公开(公告)号：US11334107B2

公开(公告)日：2022-05-17

申请号：US16986383

申请日：2020-08-06

Applicant: Massachusetts Institute of Technology

Inventor： Jacques Johannes Carolan ,  Mihika Prabhu ,  Scott A. Skirlo ,  Yichen Shen ,  Marin Soljacic ,  Dirk Englund ,  Nicholas Christopher Harris

IPC: G06E3/00 ,  G06N3/04 ,  G06N3/08 ,  G02F1/225 ,  G02F1/35 ,  G02F1/365 ,  G02F3/02 ,  G06N3/067 ,  G02F1/21

Abstract: An optical neural network is constructed based on photonic integrated circuits to perform neuromorphic computing. In the optical neural network, matrix multiplication is implemented using one or more optical interference units, which can apply an arbitrary weighting matrix multiplication to an array of input optical signals. Nonlinear activation is realized by an optical nonlinearity unit, which can be based on nonlinear optical effects, such as saturable absorption. These calculations are implemented optically, thereby resulting in high calculation speeds and low power consumption in the optical neural network.

公开(公告)号：US20220012619A1

公开(公告)日：2022-01-13

申请号：US17239830

申请日：2021-04-26

Applicant: Massachusetts Institute of Technology

Inventor： Charles ROQUES-CARMES ,  Yichen Shen ,  Li JING ,  Tena DUBCEK ,  Scott A. SKIRLO ,  Hengameh BAGHERIANLEMRASKI ,  Marin SOLJACIC

IPC: G06N10/00 ,  G06N3/04 ,  G06N7/00 ,  G06N3/08 ,  G06N3/067

Abstract: A photonic parallel network can be used to sample combinatorially hard distributions of Ising problems. The photonic parallel network, also called a photonic processor, finds the ground state of a general Ising problem and can probe critical behaviors of universality classes and their critical exponents. In addition to the attractive features of photonic networks—passivity, parallelization, high-speed and low-power—the photonic processor exploits dynamic noise that occurs during the detection process to find ground states more efficiently.

公开(公告)号：US20190294199A1

公开(公告)日：2019-09-26

申请号：US16273257

申请日：2019-02-12

Applicant: Massachusetts Institute of Technology

Inventor： Jacques Johannes Carolan ,  Mihika Prabhu ,  Scott A. Skirlo ,  Yichen Shen ,  Marin Soljacic ,  Nicholas Christopher Harris ,  Dirk Englund

IPC: G06E3/00 ,  G02F3/02 ,  G06N3/067 ,  G02F1/225 ,  G06N3/08 ,  G02F1/35 ,  G02F1/365

Abstract: An optical neural network is constructed based on photonic integrated circuits to perform neuromorphic computing. In the optical neural network, matrix multiplication is implemented using one or more optical interference units, which can apply an arbitrary weighting matrix multiplication to an array of input optical signals. Nonlinear activation is realized by an optical nonlinearity unit, which can be based on nonlinear optical effects, such as saturable absorption. These calculations are implemented optically, thereby resulting in high calculation speeds and low power consumption in the optical neural network.

公开(公告)号：US10785858B2

公开(公告)日：2020-09-22

申请号：US15014401

申请日：2016-02-03

Applicant: Massachusetts Institute of Technology

Inventor： Ido Kaminer ,  Liang Jie Wong ,  Ognjen Ilic ,  Yichen Shen ,  John Joannopoulos ,  Marin Soljacic

IPC: H05G2/00

Abstract: An apparatus includes at least one conductive layer, an electromagnetic (EM) wave source, and an electron source. The conductive layer has a thickness less than 5 nm. The electromagnetic (EM) wave source is in electromagnetic communication with the at least one conductive layer and transmits a first EM wave at a first wavelength in the at least one conductive layer so as to generate a surface plasmon polariton (SPP) field near a surface of the at least one conductive layer. The electron source propagates an electron beam at least partially in the SPP field so as to generate a second EM wave at a second wavelength less than the first wavelength.

公开(公告)号：US10268232B2

公开(公告)日：2019-04-23

申请号：US15612043

申请日：2017-06-02

Applicant: Massachusetts Institute of Technology

Inventor： Nicholas Christopher Harris ,  Jacques Johannes Carolan ,  Mihika Prabhu ,  Dirk Robert Englund ,  Scott A. Skirlo ,  Yichen Shen ,  Marin Soljacic

IPC: G02F1/21 ,  G02F3/02 ,  G06E3/00 ,  G06N3/08 ,  G02F1/225 ,  G02F1/365 ,  G06N3/067 ,  G02F1/35

Abstract: An optical neural network is constructed based on photonic integrated circuits to perform neuromorphic computing. In the optical neural network, matrix multiplication is implemented using one or more optical interference units, which can apply an arbitrary weighting matrix multiplication to an array of input optical signals. Nonlinear activation is realized by an optical nonlinearity unit, which can be based on nonlinear optical effects, such as saturable absorption. These calculations are implemented optically, thereby resulting in high calculation speeds and low power consumption in the optical neural network.

公开(公告)号：US12287842B2

公开(公告)日：2025-04-29

申请号：US17239830

申请日：2021-04-26

Applicant: Massachusetts Institute of Technology

Inventor： Charles Roques-Carmes ,  Yichen Shen ,  Li Jing ,  Tena Dubcek ,  Scott A. Skirlo ,  Hengameh Bagherianlemraski ,  Marin Soljacic

IPC: G06E3/00 ,  G06F17/16 ,  G06N3/044 ,  G06N3/045 ,  G06N3/047 ,  G06N3/067 ,  G06N3/084 ,  G06N7/01 ,  G06F17/18 ,  G06N3/04 ,  G06N3/08 ,  G06N7/00 ,  G06N10/00

Abstract: A photonic parallel network can be used to sample combinatorially hard distributions of Ising problems. The photonic parallel network, also called a photonic processor, finds the ground state of a general Ising problem and can probe critical behaviors of universality classes and their critical exponents. In addition to the attractive features of photonic networks—passivity, parallelization, high-speed and low-power—the photonic processor exploits dynamic noise that occurs during the detection process to find ground states more efficiently.

公开(公告)号：US11914415B2

公开(公告)日：2024-02-27

申请号：US17736667

申请日：2022-05-04

Applicant: Massachusetts Institute of Technology

Inventor： Jacques Johannes Carolan ,  Mihika Prabhu ,  Scott A. Skirlo ,  Yichen Shen ,  Marin Soljacic ,  Dirk Englund ,  Nicholas C. Harris

IPC: G06E3/00 ,  G06N3/04 ,  G06N3/084 ,  G02F1/225 ,  G02F1/35 ,  G02F1/365 ,  G02F3/02 ,  G06N3/067 ,  G06N3/08 ,  G02F1/21

CPC classification number: G06E3/005 ,  G02F1/225 ,  G02F1/3526 ,  G02F1/365 ,  G02F3/024 ,  G06E3/006 ,  G06E3/008 ,  G06N3/04 ,  G06N3/0675 ,  G06N3/08 ,  G06N3/084 ,  G02F1/212 ,  G02F2202/32 ,  G02F2203/15

Abstract: An optical neural network is constructed based on photonic integrated circuits to perform neuromorphic computing. In the optical neural network, matrix multiplication is implemented using one or more optical interference units, which can apply an arbitrary weighting matrix multiplication to an array of input optical signals. Nonlinear activation is realized by an optical nonlinearity unit, which can be based on nonlinear optical effects, such as saturable absorption. These calculations are implemented optically, thereby resulting in high calculation speeds and low power consumption in the optical neural network.

公开(公告)号：US11017309B2

公开(公告)日：2021-05-25

申请号：US16032737

申请日：2018-07-11

Applicant: Massachusetts Institute of Technology

Inventor： Charles Roques-Carmes ,  Yichen Shen ,  Li Jing ,  Tena Dubcek ,  Scott A. Skirlo ,  Hengameh Bagherianlemraski ,  Marin Soljacic

IPC: G06E3/00 ,  G06N10/00 ,  G06N3/04 ,  G06N7/00 ,  G06N3/08 ,  G06N3/067 ,  G06F17/16 ,  G06F17/18

Abstract: A photonic parallel network can be used to sample combinatorially hard distributions of Ising problems. The photonic parallel network, also called a photonic processor, finds the ground state of a general Ising problem and can probe critical behaviors of universality classes and their critical exponents. In addition to the attractive features of photonic networks—passivity, parallelization, high-speed and low-power—the photonic processor exploits dynamic noise that occurs during the detection process to find ground states more efficiently.

公开(公告)号：US12209826B2

公开(公告)日：2025-01-28

申请号：US16460683

申请日：2019-07-02

Applicant: MASSACHUSETTS INSTITUTE OF TECHNOLOGY

Inventor： Marin Soljacic ,  Evelyn Wang ,  Yichen Shen ,  Bikramjit Bhatia ,  Arny Leroy

IPC: F28F9/20 ,  F24F5/00 ,  F25B23/00 ,  F28F13/18

Abstract: A radiative cooling device can include a reflector positionable to permit operation during daylight hours.

公开(公告)号：US20230045938A1

公开(公告)日：2023-02-16

申请号：US17736667

申请日：2022-05-04

Applicant: Massachusetts Institute of Technology

Inventor： Jacques Johannes CAROLAN ,  Mihika PRABHU ,  Scott A. SKIRLO ,  Yichen Shen ,  Marin SOLJACIC ,  DIRK ENGLUND ,  Nicholas C. HARRIS

IPC: G06E3/00 ,  G06N3/04 ,  G06N3/08 ,  G02F1/225 ,  G02F1/35 ,  G02F1/365 ,  G02F3/02 ,  G06N3/067

Abstract: An optical neural network is constructed based on photonic integrated circuits to perform neuromorphic computing. In the optical neural network, matrix multiplication is implemented using one or more optical interference units, which can apply an arbitrary weighting matrix multiplication to an array of input optical signals. Nonlinear activation is realized by an optical nonlinearity unit, which can be based on nonlinear optical effects, such as saturable absorption. These calculations are implemented optically, thereby resulting in high calculation speeds and low power consumption in the optical neural network.