The patent badge is an abbreviated version of the USPTO patent document. The patent badge does contain a link to the full patent document.

The patent badge is an abbreviated version of the USPTO patent document. The patent badge covers the following: Patent number, Date patent was issued, Date patent was filed, Title of the patent, Applicant, Inventor, Assignee, Attorney firm, Primary examiner, Assistant examiner, CPCs, and Abstract. The patent badge does contain a link to the full patent document (in Adobe Acrobat format, aka pdf). To download or print any patent click here.

Date of Patent:
May. 17, 2022

Filed:

Aug. 06, 2020
Applicant:

Massachusetts Institute of Technology, Cambridge, MA (US);

Inventors:

Jacques Johannes Carolan, Cambridge, MA (US);

Mihika Prabhu, Cambridge, MA (US);

Scott A. Skirlo, Boston, MA (US);

Yichen Shen, Cambridge, MA (US);

Marin Soljacic, Belmont, MA (US);

Dirk Englund, Brookline, MA (US);

Nicholas Christopher Harris, Boston, MA (US);

Assignee:
Attorney:
Primary Examiner:
Assistant Examiner:
Int. Cl.
CPC ...
G06E 3/00 (2006.01); G06N 3/04 (2006.01); G06N 3/08 (2006.01); G02F 1/225 (2006.01); G02F 1/35 (2006.01); G02F 1/365 (2006.01); G02F 3/02 (2006.01); G06N 3/067 (2006.01); G02F 1/21 (2006.01);
U.S. Cl.
CPC ...
G06E 3/005 (2013.01); G02F 1/225 (2013.01); G02F 1/3526 (2013.01); G02F 1/365 (2013.01); G02F 3/024 (2013.01); G06E 3/006 (2013.01); G06E 3/008 (2013.01); G06N 3/04 (2013.01); G06N 3/0675 (2013.01); G06N 3/08 (2013.01); G06N 3/084 (2013.01); G02F 1/212 (2021.01); G02F 2202/32 (2013.01); G02F 2203/15 (2013.01);
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.


Find Patent Forward Citations

Loading…