公开(公告)号：US20220413806A1

公开(公告)日：2022-12-29

申请号：US17771143

申请日：2019-10-31

Applicant: NEC Corporation

Inventor： Takashi TAKENAKA ,  Hiroaki INOUE

IPC: G06F7/544 ,  G06N3/063

Abstract: The information processing circuit 10 performs operations on layers in deep learning, and includes a product sum circuit 11 which performs a product-sum operation using input data and parameter values, and a parameter value output circuit 12 which outputs the parameter values, wherein the parameter value output circuit 12 is composed of a combinational circuit.

公开(公告)号：US20240184525A1

公开(公告)日：2024-06-06

申请号：US18384142

申请日：2023-10-26

Applicant: NEC Corporation

Inventor： Dai KUBOTA ,  Yuta IDEGUCHI ,  Fumiyo TAKANO ,  Ryutaro DOI ,  Hiroaki INOUE ,  Takahiro NISHIMURA

IPC: G06F7/535

CPC classification number: G06F7/535

Abstract: At least one processor included in an information processing apparatus carries out: a division process of dividing input constraint conditions into a plurality of groups; a conversion process of converting the constraint conditions into a predetermined format; and an integration process of integrating the constraint conditions which are expressed in the predetermined format. In the conversion process, the processor carries out, in a parallel manner, a plurality of processes which respectively correspond to the plurality of groups, where each of the plurality of processes is constituted by conversion processes on respective constraint conditions belonging to one group. This makes it possible to support decision making of a user.

公开(公告)号：US20230359691A1

公开(公告)日：2023-11-09

申请号：US18023436

申请日：2020-09-03

Applicant: NEC Corporation

Inventor： Takuya ARAKI ,  Fumiyo TAKANO ,  Hiroaki INOUE ,  Motoi SUZUKI ,  Yuki KOBAYASHI ,  Takahiro NISHIMURA ,  Hiroshi CHISHIMA ,  Akihiro YATABE

IPC: G06F17/11

CPC classification number: G06F17/11

Abstract: The conversion means 72 generates a program for deriving a QUBO matrix that is a matrix that defines an energy function of QUBO, by converting a description of a natural language representing a combinatorial optimization problem into a description of the program for deriving the QUBO matrix. It is possible to generate a program for deriving a QUBO matrix based on a description of a natural language representing a combinatorial optimization problem.

公开(公告)号：US20240037185A1

公开(公告)日：2024-02-01

申请号：US18011329

申请日：2020-06-29

Applicant: NEC Corporation

Inventor： Fumiyo TAKANO ,  Hiroaki INOUE ,  Takuya ARAKI ,  Motoi SUZUKI ,  Yuki KOBAYASHI ,  Takahiro NISHIMURA ,  Hiroshi CHISHIMA ,  Akihiro YATABE

IPC: G06F17/18

CPC classification number: G06F17/18

Abstract: The inconsistency determination device 1 includes inconsistency determination means 9. The inconsistency determination means 9 determines whether or not there is inconsistency in an expression, which is to be converted into an energy function of a model representing states of individual spins by a first value or a second value, representing energy in a combinatorial optimization problem.

公开(公告)号：US20230306074A1

公开(公告)日：2023-09-28

申请号：US18020526

申请日：2020-08-20

Applicant: NEC Corporation

Inventor： Motoi SUZUKI ,  Hiroaki INOUE ,  Takuya ARAKI ,  Fumiyo TAKANO ,  Yuki KOBAYASHI ,  Hiroshi CHISHIMA ,  Takahiro NISHIMURA ,  Akihiro YATABE

IPC: G06F17/11 ,  G06F17/16

CPC classification number: G06F17/11 ,  G06F17/16

Abstract: The difference matrix calculation means 72 calculates a difference matrix which is a difference between a first matrix representing a combinatorial optimization problem for which a solution was found last time and a second matrix representing the latest combinatorial optimization problem. The difference matrix compression means 73 compresses the difference matrix. The transmission means 74 transmits the difference matrix after compression to a combinatorial optimization problem solution device that finds a solution to the combinatorial optimization problem.

公开(公告)号：US20230359921A1

公开(公告)日：2023-11-09

申请号：US18026056

申请日：2021-08-31

Applicant: NEC Corporation

Inventor： Takahiro NISHIMURA ,  Hiroaki INOUE ,  Takuya ARAKI ,  Motoi SUZUKI ,  Fumiyo TAKANO ,  Yuki KOBAYASHI ,  Hiroshi CHISHIMA ,  Akihiro YATABE

IPC: G06N10/60 ,  G06F17/11

CPC classification number: G06N10/60 ,  G06F17/11

Abstract: An information processing device that compares a data amount of a QUBO model to be processed by an annealing engine and a data amount of a program representing the QUBO model, and that transmits whichever has a lower data amount to the annealing engine.

公开(公告)号：US20230315807A1

公开(公告)日：2023-10-05

申请号：US18015246

申请日：2020-07-17

Applicant: NEC Corporation

Inventor： Fumiyo TAKANO ,  Hiroaki INOUE ,  Takuya ARAKI ,  Motoi SUZUKI ,  Yuki KOBAYASHI ,  Hiroshi CHISHIMA ,  Akihir YATABE ,  Takahiro NISHIMURA

IPC: G06F17/18

CPC classification number: G06F17/18

Abstract: The annealing execution means 73 executes annealing using an energy function, when a solution to a combinatorial optimization problem, and the energy function of a model representing states of individual spins by a first value or a second value which is used to obtain the solution are given, and derives multiple new solutions to the combinatorial optimization problem. The solution determination means 74 determines a solution from among the multiple solutions derived by the annealing execution means 73, based on a solution determination rule for determining a solution among the multiple new solutions and the given solution to the combinatorial optimization problem.

公开(公告)号：US20220215237A1

公开(公告)日：2022-07-07

申请号：US17607540

申请日：2019-05-08

Applicant: NEC corporation

Inventor： Takashi TAKENAKA ,  Fumiyo TAKANO ,  Seiya SHIBATA ,  Hiroaki INOUE

IPC: G06N3/063 ,  G06N3/08

Abstract: Each chip 70 includes weight storage unit for storing weights for each edge determined by learning under the condition that channels in a first layer that is a layer in a neural network and channels in a 0th layer that is a previous layer to the first layer are divided into groups whose number is equal to the number of the chips, respectively, the groups of the channels in the first layer and the groups of the channels in the 0th layer and the chips are associated, an edge is set between the channels belonging to corresponding groups, an edge is set between the channels belonging to non-corresponding groups under a restriction. The weight storage unit stores the weights determined for the edge between the channels, each of which corresponds to each chip including the weight storage unit, belonging to corresponding groups.

公开(公告)号：US20220207339A1

公开(公告)日：2022-06-30

申请号：US17607473

申请日：2019-05-08

Applicant: NEC Corporation

Inventor： Takashi TAKENAKA ,  Fumiyo TAKANO ,  Seiya SHIBATA ,  Hiroaki INOUE

IPC: G06N3/063

Abstract: The determining unit 72 divides channels in the 0th layer and channels in the first layer into groups whose number is equal to the number of chips that are included in an operation device executing an operation of the neural network using a learning result of the weight for each edge, respectively. The determining unit 72 determines association of the groups of the channels in the 0th layer and the groups of the channels in the first layer and the chips included in the operation device, and edges to be removed, and removes the edges to be removed. The weight assignment unit 73 stores the weights of the edges in the weight storage unit in the chip corresponding to the edge.