Apparatus and methods for optical neural network

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...

Full description

Saved in:
Bibliographic Details
Main Authors Soljacic, Marin, Harris, Nicholas Christopher, Skirlo, Scott A, Carolan, Jacques Johannes, Shen, Yichen, Prabhu, Mihika, Englund, Dirk Robert
Format Patent
LanguageEnglish
Published 23.04.2019
Subjects
CALCULATING
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
COMPUTING
COUNTING
DEVICES OR ARRANGEMENTS, THE OPTICAL OPERATION OF WHICH ISMODIFIED BY CHANGING THE OPTICAL PROPERTIES OF THE MEDIUM OF THEDEVICES OR ARRANGEMENTS FOR THE CONTROL OF THE INTENSITY,COLOUR, PHASE, POLARISATION OR DIRECTION OF LIGHT, e.g.SWITCHING, GATING, MODULATING OR DEMODULATING
FREQUENCY-CHANGING
NON-LINEAR OPTICS
OPTICAL ANALOGUE/DIGITAL CONVERTERS
OPTICAL COMPUTING DEVICES
OPTICAL LOGIC ELEMENTS
OPTICS
PHYSICS
TECHNIQUES OR PROCEDURES FOR THE OPERATION THEREOF
Online AccessGet full text

Cover

More Information
Summary: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.
Bibliography:Application Number: US201715612043