Spiking Neuron Apparatus Using Coherent Ising Machine

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Dedicated semiconductor processors used for spiking neurons face inefficiencies in processing time and difficulty in controlling the type of spiking, as they perform electrical signal processing and are limited in simulating biological spiking dynamics.

Innovation Solution

A spiking neuron apparatus utilizing a coherent Ising machine with a resonator unit, measurement unit, and feedback configuration to simulate spiking neurons using optical pulses, allowing for efficient processing and control of spiking types by adjusting pump light intensity and coupling coefficients.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Manufacturing precision

If dedicated semiconductor processors are used for spiking neuron simulation, then the device can be manufactured with high precision, but the processing time increases and the ability to control spiking types is limited

Engineering Contradiction:

Improvedevice manufacturing precisionVSAvoidprocessing time

Core Design Contradiction:

Manufacturing precisionVSLoss of time

Solution Approach 1:

The patent replaces electrical signal processing in semiconductor processors with optical signal processing using optical parametric oscillators. Optical pulses propagate through resonators and interact via optical coupling, enabling parallel processing without the sequential electrical signal transmission delays inherent in semiconductor-based systems. This substitution of optical for electrical mechanisms resolves the contradiction by achieving both manufacturing precision and reduced processing time.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The patent introduces dynamic control of spiking behavior through adjustable pump light intensity and coupling coefficients. The optical system allows real-time modulation of oscillator dynamics, enabling flexible control over spiking types (Type I and Type II) and dynamics speed. This dynamic adjustability resolves the contradiction by maintaining precise device operation while enabling rapid reconfiguration for different computational tasks.

Inventive Principle:

Principle #15Dynamics

2Device complexity

If dedicated semiconductor processors are used for spiking neuron simulation, then the device structure can be simplified, but the control flexibility over spiking types is reduced

Engineering Contradiction:

Improvedevice structure complexityVSAvoidcontrol flexibility

Core Design Contradiction:

Device complexityVSAdaptability or versatility

Solution Approach 1:

The patent achieves control flexibility through parameter modulation of the optical system. By adjusting pump light intensity, coupling coefficients between resonators, and resonator characteristics, the system can dynamically switch between different spiking types and computational modes. These parameter changes enable versatile control without requiring complex structural modifications, resolving the contradiction between device simplicity and adaptability.

Inventive Principle:

Principle #35Parameter changes

Solution Approach 2:

The optical parametric oscillator system serves multiple functions within a unified structure. The same resonator network can simulate different types of spiking neurons, perform various combinatorial optimization algorithms, and adapt to different computational problems by reconfiguring optical coupling parameters. This multi-functionality resolves the contradiction by providing high versatility through parameter control rather than structural complexity.

Inventive Principle:

Principle #6Universality (Multi-functionality)

Applied Scientific Principles

This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.

Function Achieved in This Case

The apparatus achieves efficient simulation of spiking neurons with controlled dynamics speed and type, enabling faster processing and more precise control of spiking behaviors, overcoming limitations of traditional semiconductor processors.

Implementation Method 1

a resonator unit for amplifying a plurality of optical pulses

Methodology Applied

Scientific EffectOptical parametric oscillation:

Data Source

PatentUS12182696B2Spiking neuron device and combinatorial optimization problem calculation device

Publication Date: 2024.12.31 NIPPON TELEGRAPH & TELEPHONE CORP

AI summary

To provide a spiking neuron apparatus able to efficiently implement a simulation of a spiking neuron. A spiking neuron apparatus using a coherent Ising machine, the coherent Ising machine including: a resonator unit for amplifying a plurality of optical pulses; a measurement unit for measuring phases and amplitudes of the optical pulses to obtain a measurement result; and a feedback configuration for computing and feeding back an interaction related to a certain optical pulse using a coupling coefficient of Ising Model on the basis of the measurement result, the feedback configuration feedback inputting correlation determined by two coupling coefficients with opposite signs to two predetermined optical pulses of the optical pulses, the spiking neuron apparatus simulating a state of a spiking neuron using one of values of two optical pulses finally obtained by the measurement unit.