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：US20220076122A1

公开(公告)日：2022-03-10

申请号：US17195865

申请日：2021-03-09

Applicant: Kioxia Corporation

Inventor： Daisuke MIYASHITA ,  Asuka MAKI

IPC: G06N3/08 ,  G06N3/04 ,  G06F3/06

Abstract: According to one embodiment, an arithmetic apparatus includes a non-volatile first memory, a second memory, and a controller. The first memory stores a model to be trained. The second memory has a smaller storage capacity than the first memory. The controller executes learning processing that updates a first parameter of the model based on a loss value obtained by inputting training data into the model stored in the first memory, and stores cumulative update information indicating a difference of the first parameter before and after the update in the second memory. In addition, the controller executes the learning processing using a second parameter in which the cumulative update information stored in the second memory is reflected in the first parameter read from the model stored in the first memory, and stores a difference between a third parameter obtained by updating the second parameter and the first parameter, in the second memory as the cumulative update information.

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.

公开(公告)号：US20230185468A1

公开(公告)日：2023-06-15

申请号：US17840981

申请日：2022-06-15

Applicant: Kioxia Corporation

Inventor： Taiga IKEDA ,  Daisuke MIYASHITA ,  Jun DEGUCHI ,  Asuka MAKI

IPC: G06F3/06 ,  G06F12/02

CPC classification number: G06F3/0638 ,  G06F3/0611 ,  G06F3/0685 ,  G06F12/023 ,  G06F2212/1024

Abstract: An information processing device includes a first memory, a second memory, and a processor. The first memory stores clusters into which first data segments are grouped according to distances among the first data segments and each including one or more first data segments. The second memory is operable at a higher speed than the first memory and stores second data segments corresponding one-to-one to the clusters. The processor receives an input query and identify a third data segment being one of the second data segments closest to the query, from the second data segments. The processor collectively reads, from the first memory, one or more first data segments included in a cluster corresponding to the third data segment among the clusters, and identify a fourth data segment being one of the first data segments closest to the query from the one or more first data segments for output.

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.