# US 2019/0244098 A1 · Optimization system, optimization apparatus, and optimization system control method

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2019/0244098 A1
- Document ID: US20190244098A1
- Status: Published application
- Kind: A1
- Application number: 16/266,165
- Filed: 2019-02-04
- Published: 2019-08-08
- Earliest claimed: 2018-02-06
- Assignees: Fujitsu Limited
- Applicants: Fujitsu Limited
- Inventors: Sanroku TSUKAMOTO; SATOSHI MATSUBARA; Hirotaka TAMURA
- Web page: https://patentgrep.com/patent/US20190244098A1

## CPC

- G06N 3/063: using electronic means
- G06N 3/08: Learning methods
- G06N 3/044: Recurrent networks, e.g. Hopfield networks
- G06N 3/047: Probabilistic or stochastic networks
- G06N 3/0495: Quantised networks; Sparse networks; Compressed networks
- G06N 5/01: Dynamic search techniques; Heuristics; Dynamic trees; Branch-and-bound
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

An optimization apparatus calculates a first portion, among energy change caused by change in value of a neuron of a neuron group, caused by influence of another neuron of the neuron group, determines whether to allow updating the value, based on a sum of the first and second portions of the energy change, and repeats a process of updating or maintaining the value according to the determination. An arithmetic processing apparatus calculates the second portion caused by influence of a neuron not belonging to the neuron group and an initial value of the sum. A control apparatus transmits data for calculating the second portion and the initial value to the arithmetic processing apparatus, and the initial value and data for calculating the first portion to the optimization apparatus, and receives the initial value from the arithmetic processing apparatus, and a value of the neuron group from the optimization apparatus.

## Claims

### Claim 1

An optimization system comprising:
an optimization apparatus configured to calculate a first change portion of an energy change caused by a change in a value of a first neuron that belongs to a neuron group selected from all neurons corresponding to all state variables of an evaluation function indicative of an energy, the first change portion being caused by an influence of another neuron that belongs to the neuron group, determine by a stochastic search whether to allow an update of the value of the first neuron, based on a sum of the first change portion and a second change portion of the energy change, and repeat an update process of updating or maintaining the value of the first neuron according to a result of determining whether to allow the update;
an arithmetic processing apparatus configured to calculate an initial value of the sum and the second change portion caused by an influence of a second neuron that is included in all the neurons but does not belong to the neuron group; and
a control apparatus configured to select the neuron group from all the neurons, transmit to the arithmetic processing apparatus first data for calculating the second change portion and the initial value, receive the initial value from the arithmetic processing apparatus, transmit to the optimization apparatus the initial value and second data for calculating the first change portion, and receive a value of the neuron group from the optimization apparatus.

### Claim 2 (depends on 1)

The optimization system according to claim 1, wherein:
the first data include a first weighting coefficient group whose values are set so that the first neuron is coupled to some of all the neurons, the some of the all the neurons including the second neuron; and
the second data include a second weighting coefficient group whose values are set so that the first neuron is coupled to all other neurons of the neuron group.

### Claim 3 (depends on 1)

The optimization system according to claim 1, further comprising:
a plurality of optimization apparatuses including the optimization apparatus,
wherein:
the plurality of optimization apparatuses perform the update process for different neuron groups; and
the control apparatus transmits, upon selection of a first neuron group, the sum updated based on a value of a previously selected second neuron group received from a first optimization apparatus that has performed the update process for the second neuron group to a second optimization apparatus that performs the update process for the first neuron group.

### Claim 4 (depends on 2)

The optimization system according to claim 2, wherein:
the control apparatus transmits the first weighting coefficient group to the optimization apparatus, detects an updated neuron by the value of the neuron group received from the optimization apparatus, and transmits information regarding the updated neuron to the optimization apparatus; and
the optimization apparatus updates the sum, based on the first weighting coefficient group and the information received.

### Claim 5 (depends on 2)

The optimization system according to claim 2, further comprising:
a plurality of optimization apparatuses including the optimization apparatus,
wherein:
the plurality of optimization apparatuses perform the update process for different neuron groups;
the control apparatus transmits the first weighting coefficient group to the plurality of optimization apparatuses, detects an updated neuron by the value of the neuron group received from a first optimization apparatus that has performed the update process for the neuron group, and transmits information regarding the updated neuron to a second optimization apparatus different from the first optimization apparatus among the plurality of optimization apparatuses; and
the second optimization apparatus updates the sum, based on the first weighting coefficient group and the information received.

### Claim 6

An optimization apparatus comprising:
a storage section configured to store data for calculating a first change portion of an energy change caused by a change in a value of a first neuron that belongs to a neuron group selected from all neurons corresponding to all state variables of an evaluation function indicative of an energy, the first change portion being caused by an influence of another neuron that belongs to the neuron group, and an initial value of a sum of the first change portion and a second change portion of the energy change, the second change portion being caused by an influence of a second neuron that is included in all the neurons but does not belong to the neuron group; and
a stochastic search circuit configured to calculate the first change portion, based on the data, determine by a stochastic search whether to allow an update of the value of the first neuron, based on the sum, and repeat an update process of updating or maintaining the value of the first neuron according to a result of determining whether to allow the update.

### Claim 7

An optimization system control method comprising:
calculating, by an optimization apparatus included in an optimization system, a first change portion of an energy change caused by a change in a value of a first neuron that belongs to a neuron group selected from all neurons corresponding to all state variables of an evaluation function indicative of an energy, the first change portion being caused by an influence of another neuron that belongs to the neuron group, determining by a stochastic search whether to allow an update of the value of the first neuron, based on a sum of the first change portion and a second change portion of the energy change, and repeating an update process of updating or maintaining the value of the first neuron according to a result of determining whether to allow the update;
calculating, by an arithmetic processing apparatus included in the optimization system, an initial value of the sum and the second change portion caused by an influence of a second neuron that is included in all the neurons but does not belong to the neuron group; and
selecting, by a control apparatus included in the optimization system, the neuron group from all the neurons, transmitting to the arithmetic processing apparatus first data for calculating the second change portion and the initial value, receiving the initial value from the arithmetic processing apparatus, transmitting to the optimization apparatus the initial value and second data for calculating the first change portion, and receiving a value of the neuron group from the optimization apparatus.
