公开(公告)号：US11907679B2

公开(公告)日：2024-02-20

申请号：US16818823

申请日：2020-03-13

Applicant: Kioxia Corporation

Inventor： Kengo Nakata ,  Asuka Maki ,  Daisuke Miyashita

IPC: G06F7/48 ,  G06N20/20 ,  G06N3/082 ,  G06N5/04

CPC classification number: G06F7/48 ,  G06N3/082 ,  G06N5/04 ,  G06N20/20

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

公开(公告)号：US20220147821A1

公开(公告)日：2022-05-12

申请号：US17344192

申请日：2021-06-10

Applicant: Kioxia Corporation

Inventor： Kengo Nakata ,  Daisuke Miyashita ,  Jun Deguchi

IPC: G06N3/08 ,  G06N3/04

Abstract: According to one embodiment, a processor is configured to calculate a calculation amount in inference time of a neural network, using a result of summing, with respect to a group to which quantization is applied, products of the number of product-sum operations and bit widths of weight for the product-sum operations in the neural network. Then, the processor is configured to optimize a value of the weight and a quantization step size to minimize the recognition error by the neural network based on the calculated calculation amount, and execute computing about the neural network based on the optimized weight and the quantization step size.