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：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：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：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.