公开(公告)号：US20230153386A1

公开(公告)日：2023-05-18

申请号：US17807005

申请日：2022-06-15

Applicant: Kioxia Corporation

Inventor： Kengo NAKATA ,  Asuka MAKI ,  Daisuke MIYASHITA ,  Jun DEGUCHI

IPC: G06K9/00 ,  G06K9/62

CPC classification number: G06K9/00523 ,  G06K9/6256 ,  G06K9/00503

Abstract: According to one embodiment, an information processing method includes: calculating a first feature amount of query data in a first field; calculating first similarity degrees between the first feature amount and second feature amounts in the first field; obtaining, based on the first similarity degrees, third feature amounts in a second field that are associated with feature amounts selected from the second feature amounts, the second field being different from the first field; calculating fourth feature amounts in the second field, for choices concerning the query data; calculating second similarity degrees between the third feature amounts and the fourth feature amounts; and selecting, based on the second similarity degrees, an answer to the query data among answer candidates corresponding to the third feature amounts.

公开(公告)号：US20210089885A1

公开(公告)日：2021-03-25

申请号：US16811137

申请日：2020-03-06

Applicant: Kioxia Corporation

Inventor： Daisuke MIYASHITA ,  Jun DEGUCHI ,  Asuka MAKI ,  Fumihiko TACHIBANA ,  Shinichi SASAKI ,  Kengo NAKATA

IPC: G06N3/08 ,  G06N3/04 ,  G06N3/063

Abstract: According to one embodiment, a training device includes a first memory, a second memory, and a processing circuit. The first memory is a memory accessible at a higher speed than the second memory. The training device executes a training process of a machine learning model using a stochastic gradient descent method. The processing circuit stores a first output produced by the process of a first layer in the second memory, and stores a second output produced by the process of a second layer, in a forward process of the training process. The processing circuit updates a parameter of the second layer based on the second output stored in the first memory, reads the first output stored in the second memory, and updates a parameter of the first layer based on the read first output, in a backward process of the training process.

公开(公告)号：US20230290125A1

公开(公告)日：2023-09-14

申请号：US17942815

申请日：2022-09-12

Applicant: Kioxia Corporation

Inventor： Bo WANG ,  Youyang NG ,  Yuchieh LIN ,  Kengo NAKATA ,  Takeshi FUJIWARA

IPC: G06V10/774 ,  G06V10/40 ,  G06V10/82 ,  G06V10/764 ,  G06V20/70 ,  G06V10/776

CPC classification number: G06V10/7747 ,  G06V10/40 ,  G06V10/82 ,  G06V10/764 ,  G06V20/70 ,  G06V10/776

Abstract: An image processing apparatus has a first image acquisitor that acquires a source image, a second image acquisitor that acquires a first target image, a label acquisitor that acquires a label, a feature extractor including a first neural network that extracts a feature of the source image and a feature of the first target image, a class classifier including a second neural network that performs a class classification of the source image and the first target image, a domain classifier including a third neural network that performs a domain classification of the source image and the first target image, a processor that assigns a pseudo label to the first target image, a self-learner that performs a self-learning of the first neural network, the second neural network, and the third neural network, and a learner that learns the first, second and third neural networks, by performing a back propagation process.

公开(公告)号：US20210089271A1

公开(公告)日：2021-03-25

申请号：US16818823

申请日：2020-03-13

Applicant: Kioxia Corporation

Inventor： Kengo NAKATA ,  Asuka MAKI ,  Daisuke MIYASHITA

IPC: G06F7/48 ,  G06N5/04 ,  G06N3/08 ,  G06N20/20

Abstract: According to one embodiment, an arithmetic operation device removes a part of parameters of a predetermined number of parameters from a first model which includes the predetermined number of parameters and is trained so as to output second data corresponding to input first data and determines the number of bits of a weight parameters according to required performance related to an inference to generate a second model, and acquires data output from the second model so as to correspond to the input first data with a smaller computational complexity than the first model.