Country
Full text data for US,EP,CN
Type
Legal Validity
Legal Status
Filing Date
Publication Date
Inventor
Assignee
Click to expand
IPC(Section)
IPC(Class)
IPC(Subclass)
IPC(Group)
IPC(Subgroup)
Agent
Agency
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
1 US2020012932A1
MACHINE LEARNING METHOD AND MACHINE LEARNING DEVICE
Publication/Patent Number: US2020012932A1 Publication Date: 2020-01-09 Application Number: 16/030,859 Filing Date: 2018-07-10 Inventor: Wang, Jia-ching   Wang, Chien-yao   Yang, Chih-hsuan   Assignee: National Central University   IPC: G06N3/08 Abstract: A machine learning method and a machine learning device are provided. The machine learning method includes: receiving an input signal and performing normalization on the input signal; transmitting the normalized input signal to a convolutional layer; and adding a sparse coding layer after the convolutional layer, wherein the sparse coding layer uses dictionary atoms to reconstruct signals on a projection of the normalized input signal passing through the convolutional layer, and the sparse coding layer receives a mini-batch input to refresh the dictionary atoms. A machine learning method and a machine learning device are provided. The machine learning method includes: receiving an input signal and performing normalization on the input signal; transmitting the normalized input signal to a convolutional layer; and adding a sparse coding ...More Less
2 US10532432B2
Machine learning device, machine learning system, and machine learning method
Publication/Patent Number: US10532432B2 Publication Date: 2020-01-14 Application Number: 16/050,252 Filing Date: 2018-07-31 Inventor: Kubo, Yoshitaka   Assignee: Fanuc Corporation   IPC: G06K9/62 Abstract: Quality judgment on a laser beam intensity distribution is performed by taking an observation condition of the laser beam into consideration. A machine learning device includes: a state observing means that acquires data indicating an intensity distribution of a laser beam and data indicating a condition for observing the laser beam, performed to generate the data indicating the intensity distribution as input data; a label acquisition means that acquires an evaluation value related to judgment of the quality of the laser beam as a label; and a learning means that performs supervised learning using a pair of the input data acquired by the state observing means and the label acquired by the label acquisition means as training data to construct a learning model for judging the quality of the laser beam. Quality judgment on a laser beam intensity distribution is performed by taking an observation condition of the laser beam into consideration. A machine learning device includes: a state observing means that acquires data indicating an intensity distribution of a laser beam and ...More Less
3 EP3683736A1
MACHINE LEARNING METHOD, MACHINE LEARNING PROGRAM, AND MACHINE LEARNING APPARATUS
Publication/Patent Number: EP3683736A1 Publication Date: 2020-07-22 Application Number: 20150943.7 Filing Date: 2020-01-09 Inventor: Nishino, Takuya   Assignee: FUJITSU LIMITED   IPC: G06N3/08 Abstract: A computer-implemented machine learning method of a machine learning model includes: performing(S1) first training of the machine learning model by using pieces of training data associated with a correct label; determining(S3,S4), from the pieces of training data, a set of pieces of training data that are close to each other in a feature space based on a core tensor generated by the trained machine learning model and have a same correct label; generating(S6) extended training data based on the determined set of pieces of training data; and performing(S7) second training of the trained machine learning model by using the generated extended training data. A computer-implemented machine learning method of a machine learning model includes: performing(S1) first training of the machine learning model by using pieces of training data associated with a correct label; determining(S3,S4), from the pieces of training data, a set of ...More Less
4 US10572773B2
On the fly deep learning in machine learning for autonomous machines
Publication/Patent Number: US10572773B2 Publication Date: 2020-02-25 Application Number: 15/659,818 Filing Date: 2017-07-26 Inventor: Yehezkel, Rohekar Raanan Yonatan   Assignee: INTEL CORPORATION   IPC: G06K9/62 Abstract: A mechanism is described for facilitating on-the-fly deep learning in machine learning for autonomous machines. A method of embodiments, as described herein, includes detecting an output associated with a first deep network serving as a user-independent model associated with learning of one or more neural networks at a computing device having a processor coupled to memory. The method may further include automatically generating training data for a second deep network serving as a user-dependent model, where the training data is generated based on the output. The method may further include merging the user-independent model with the user-dependent model into a single joint model. A mechanism is described for facilitating on-the-fly deep learning in machine learning for autonomous machines. A method of embodiments, as described herein, includes detecting an output associated with a first deep network serving as a user-independent model associated with ...More Less
5 US2020184337A1
LEARNING COACH FOR MACHINE LEARNING SYSTEM
Publication/Patent Number: US2020184337A1 Publication Date: 2020-06-11 Application Number: 16/334,204 Filing Date: 2017-09-18 Inventor: Baker, James K.   Assignee: D5AI LLC   IPC: G06N3/08 Abstract: A machine learning system includes a coach machine learning system that uses machine learning to help a student machine learning system learn its system. By monitoring the student learning system, the coach machine learning system can learn (through machine learning techniques) “hyperparameters” for the student learning system that control the machine learning process for the student learning system. The machine learning coach could also determine structural modifications for the student learning system architecture. The learning coach can also control data flow to the student learning system. A machine learning system includes a coach machine learning system that uses machine learning to help a student machine learning system learn its system. By monitoring the student learning system, the coach machine learning system can learn (through machine learning techniques) ...More Less
6 EP3602316A1
LEARNING COACH FOR MACHINE LEARNING SYSTEM
Publication/Patent Number: EP3602316A1 Publication Date: 2020-02-05 Application Number: 18772282.2 Filing Date: 2018-03-05 Inventor: Baker, James K.   Assignee: D5A1 LLC   IPC: G06F15/18
7 US10664767B2
Machine learning apparatus, laser machining system and machine learning method
Publication/Patent Number: US10664767B2 Publication Date: 2020-05-26 Application Number: 15/460,850 Filing Date: 2017-03-16 Inventor: Takigawa, Hiroshi   Ohyama, Akinori   Assignee: FANUC CORPORATION   IPC: G06N20/00 Abstract: A machine learning apparatus that learns laser machining condition data of a laser machining system includes: a state amount observation unit that observes a state amount of the laser machining system; an operation result acquisition unit that acquires a machined result of the laser machining system; a learning unit that receives an output from the state amount observation unit and an output from the operation result acquisition unit, and learns the laser machining condition data in association with the state amount and the machined result of the laser machining system; and a decision-making unit that outputs laser machining condition data by referring to the laser machining condition data learned by the learning unit. A machine learning apparatus that learns laser machining condition data of a laser machining system includes: a state amount observation unit that observes a state amount of the laser machining system; an operation result acquisition unit that acquires a machined result of the ...More Less
8 US2020192733A1
MACHINE LEARNING REPOSITORY SERVICE
Publication/Patent Number: US2020192733A1 Publication Date: 2020-06-18 Application Number: 16/799,443 Filing Date: 2020-02-24 Inventor: Khare, Vineet   Smola, Alexander Johannes   Wiley, Craig   Assignee: Amazon Technologies, Inc.   IPC: G06F9/54 Abstract: Techniques for providing and servicing listed repository items such as algorithms, data, models, pipelines, and/or notebooks are described. In some examples, web services provider receives a request for a listed repository item from a requester, the request indicating at least a category of the repository item and each listing of a repository item includes an indication of a category that the listed repository item belongs to and a storage location of the listed repository item, determines a suggestion of at least one listed repository item based on the request, and provides the suggestion of the at least one listed repository item to the requester. Techniques for providing and servicing listed repository items such as algorithms, data, models, pipelines, and/or notebooks are described. In some examples, web services provider receives a request for a listed repository item from a requester, the request indicating at least a ...More Less
9 US2020193327A1
MACHINE LEARNING METHOD
Publication/Patent Number: US2020193327A1 Publication Date: 2020-06-18 Application Number: 16/697,179 Filing Date: 2019-11-27 Inventor: Iwakura, Satoko   Watanabe, Shunichi   Shiota, Tetsuyoshi   Nitta, Izumi   Fukuda, Daisuke   Todoriki, Masaru   Assignee: FUJITSU LIMITED   IPC: G06N20/00 Abstract: A machine learning method includes acquiring data including attendance records of employees and information indicating which employee has taken a leave of absence from work, in response to determining that a first employee of the employees has not taken a leave of absence in accordance with the data, generating a first tensor on a basis of an attendance record of the first employee and parameters associated with elements included in the attendance record, in response to determining that a second employee of the employees has taken a leave of absence in accordance with the data, modifying the parameters, and generating a second tensor on a basis of an attendance record of the second employee and the modified parameters, and generating a model by machine learning based on the first tensor and the second tensor. A machine learning method includes acquiring data including attendance records of employees and information indicating which employee has taken a leave of absence from work, in response to determining that a first employee of the employees has not taken a leave of absence in ...More Less
10 US2020159924A1
PROTECTING A MACHINE LEARNING MODEL
Publication/Patent Number: US2020159924A1 Publication Date: 2020-05-21 Application Number: 16/192,787 Filing Date: 2018-11-15 Inventor: Tran, Ngoc Minh   Sinn, Mathieu   Rawat, Ambrish   Nicolae, Maria-irina   Wistuba, Martin   Assignee: International Business Machines Corporation   IPC: G06F21/56 Abstract: A method for protecting a machine learning model includes: generating a first adversarial example by modifying an original input using an attack tactic, wherein the model accurately classifies the original input but does not accurately classify at least the first adversarial example; training a defender to protect the model from the first adversarial example by updating a strategy of the defender based on predictive results from classifying the first adversarial example; updating the attack tactic based on the predictive results from classifying the first adversarial example; generating a second adversarial example by modifying the original input using the updated attack tactic, wherein the trained defender does not protect the model from the second adversarial example; and training the defender to protect the model from the second adversarial example by updating the at least one strategy of the defender based on results obtained from classifying the second adversarial example. A method for protecting a machine learning model includes: generating a first adversarial example by modifying an original input using an attack tactic, wherein the model accurately classifies the original input but does not accurately classify at least the first adversarial ...More Less
11 US2020012962A1
Automated Machine Learning System
Publication/Patent Number: US2020012962A1 Publication Date: 2020-01-09 Application Number: 16/416,773 Filing Date: 2019-05-20 Inventor: Dent, Killian B.   Friedman, James M.   Johnson, Allan D.   Moran, Shauna J.   Cooper, Tyler P.   Knoch, Chris K.   Magnuson, Nicholas R.   Wallace, Daniel J.   Assignee: Big Squid Inc.   IPC: G06N20/00 Abstract: A technology is described for automating deployment of a machine learning model. An example method may include receiving, via a graphical user interface, credentials for connecting to a data store containing a plurality of datasets and connecting to the data store using the credentials. A selection of a target metric to predict using the machine learning model can be received, via the graphical user interface, and datasets included in the plurality of datasets that correlate to the target metric can be identified by analyzing the datasets to identify an association between the target metric and data contained within the datasets. The datasets can be input to the machine learning model to train the machine learning model to generate predictions of the target metric, and the machine learning model can be deployed to computing resources in a service provider environment to generate predictions associated with the target metric. A technology is described for automating deployment of a machine learning model. An example method may include receiving, via a graphical user interface, credentials for connecting to a data store containing a plurality of datasets and connecting to the data store using the ...More Less
12 US10546393B2
Compression in machine learning and deep learning processing
Publication/Patent Number: US10546393B2 Publication Date: 2020-01-28 Application Number: 15/859,408 Filing Date: 2017-12-30 Inventor: Ray, Joydeep   Ashbaugh, Ben   Surti, Prasoonkumar   Ramani, Pradeep   Harihara, Rama   Justin, Jerin C.   Huang, Jing   Cui, Xiaoming   Costa, Timothy B.   Gong, Ting   Ould-ahmed-vall, Elmoustapha   Balasubramanian, Kumar   Thomas, Anil   Elibol, Oguz H.   Bobba, Jayaram   Zhuang, Guozhong   Subramanian, Bhavani   Keskin, Gokce   Sakthivel, Chandrasekaran   Poornachandran, Rajesh   Assignee: INTEL CORPORATION   IPC: G06T9/00 Abstract: Embodiments are generally directed to compression in machine learning and deep learning processing. An embodiment of an apparatus for compression of untyped data includes a graphical processing unit (GPU) including a data compression pipeline, the data compression pipeline including a data port coupled with one or more shader cores, wherein the data port is to allow transfer of untyped data without format conversion, and a 3D compression/decompression unit to provide for compression of untyped data to be stored to a memory subsystem and decompression of untyped data from the memory subsystem. Embodiments are generally directed to compression in machine learning and deep learning processing. An embodiment of an apparatus for compression of untyped data includes a graphical processing unit (GPU) including a data compression pipeline, the data compression pipeline ...More Less
13 US10617961B2
Online learning simulator using machine learning
Publication/Patent Number: US10617961B2 Publication Date: 2020-04-14 Application Number: 15/968,780 Filing Date: 2018-05-02 Inventor: Ma, Yanjun   Ma, Christine K.   Ma, Kevin L.   Assignee: Interlake Research, LLC   IPC: A63F13/825 Abstract: Technologies for executing a virtual character development application using machine learning are described herein. In typical simulation applications, a user may be enabled to create a virtual character and navigate a virtual world. A typical simulation application may accept inputs from the user, determine actions initiated by the user based on the inputs, determine subsequent outcomes of the user initiated actions, and mold the simulation according to the outcomes. However most outcomes may be predetermined and predictable by design. In contrast, some embodiments may include a server configured to execute a virtual character development application in conjunction with one or more client devices. A user may utilize a client device to create and develop a virtual character within the application. The user may be enabled to provide inputs to the virtual character development application, and the artificial component may process the input and extract information associated with the virtual character. Technologies for executing a virtual character development application using machine learning are described herein. In typical simulation applications, a user may be enabled to create a virtual character and navigate a virtual world. A typical simulation application may accept ...More Less
14 US2020192976A1
ADAPTIVE HUMAN TO MACHINE INTERACTION USING MACHINE LEARNING
Publication/Patent Number: US2020192976A1 Publication Date: 2020-06-18 Application Number: 16/219,209 Filing Date: 2018-12-13 Inventor: Swamypillai, Ganesh   Venkatnarayanan, Shriram   Balakrishnan, Balaji   Assignee: SOFTWARE AG   IPC: G06F17/27 Abstract: A computer system is provided that automatically generates a natural language processing model from a provided API specification. Intent names are based on operation type and name. Entity datasets are constructed based on the generated intent name. A plurality of training phrases are generated based on the entity dataset and an action dataset with a name and corresponding parameters is generated. A computer system is provided that automatically generates a natural language processing model from a provided API specification. Intent names are based on operation type and name. Entity datasets are constructed based on the generated intent name. A plurality of training ...More Less
15 US10643127B2
Machine learning apparatus for learning condition for starting laser machining, laser apparatus, and machine learning method
Publication/Patent Number: US10643127B2 Publication Date: 2020-05-05 Application Number: 15/411,232 Filing Date: 2017-01-20 Inventor: Takigawa, Hiroshi   Yoshida, Hiroyuki   Machida, Hisatada   Maeda, Michinori   Miyata, Ryusuke   Ohyama, Akinori   Assignee: FANUC CORPORATION   IPC: B23K37/00 Abstract: The machine learning apparatus includes: a state data observing unit which observes state data of the laser apparatus, including data output from a reflected light detecting unit for measuring a reflected light amount; an operation result acquiring unit which acquires a success/failure result indicating whether the machining has been started successfully by the laser beam output from a laser oscillator; a learning unit which learns light output command data by associating the light output command data with the state data of the laser apparatus and the success/failure result of the machining start; and a decision making unit which determines the light output command data by referring to the light output command data learned by the learning unit. The machine learning apparatus includes: a state data observing unit which observes state data of the laser apparatus, including data output from a reflected light detecting unit for measuring a reflected light amount; an operation result acquiring unit which acquires a ...More Less
16 US2020160095A1
AUTOMATION RATING FOR MACHINE LEARNING CLASSIFICATION
Publication/Patent Number: US2020160095A1 Publication Date: 2020-05-21 Application Number: 16/192,679 Filing Date: 2018-11-15 Inventor: Weller, Tobias   Assignee: SAP SE   IPC: G06K9/62 Abstract: In some embodiments, a first output is received from a first prediction network at a second prediction network. The first prediction network generates the first output from a first input. Also, a second input is received at the second prediction network that describes the first input. The second prediction network analyzes the first output and the second input and generates a second output that classifies the first output in one of a set of classifications. The first output is output with the one of the set of classifications for the second output where the second output indicates whether the first output should be reviewed when the second output is classified in a first classification in the set of classifications or not reviewed when the second output is classified in a second classification in the set of classifications. In some embodiments, a first output is received from a first prediction network at a second prediction network. The first prediction network generates the first output from a first input. Also, a second input is received at the second prediction network that describes the first ...More Less
17 US2020160550A1
MACHINE LEARNING FRAMEWORK FOR VISUAL TRACKING
Publication/Patent Number: US2020160550A1 Publication Date: 2020-05-21 Application Number: 16/192,137 Filing Date: 2018-11-15 Inventor: Hunt, Shawn   Assignee: DENSO International America, Inc.   IPC: G06T7/70 Abstract: A method of analyzing autonomous vehicle data comprising recording a video of a vehicle environment utilizing one or more vehicle cameras, identifying corner points of objects in the video, identifying a forward-tracked location of one or more corner points in each frame from an earlier frame to a later frame of the recorded video played in forward, identifying a reverse-tracked location of one or more corner points in each frame from the later frame to the earlier frame of the recorded video played in reverse, comparing the forward-tracked location of the earlier frame and reverse-tracked location of the later frame, and adjusting a descriptor defining characteristics of one or more pixels of the corner point in response the comparison indicating an error rate exceeding a threshold. A method of analyzing autonomous vehicle data comprising recording a video of a vehicle environment utilizing one or more vehicle cameras, identifying corner points of objects in the video, identifying a forward-tracked location of one or more corner points in each frame from an ...More Less
18 US2020013484A1
MACHINE LEARNING VARIANT SOURCE ASSIGNMENT
Publication/Patent Number: US2020013484A1 Publication Date: 2020-01-09 Application Number: 16/460,588 Filing Date: 2019-07-02 Inventor: Shenoy, Archana   Hubbell, Earl   Assignee: GRAIL, INC.   IPC: G16B40/20 Abstract: Systems and methods for determining a source of a variant include receiving a plurality of variants obtained from a biological sample, the variants being of unknown source upon receipt, and receiving, for each of the variants, a plurality of values for a plurality of covariates from the biological sample. The variants are input into a source assignment classifier to determine a source for each of the variants, the source being one of a plurality of possible sources. The source assignment classifier includes a plurality of coefficients associated with the plurality of covariates and a function that receives as input the values associated with each variant and the coefficients and outputs the determined source of each of the variants. Systems and methods for determining a source of a variant include receiving a plurality of variants obtained from a biological sample, the variants being of unknown source upon receipt, and receiving, for each of the variants, a plurality of values for a plurality of covariates ...More Less
19 US10685295B1
Allocating resources for a machine learning model
Publication/Patent Number: US10685295B1 Publication Date: 2020-06-16 Application Number: 15/859,077 Filing Date: 2017-12-29 Inventor: Ross, Jonathan   Stivoric, John Michael   Assignee: X Development LLC   IPC: G06N20/00 Abstract: A method for allocating resources for a machine learning model is disclosed. A machine learning model to be executed on a special purpose machine learning model processor is received. A computational data graph is generated from the machine learning model. The computational dataflow graph represents the machine learning model which includes nodes, connector directed edges, and parameter directed edges. The operations of the computational dataflow graph is scheduled and then compiled using a deterministic instruction set architecture that specifies functionality of a special purpose machine learning model processor. An amount of resources required to execute the computational dataflow graph is determined. Resources are allocated based on the determined amounts of resources required to execute the machine learning model represented by the computational dataflow graph. A method for allocating resources for a machine learning model is disclosed. A machine learning model to be executed on a special purpose machine learning model processor is received. A computational data graph is generated from the machine learning model. The computational ...More Less
20 US2020193219A1
DISCRIMINATION DEVICE AND MACHINE LEARNING METHOD
Publication/Patent Number: US2020193219A1 Publication Date: 2020-06-18 Application Number: 16/640,729 Filing Date: 2019-08-01 Inventor: Namiki, Yuta   Assignee: FANUC CORPORATION   IPC: G06K9/62 Abstract: A discrimination device includes a sub-data set extraction unit for extracting from a plurality of labeled learning data a sub-learning data set to be used for learning and a sub-verification data set to be used for verification, a learning unit for performing supervised learning on the basis of the sub-learning data set to generate a pre-trained model for discriminating a label from data related to an object, a discrimination unit for conducting a discrimination processing using the pre-trained model on each piece of learning data contained in the sub-verification data set, a verification result recording unit for recording a result of the discrimination processing in association with the learning data, and a correctness detection unit for detecting learning data attached with a label that may be incorrect based on the discrimination processing results recorded in association with respective learning data. A discrimination device includes a sub-data set extraction unit for extracting from a plurality of labeled learning data a sub-learning data set to be used for learning and a sub-verification data set to be used for verification, a learning unit for performing supervised ...More Less