Title:
NEURAL NETWORK ARITHMETIC CIRCUIT
Document Type and Number:
WIPO Patent Application WO/2023/171683
Kind Code:
A1
Abstract:
This neural network arithmetic circuit holds a plurality of coupling weight coefficients corresponding respectively to a plurality of input data pieces, and outputs output data in accordance with the results of product-sum operations between the plurality of input data pieces and the corresponding coupling weight coefficients, wherein: the neural network arithmetic circuit comprises at least two bits of semiconductor storage elements, namely a variable resistance element (RPA0) and a variable resistance element (RPB0) for storing the coupling weight coefficients; and each of the plurality of coupling weight coefficients corresponds to a total current value obtained by adding a current value for the current flowing through the variable resistance element (RPA0) and a current value for the current flowing through the variable resistance element (RPB0).
Inventors:
MOCHIDA REIJI
ONO TAKASHI
KOUNO KAZUYUKI
NAKAYAMA MASAYOSHI
SUWA HITOSHI
KATO JUNICHI
ONO TAKASHI
KOUNO KAZUYUKI
NAKAYAMA MASAYOSHI
SUWA HITOSHI
KATO JUNICHI
Application Number:
PCT/JP2023/008647
Publication Date:
September 14, 2023
Filing Date:
March 07, 2023
Export Citation:
Assignee:
NUVOTON TECH CORPORATION JAPAN (JP)
International Classes:
G06F12/00; G06G7/60; G06G7/14; G06G7/16; G06N3/063; G11C11/54
Domestic Patent References:
WO2019049741A1 | 2019-03-14 |
Foreign References:
US20210150319A1 | 2021-05-20 | |||
JP2021185479A | 2021-12-09 | |||
JP2020160887A | 2020-10-01 |
Attorney, Agent or Firm:
NII, Hiromori et al. (JP)
Download PDF: