Optical neuron

US11157807B2 · US · B2

Patent metadata
FieldValue
Publication numberUS-11157807-B2
Application numberUS-201815953438-A
CountryUS
Kind codeB2
Filing dateApr 14, 2018
Priority dateApr 14, 2018
Publication dateOct 26, 2021
Grant dateOct 26, 2021

How to read this patent

A practical reading order for non-experts. Skip the full description unless you need deep technical detail.

  1. Title

    What the patent document calls the invention.

  2. Abstract

    A short plain-language summary of the technical disclosure.

  3. Assignees and inventors

    Who owns or filed the patent and who is credited as inventor.

  4. Key dates

    Filing, priority, publication, and grant dates set the timeline.

  5. First independent claim

    The legal scope of protection — read this for what is actually claimed.

  6. CPC / IPC classifications

    Technology tags used to group this patent with similar filings.

  7. Citations and related patents

    Prior art links and similar publications in this corpus.

Abstract

Official abstract text for this publication.

An integrated optical circuit for an optical neural network is provided. The optical circuit is configured to process a plurality of phase-encoded optical input signals and to provide a phase-encoded optical output signal depending on the phase-encoded optical input signals. The phase-encoded optical output signal emulates a neuron functionality with respect to the plurality of phase-encoded optical input signals. Such an embodied optical circuit uses the phase to encode information in the optical domain. A related method and a related design structure are further provided.

First claim

Opening claim text (preview).

What is claimed is: 1. An integrated optical circuit for an optical neural network, the optical circuit being configured: to process a plurality of phase-encoded optical input signals; and to provide a phase-encoded optical output signal as a function of the phase-encoded optical input signals, the phase-encoded optical output signal emulating a neuron functionality with respect to the plurality of phase-encoded optical input signals; the integrated optical circuit comprising: a reference waveguide configured to carry an optical reference signal; a plurality of input waveguides configured to receive the plurality of phase-encoded optical input signals, wherein phase differences between the optical reference signal and the optical input signals represent the respective phase of the respective phase-encoded optical input signal; an output waveguide; an optical interferometer system configured: to superimpose the plurality of optical input signals and the optical reference signal into a plurality of first interference signals; and to superimpose the plurality of first interference signals into a second interference signal; and a phase-shifting device configured to provide the phase-encoded optical output signal as a function of the second interference signal. 2. The integrated optical circuit according to claim 1 , wherein the integrated optical circuit is configured: to convert the plurality of phase-encoded optical input signals into a plurality of amplitude-encoded signals; to combine the plurality of amplitude-encoded signals into a summation signal; and to perform a non-linear conversion of the summation signal into the phase-encoded optical output signal. 3. The integrated optical circuit according to claim 1 , further comprising: a plurality of first interferometers, each of the first interferometers being configured: to receive the optical reference signal and one of the plurality of optical input signals; and to superimpose the optical reference signal and the optical input signals into the plurality of first interference signals; and a second interferometer configured to receive the plurality of first interference signals and to superimpose the plurality of first interference signals into the second interference signal. 4. The integrated optical circuit according to claim 1 , wherein the optical interferometer system comprises at least one of one or more multi-mode interferometers and one or more single-mode interferometers. 5. The integrated optical circuit according to claim 1 , wherein the phase-encoded optical output signal comprises a phase shift within a predefined range relative to the optical reference signal. 6. The integrated optical circuit according to claim 1 , further comprising a power normalization unit configured to perform a normalization of an output power of the phase-encoded optical output signal. 7. The integrated optical circuit according to claim 1 , wherein the phase-shifting device comprises a non-linear material providing a non-linear power-to-refractive-index conversion. 8. The integrated optical circuit according to claim 1 , wherein the phase-shifting device comprises a phase change material. 9. The integrated optical circuit according to claim 1 , wherein the phase-shifting device comprises a plasma dispersion modulator. 10. The integrated optical circuit according to claim 1 , wherein the phase-shifting device comprises: an optical cavity comprising a non-linear material; and a gate waveguide coupled to the optical cavity and configured to guide the second interference signal to the optical cavity and to change the refractive index of the non-linear material as a function of the optical power of the second interference signal; wherein the optical cavity is configured: to receive the optical reference signal; to induce a phase shift in the optical reference signal; and to provide the phase-encoded optical output signal. 11. The integrated optical circuit according to claim 5 , wherein the predefined range is a range between 0° and 180°. 12. The integrated optical circuit according to claim 6 , wherein the power normalization unit comprises an amplifier and a saturated absorber. 13. The integrated optical circuit according to claim 7 , wherein the nonlinear material is selected from the group consisting of: BaTiO3, LiNbO3, ferroelectric perovskites, polymers with non-linear optical properties, chalcogenides and III-V compound semiconductors. 14. The integrated optical circuit according to claim 8 , wherein the phase change material is selected from the group consisting of: VO2, V4O7, V6O11, V2O3, V6O13, V5O9, VO, V8O15, NbO2, Ti2O3, LaCoO3, Ti3O5, SmNiO3, NdNiO3, PrNiO3, Fe3O4 and chalcogenides. 15. A method for emulating a neuron functionality, the method comprising: providing an integrated optical circuit; processing, by the integrated optical circuit, a phase-encoded optical input signal; emulating, by the integrated optical circuit, a neuron functionality with respect to the phase-encoded optical input signal; and providing, by the integrated optical circuit, a phase-encoded optical output signal carrying, by a reference waveguide, an optical reference signal; receiving, by a plurality of input waveguides, the plurality of phase-encoded optical input signals, wherein phase differences between the optical reference signal and the optical input signals represent the respective phase of the respective phase encoded input signal; superimposing, by an optical interferometer system, the plurality of optical input signals and the optical reference signal into a plurality of first interference signals; superimposing, by the optical interferometer system, the plurality of first interference signals into a second interference signal; and providing, by a phase-shifting device, the phase-encoded optical output signal as a function of the second interference signal. 16. The method according to claim 15 , further comprising: converting the plurality of phase-encoded optical input signals into a plurality of amplitude-encoded signals; combining the plurality of amplitude-encoded signals into a summation signal; and performing a non-linear conversion of the summation signal into the phase-encoded optical output signal. 17. An optical neural network, comprising: a plurality of integrated optical circuits as neurons, each of at least a subset of the integrated optical circuits being configured: to process a plurality of phase-encoded optical input signals; and to provide a phase-encoded optical output signal as a function of the phase-encoded optical input signals, the phase-encoded optical output signal emulating a neuron functionality with respect to the plurality of phase-encoded optical input signals; a plurality of further integrated optical circuits as synapse circuits, the synapse circuits being configured: to process a phase-encoded optical input signal; and to provide a phase-encoded output signal, the phase-encoded optical output signal emulating a synapse functionality with respect to the phase-encoded optical input signal; wherein the synapse circuits are configured: to convert the phase-encoded optical input signal into an amplitude-encoded signal; to perform a weighting of the amplitude-encoded signal; and to convert the weighted amplitude-encoded signal into the phase-encoded optical output signal; the synapse circuits comprising: a reference waveguide configured to carry an optical reference signal; an input waveguide configured to receive the phase-encoded optical

Assignees

Inventors

Classifications

  • Architecture, e.g. interconnection topology · CPC title

  • Feedforward networks · CPC title

  • G06N3/067Primary

    using optical means · CPC title

  • Constructional details or arrangements of non-linear optical devices, e.g. shape of non-linear crystals · CPC title

  • characterised by the materials used · CPC title

Patent family

Related publications grouped by family.

External sources

Frequently asked questions

Answers are generated from the same data shown on this page.

What does patent US11157807B2 cover?
An integrated optical circuit for an optical neural network is provided. The optical circuit is configured to process a plurality of phase-encoded optical input signals and to provide a phase-encoded optical output signal depending on the phase-encoded optical input signals. The phase-encoded optical output signal emulates a neuron functionality with respect to the plurality of phase-encoded op…
Who is the assignee on this patent?
IBM
What technology area does this patent fall under?
Primary CPC classification G06N3/067. Mapped technology areas include Physics.
When was this patent published?
Publication date Tue Oct 26 2021 00:00:00 GMT+0000 (Coordinated Universal Time) (B2). Legal status and post-grant events are not shown on this page.
What related patents are in patentsdb?
We list 5 related publications on this page (citations in our corpus or others sharing the same primary CPC).