公开(公告)号：US20220292345A1

公开(公告)日：2022-09-15

申请号：US17392261

申请日：2021-08-03

Applicant: NEC CORPORATION

Inventor： Vivek BARSOPIA ,  Yoshio KAMEDA ,  Tomoya SAKAI

IPC: G06N3/08 ,  G06N3/04

Abstract: Distributionally robust models are obtained by operations including training, according to a loss function, a first learning function with a training data set to produce a first model, the training data set including a plurality of samples. The operations may further include training a second learning function with the training data set to produce a second model, the second model having a higher accuracy than the first model. The operations may further include assigning an adversarial weight to each sample among the plurality of samples set based on a difference in loss between the first model and the second model. The operations may further include retraining, according to the loss function, the first learning function with the training data set to produce a distrtibutionally robust model, wherein during retraining the loss function further modifies loss associated with each sample among the plurality of samples based on the assigned adversarial weight.

公开(公告)号：US20230206616A1

公开(公告)日：2023-06-29

申请号：US17927739

申请日：2020-10-05

Applicant: NEC CORPORATION

Inventor： Vivek BARSOPIA ,  Hiroshi TAMANO ,  Yoshio KAMEDA

IPC: G06V10/82 ,  G06V10/764 ,  G06V10/77

CPC classification number: G06V10/82 ,  G06V10/764 ,  G06V10/7715

Abstract: A method of training an image recognition model includes masking a first region of a first image with a first portion of a second image to define a mixed image, wherein the first image is different from the second image, and a location of the first region in the first image corresponds to a location of the first portion in the second image. The method further includes performing masked global average pooling (GAP) on both the mixed image. The method further includes generating a first classification score for the first image and a second classification score for the second image based on the masked GAP of the mixed image.

公开(公告)号：US20190188344A1

公开(公告)日：2019-06-20

申请号：US16311240

申请日：2017-06-20

Applicant: NEC Corporation

Inventor： Riki ETO ,  Yoshio KAMEDA

IPC: G06F17/50

CPC classification number: G06F17/5009 ,  G05B13/04 ,  G06F2217/16

Abstract: A linear parameter varying model estimation means (83) estimates a linear parameter varying model of a target system based on input data and output data of the target system collected under a condition around each endpoint of an operating region. When a determination is made that the prediction performance is not good, a data addition instruction means (85) outputs a message indicating an instruction for adding input data and output data of the target system collected under a condition corresponding to a point in the operating region. When the input data and the output data of the target system are additionally input, the linear parameter varying model estimation means (83) further uses the input data and the output data to estimate the linear parameter varying model.

公开(公告)号：US20220343212A1

公开(公告)日：2022-10-27

申请号：US17389237

申请日：2021-07-29

Applicant: NEC CORPORATION

Inventor： Vivek BARSOPIA ,  Yoshio KAMEDA ,  Tomoya SAKAI

IPC: G06N20/00

Abstract: Forward compatible models are obtained by operations including training a learning function with a current training data set to produce a first model, the current training data set including a plurality of samples, generating a plurality of prospective models, each prospective model based on a variation of one of the current training data set or the first model, adjusting a plurality of sample weights based on output of one or more prospective models among the plurality of prospective models in response to input of the current training data set, and retraining the learning function with the current training data set and the plurality of sample weights to produce a second model.

公开(公告)号：US20200317220A1

公开(公告)日：2020-10-08

申请号：US16305441

申请日：2017-06-05

Applicant: NEC Corporation

Inventor： Yoshio KAMEDA ,  Riki ETO ,  Wemer WEE ,  Yusuke KIKUCHI

IPC: B60W60/00 ,  B60W40/105 ,  B60W40/107 ,  G06K9/62

Abstract: A vehicle control system for controlling driving of a vehicle reflecting an environment and a characteristic of a user, while suppressing increase in learning time, is provided. The vehicle control system includes classification means for classifying, by using one or more attributes selected from accumulation means for accumulating data including attributes relating to driving of a vehicle, driving properties included in the data, learning means for learning a model representing the driving property, for each of types that are a result of classification by the classification means, and control information determination means for determining, by using the model learned for the type associated with a value of the attribute at time of driving of a control target vehicle, control information for the driving.

公开(公告)号：US20190311269A1

公开(公告)日：2019-10-10

申请号：US15316390

申请日：2015-06-01

Applicant: NEC Corporation

Inventor： Yoshio KAMEDA

IPC: G06N3/12

Abstract: To efficiently process a programming problem including a function defined piecewise without having the differentiability and continuity of the function expressing the problem or spatial continuity as prerequisites, a non-linear programming problem processing device is provided with: a non-linear programming problem input unit; a provisional solution generation unit that produces a solution obtained in a certain region of the non-linear programming problem as a provisional solution; a solution candidate generation unit that produces a solution obtained in a nearby region of the provisional solution as a solution candidate; a provisional solution update unit that updates the solution candidate in accordance with the result of comparison of the provisional solution and the solution candidate; an end determination unit that determines the end of the process using a provisional solution improvement degree and/or the number of times of generation of the solution candidate; and a non-linear programming problem solution output unit.

公开(公告)号：US20240028912A1

公开(公告)日：2024-01-25

申请号：US17863338

申请日：2022-07-12

Applicant: NEC CORPORATION

Inventor： Vivek BARSOPIA ,  Yoshio KAMEDA ,  Tomoya SAKAI ,  Keita SAKUMA ,  Ryuta MATSUNO

IPC: G06N5/02

CPC classification number: G06N5/022

Abstract: Predictively robust models are trained by embedding a distribution of each temporal data set among a plurality of temporal data sets into a feature vector, predicting a future feature vector of a distribution of a future data set, based on the feature vector of each temporal data set among a plurality of temporal data sets, creating the future data set from the future feature vector, perturbing the future data set to produce a plurality of perturbed future data sets, and training a learning function using the future data set and each perturbed future data set to produce a model.

公开(公告)号：US20210390451A1

公开(公告)日：2021-12-16

申请号：US17288595

申请日：2019-10-29

Applicant: NEC CORPORATION ,  NATIONAL INSTITUTE OF ADVANCED INDUSTRIAl SCIENCE AND TECHNOLOGY

Inventor： Keiichi KISAMORI ,  Yuto KOMORI ,  Takashi WASHIO ,  Yoshio KAMEDA

IPC: G06N20/00

Abstract: An analysis device applies, for each of a plurality of candidates set according to a update target parameter value, the update target parameter value and the candidate to a machine learning result to acquire information, the information indicating a degree of difference of an evaluation target value in a case of the candidate with respect to an evaluation target value in a case of the update target parameter value; calculates, for each candidate, an evaluation target value in a case of the candidate, based on the degree of difference of the evaluation target values and the evaluation target value in the case of the update target parameter value; and compares the evaluation target values in a case of each of the plurality of candidates and selects a candidate from the plurality of candidates based on a result of the comparison.

公开(公告)号：US20200027013A1

公开(公告)日：2020-01-23

申请号：US16481715

申请日：2018-01-18

Applicant: NEC CORPORATION

Inventor： Riki ETO ,  Yoshio KAMEDA

IPC: G06N7/00 ,  G06N20/00 ,  G06F17/50

Abstract: Provided is a model estimation system that can estimate a discrete time state space model having controllability. The model estimation system of the present invention estimates a model of a system that is represented by an ordinary differential equation with all the coefficients being non-zero, and with which input data and a state at each time can be obtained. When an order of the ordinary differential equation and input data and a state at multiple past times in the system are inputted, a model expression construction means 22 constructs an expression representing a model by using a first matrix that is a matrix according to the order and has only some elements as unknown elements and a second matrix that is a matrix according to the order and has only some element as an unknown element. A model estimation means 23 uses input data and a state at multiple past times, to estimate the model by learning unknown elements of the first matrix and an unknown element of the second matrix in the expression.

公开(公告)号：US20180373208A1

公开(公告)日：2018-12-27

申请号：US16062722

申请日：2015-12-25

Applicant: NEC CORPORATION

Inventor： Wemer WEE ,  Yoshio KAMEDA ,  Riki ETO

IPC: G05B13/02 ,  G05B13/04 ,  G06F15/18

Abstract: A learner unit 81 learns a quantity model for a quantity the user is interest in based on data acquired from dynamics and surroundings of a plant which is a control target. A cost function designing unit 82 designs a cost function to be used in the derivation of solutions to optimally control the plant so as to include at least the quantity model as terms.