Patents Examined by Miranda M Huang
-
Patent number: 11966846Abstract: An encoding apparatus connected to a learning circuit processing learning of a deep neural network and configured to perform encoding for reconfiguring connection or disconnection of a plurality of edges in a layer of the deep neural network using an edge sequence generated based on a random number sequence and dropout information indicating a ratio between connected edges and disconnected edges of a plurality of edges included in a layer of the deep neural network.Type: GrantFiled: February 21, 2019Date of Patent: April 23, 2024Assignee: SAMSUNG ELECTRONICS CO., LTD.Inventors: Sungho Kang, Hyungdal Kwon, Cheon Lee, Yunjae Lim
-
Patent number: 11952693Abstract: Software and lasers are used in finishing apparel to produce a desired wear pattern or other design. A technique includes using machine learning to create or extract a laser input file for wear pattern from an existing garment. Machine learning can be by a generative adversarial network, having generative and discriminative neural nets. The generative adversarial network is trained and then used to create a model. This model is used generate the laser input file from an image of the existing garment with the finishing pattern. With this laser input file, a laser can re-create the wear pattern from the existing garment onto a new garment.Type: GrantFiled: October 31, 2018Date of Patent: April 9, 2024Assignee: Levi Strauss & Co.Inventors: Jennifer Schultz, Benjamin Bell, Debdulal Mahanty, Christopher Schultz
-
Patent number: 11948062Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for implementing a compressed recurrent neural network (RNN). One of the systems includes a compressed RNN, the compressed RNN comprising a plurality of recurrent layers, wherein each of the recurrent layers has a respective recurrent weight matrix and a respective inter-layer weight matrix, and wherein at least one of recurrent layers is compressed such that a respective recurrent weight matrix of the compressed layer is defined by a first compressed weight matrix and a projection matrix and a respective inter-layer weight matrix of the compressed layer is defined by a second compressed weight matrix and the projection matrix.Type: GrantFiled: December 4, 2020Date of Patent: April 2, 2024Assignee: Google LLCInventors: Ouais Alsharif, Rohit Prakash Prabhavalkar, Ian C. McGraw, Antoine Jean Bruguier
-
Patent number: 11941522Abstract: The present disclosure discloses an address information feature extraction method based on a deep neural network model. The present disclosure uses a deep neural network architecture, and transforms tasks, such as text feature extraction, address standardization construction and semantic-geospatial fusion, into quantifiable deep neural network model construction and training optimization problems. Taking a character in an address as a basic input unit, the address language model is designed to express it in vectors, then a key technology of standardization construction of Chinese addresses is realized through neural network target tasks.Type: GrantFiled: September 28, 2020Date of Patent: March 26, 2024Assignee: ZHEJIANG UNIVERSITYInventors: Feng Zhang, Ruichen Mao, Zhenhong Du, Liuchang Xu, Huaxin Ye
-
Patent number: 11941531Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for processing an input data element to generate a prediction output that characterizes the input data element. In one aspect, a method comprises: determining a respective attention weight between an input data element and each of a plurality of reference data elements; processing each of the reference data elements using the encoder neural network to generate a respective value embedding of each reference data element; determining a combined value embedding of the reference data elements based on (i) the respective value embedding of each reference data element, and (ii) the respective attention weight between the input data element and each reference data element; and processing the combined value embedding of the reference data elements using a prediction neural network to generate the prediction output that characterizes the input data element.Type: GrantFiled: February 7, 2020Date of Patent: March 26, 2024Assignee: Google LLCInventors: Sercan Omer Arik, Tomas Jon Pfister
-
Patent number: 11915131Abstract: In an approach to improve the efficiency of solving problem instances by utilizing a machine learning model to solve a sequential optimization problem. Embodiments of the present invention receive a sequential optimization problem for solving and utilize a random initialization to solve a first instance of the sequential optimization problem. Embodiments of the present invention learning, by a computing device a machine learning model, based on a previously stored solution to the first instance of the sequential optimization problem. Additionally, embodiments of the present invention generate, by the machine learning model, one or more subsequent approximate solutions to the sequential optimization problem; and output, by a user interface on the computing device, the one or more subsequent approximate solutions to the sequential optimization problem.Type: GrantFiled: November 23, 2020Date of Patent: February 27, 2024Assignee: International Business Machines CorporationInventors: Kartik Ahuja, Amit Dhurandhar, Karthikeyan Shanmugam, Kush Raj Varshney
-
Patent number: 11900262Abstract: A neural network system for processing a neural network model including an operation processing graph that includes a plurality of operations, includes an operation processor including an internal memory storing a first module input feature map. The operation processor is configured to obtain a first branch output feature map by performing a first operation among the plurality of operations, based on the stored first module input feature map, and obtain a second branch output feature map by performing a second operation among the plurality of operations after the first operation is performed, based on the stored first module input feature map. The internal memory maintains storage of the first module input feature map while the first operation is performed.Type: GrantFiled: January 9, 2020Date of Patent: February 13, 2024Assignee: SAMSUNG ELECTRONICS CO., LTD.Inventors: Kyoungyoung Kim, Sangsoo Ko, Doyun Kim, Sanghyuck Ha
-
Patent number: 11900250Abstract: A system and method for using a deep learning model to learn program semantics is disclosed. The method includes receiving a plurality of execution traces of a program, each execution trace comprising a plurality of variable values. The plurality of variable values are encoded by a first recurrent neural network to generate a plurality of program states for each execution trace. A bi-directional recurrent neural network can then determine a reduced set of program states for each execution trace from the plurality of program states. The reduced set of program states are then encoded by a second recurrent neural network to generate a plurality of executions for the program. The method then includes pooling the plurality of executions to generate a program embedding and predicting semantics of the program using the program embedding.Type: GrantFiled: October 1, 2019Date of Patent: February 13, 2024Assignee: Visa International Service AssociationInventor: Ke Wang
-
Patent number: 11894143Abstract: The invention relates generally to a system and method for integrating pet health records, and more specifically to an integrated pet health record that is configured to collect, store, maintain, analyze, and provide recommendations about a pet's health from a variety of sources. The system may analyze health conditions for a pet on both an individual basis and in regards to a global population. This analysis provides an assessment of the pet based on pet type, breed, age, weight, geographic location, living conditions, diet, exercise, and more. The system may also generate global statistics, providing various metrics that can be applied to sub-populations of pets. Advantageously, the system is configured to categorize causes and symptoms based on the pet's health conditions and how treatments can be refined to improve outcomes, and transmit that information to a client device.Type: GrantFiled: March 6, 2020Date of Patent: February 6, 2024Assignee: Whiskers Worldwide, LLCInventors: Debra Leon, Trevor Page, Gunnison Carbone
-
Patent number: 11894144Abstract: The invention relates generally to a system and method for animal health decision support, and more specifically to a non-human animal health decision support system that is configured to collect animal information, determine a health topic, and transmit a question set corresponding to the health topic. The system may analyze answers associated with the question set to determine a course of action. The course of action may be a recommendation, such as contacting a veterinarian, obtaining a relevant product, making an appointment with a veterinarian, watching for change in symptoms in the non-human animal, and transporting the non-human animal to a clinic. Advantageously, the system is configured to provide decision support and transmit that information to a client device.Type: GrantFiled: November 4, 2020Date of Patent: February 6, 2024Assignee: Whiskers Worldwide, LLCInventors: Debra Leon, Trevor Page, Gunnison Carbone
-
Patent number: 11887019Abstract: Systems, methods, and apparatuses are provided for permeability prediction. The method acquires data associated with one or more geological formations, calculates, using processing circuitry and a trained Hidden Markov model, log-likelihood values to group the data into a plurality of clusters, and trains an artificial neural network for each of the plurality of clusters when the mode of operation is training mode. Further, the method acquires one or more formation properties corresponding to a geological formation, determines using the trained Hidden Markov model, a log-likelihood score associated with the one or more formation properties, identifies a cluster associated with the one or more formation properties as a function of the log-likelihood score, and predicts a permeability based at least in part on the one or more formation properties and a trained artificial neural network associated with the identified cluster when the mode of operation is forecasting mode.Type: GrantFiled: February 14, 2020Date of Patent: January 30, 2024Assignee: KING FAHD UNIVERSITY OF PETROLEUM AND MINERALSInventors: Md Rafiul Hassan, Muhammad Imtiaz Hossain, Abdulazeez Abdulraheem
-
Patent number: 11886993Abstract: Disclosed are a method and apparatus for task scheduling based on deep reinforcement learning and a device. The method comprises: obtaining multiple target subtasks to be scheduled; building target state data corresponding to the multiple target subtasks, wherein the target state data comprises a first set, a second set, a third set, and a fourth set; inputting the target state data into a pre-trained task scheduling model, to obtain a scheduling result of each target subtask; wherein, the scheduling result of each target subtask comprises a probability that the target subtask is scheduled to each target node; for each target subtask, determining a target node to which the target subtask is to be scheduled based on the scheduling result of the target subtask, and scheduling the target subtask to the determined target node.Type: GrantFiled: September 9, 2020Date of Patent: January 30, 2024Assignee: BEIJING UNIVERSITY OF POSTS AND TELECOMMUNICATIONSInventors: Qi Qi, Haifeng Sun, Jing Wang, Lingxin Zhang, Jingyu Wang, Jianxin Liao
-
Patent number: 11880777Abstract: The described features of the present disclosure generally relate to one or more improved systems for analyzing the electronic information associated with driving activities (e.g., driver log information) obtained from the one or more mobile computing platforms (ELDs) associated with one or more vehicles to identify a likelihood of a driver resigning or deserting his or her position. Accordingly, features of the present disclosure may identify “at-risk” drivers for the fleet operators to trigger remedial measures to prevent such adverse event (e.g., driver quitting).Type: GrantFiled: January 23, 2017Date of Patent: January 23, 2024Assignee: OMNITRACS, LLCInventor: Lauren Domnick
-
Patent number: 11875222Abstract: In a general aspect, a method executed in a quantum computing system includes performing a calibration process in the quantum computing system to identify a value of a parameter of the quantum computing system. The method also includes analyzing a variation of the value in response to a change in a condition of the quantum computing system, thereby determining a stability of the parameter. The method additionally includes scheduling a recalibration of the parameter based on the stability of the parameter and executing a quantum algorithm in the quantum computing system based on the value of the parameter identified by the calibration process.Type: GrantFiled: September 18, 2018Date of Patent: January 16, 2024Assignee: Rigetti & Co, LLCInventors: Matthew J. Reagor, Christopher Butler Osborn, Alexa Nitzan Staley, Sabrina Sae Byul Hong, Benjamin Jacob Bloom, Alexander Papageorge, Nasser Alidoust
-
Patent number: 11875252Abstract: Some embodiments are directed to a neural network training device for training a neural network. At least one layer of the neural network layers is a projection layer. The projection layer projects a layer input vector (x) of the projection layer to a layer output vector (y). The output vector (y) sums to the summing parameter (k).Type: GrantFiled: May 17, 2019Date of Patent: January 16, 2024Inventors: Brandon David Amos, Vladlen Koltun, Jeremy Zieg Kolter, Frank Rüdiger Schmidt
-
Patent number: 11868899Abstract: A model configuration selection system, the model configuration selection system comprising a processing circuitry configured to: (A) obtain: (a) one or more model configurations, each model configuration includes a set of parameters utilized to generate respective models, and (b) a training data-set comprising a plurality of unlabeled records, each unlabeled record including a collection of features describing a given state of a physical entity; (B) cluster the training data-set into two or more training data-set clusters using a clustering algorithm; (C) label (a) the unlabeled records of a subset of the training data-set clusters with a synthetic normal label, giving rise to a normal training data-set, and (b) the unlabeled records of the training data-set clusters not included in the subset with a synthetic abnormal label; (D) train, for each model configuration, using the normal training data-set, a corresponding model utilizing the corresponding set of parameters, each model capable of receiving the unlType: GrantFiled: February 27, 2023Date of Patent: January 9, 2024Assignee: Saferide Technologies Ltd.Inventors: Sofiia Kovalets, Stanislav Barabanov, Yuval Shalev, Alexander Apartsin
-
Patent number: 11868916Abstract: A social networking application provides for automated link and/or content recommendation to users of a social media platform by automated social graph refinement that augments a baseline social graph with predicted links and inferred labels by iteratively (a) propagating attribute labels through optimizing attribute label similarity between user nodes constrained by closeness of links between the users, and (b) predicting links between users through optimizing link closeness constrained by label similarity. Each label inference iteration is based on predicted labels generated in and immediately prior link prediction iteration, and each link prediction iteration is based on inferred labels generated in and immediately prior label inference iteration.Type: GrantFiled: August 11, 2017Date of Patent: January 9, 2024Assignee: Snap Inc.Inventors: Jia Li, Jie Luo, Ji Yang, Lin Zhong
-
Patent number: 11868851Abstract: A method comprises receiving a network of a plurality of nodes and a plurality of edges, each of the nodes comprising members representative of at least one subset of training data points, each of the edges connecting nodes that share at least one data point, grouping the data points into a plurality of groups, each data point being a member of at least one group, creating a first transformation data set, the first transformation data set including the training data set as well as a plurality of feature subsets associated with at least one group, values of a particular data point for a particular feature subset for a particular group being based on values of the particular data point if the particular data point is a member of the particular group, and applying a machine learning model to the first transformation data set to generate a prediction model.Type: GrantFiled: March 11, 2016Date of Patent: January 9, 2024Assignee: SymphonyAI Sensa LLCInventor: Gunnar Carlsson
-
Patent number: 11861452Abstract: Quantized softmax layers in neural networks are described. Some embodiments involve receiving, at an input to a softmax layer of a neural network from an intermediate layer of the neural network, a non-normalized output comprising a plurality of intermediate network decision values. Then for each intermediate network decision value of the plurality of intermediate network decision values, the embodiment involves: calculating a difference between the intermediate network decision value and a maximum network decision value; requesting, from a lookup table, a corresponding lookup table value using the difference between the intermediate network decision value and the maximum network decision value; and selecting the corresponding lookup table value as a corresponding decision value. A normalized output is then generated comprising the corresponding lookup table value for said each intermediate network decision value of the plurality of intermediate network decision values.Type: GrantFiled: June 17, 2019Date of Patent: January 2, 2024Assignee: Cadence Design Systems, Inc.Inventor: Ming Kai Hsu
-
Patent number: 11847544Abstract: A mechanism is provided in a data processing system for preventing data leakage in automated machine learning. The mechanism receives a data set comprising a label for a target variable for a classifier machine learning model and a set of features. For each given feature in the set of features, the mechanism trains a subprime classifier model using the given feature as a target variable and remaining features as independent input features, tests the subprime classifier model, and records results of the subprime classifier model. The mechanism performs statistical analysis on the recorded results to identify an outlier result corresponding to an outlier subprime classifier model.Type: GrantFiled: July 21, 2020Date of Patent: December 19, 2023Assignee: International Business Machines CorporationInventor: Kunal Sawarkar