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.

公开(公告)号：US20190310070A1

公开(公告)日：2019-10-10

申请号：US16433649

申请日：2019-06-06

Applicant: Massachusetts Institute of Technology

Inventor： JACOB C. MOWER ,  Nicholas C. HARRIS ,  DIRK ENGLUND ,  GREG STEINBRECHER

IPC: G01B9/02 ,  G06N10/00 ,  B82Y20/00 ,  G06N20/00

Abstract: A programmable photonic integrated circuit implements arbitrary linear optics transformations in the spatial mode basis with high fidelity. Under a realistic fabrication model, we analyze programmed implementations of the CNOT gate, CPHASE gate, iterative phase estimation algorithm, state preparation, and quantum random walks. We find that programmability dramatically improves device tolerance to fabrication imperfections and enables a single device to implement a broad range of both quantum and classical linear optics experiments. Our results suggest that existing fabrication processes are sufficient to build such a device in the silicon photonics platform.