics are described. In a method for selecting a predictive model for a prediction problem, the suitabilities of predictive modeling procedures for the prediction problem may be determined based on characteristics of the prediction problem and/or on attributes of the respective modeling procedures. A subset of the predictive modeling procedures may be selected based on the determined suitabilities of the selected modeling procedures for the prediction problem. A resource allocation schedule allocating computational resources for execution of the selected modeling procedures may be generated, based on the determined suitabilities of the selected modeling procedures for the prediction problem. Results of the execution of the selected modeling procedures in accordance with the resource allocation schedule may be obtained. A predictive model for the prediction problem may be selected based on those results.
Estimating the amount of degradation with a regression objective in deep learning
Publication/Patent Number: US11074506B2 Publication Date: 2021-07-27 Application Number: 16/646,169 Filing Date: 2018-09-17 Inventor: Baker, James K.   Baker, Bradley J.   Assignee: D5AI LLC   IPC: G06F15/18 Abstract: Computer systems and computer-implemented methods train a machine-learning regression system. The method comprises the step of generating, with a machine-learning generator, output patterns; distorting the output patterns of the generator by a scale factor to generate distorted output patterns; and training the machine-learning regression system to predict the scaling factor, where the regression system receives the distorted output patterns as input and learns and the scaling factor is a target value for the regression system. The method may further comprise, after training the machine-learning regression system, training a second machine-learning generator by back propagating partial derivatives of an error cost function from the regression system to the second machine-learning generator and training the second machine-learning generator using stochastic gradient descent.
Intelligent image note processing
Publication/Patent Number: US11100160B2 Publication Date: 2021-08-24 Application Number: 16/051,359 Filing Date: 2018-07-31 Inventor: Frank, Paul A. R.   Keen, Martin G.   Smye-rumsby, Adam   Cunico, Hernan A.   Assignee: INTERNATIONAL BUSINESS MACHINES CORPORATION   IPC: G06F17/30 Abstract: Embodiments for intelligent image note processing by a processor. One or more images associated with a user equipment (UE) may be determined to have notation data. The notation data may be extracted from the one or more images to create one or more actions in relation to the notation data.
Total 500 pages