公开(公告)号：US20230274156A1

公开(公告)日：2023-08-31

申请号：US18247129

申请日：2021-07-29

Applicant: Ryan HAMERLY ,  Dirk Robert ENGLUND ,  Massachusetts Institute of Technology

Inventor： Ryan HAMERLY ,  Dirk Robert ENGLUND

IPC: G06N3/098 ,  G06N5/04

CPC classification number: G06N3/098 ,  G06N5/04

Abstract: NetCast is an optical neural network architecture that circumvents constraints on deep neural network (DNN) inference at the edge. Many DNNs have weight matrices that are too large to run on edge processors, leading to limitations on DNN inference at the edge or bandwidth bottlenecks between the edge and server that hosts the DNN. With NetCast, a weight server stores the DNN weight matrix in local memory, modulates the weights onto different spectral channels of an optical carrier, and distributes the weights to one or more clients via optical links. Each client stores the activations, or layer inputs, for the DNN and computes the matrix-vector product of those activations with the weights from the weight server in the optical domain. This multiplication can be performed coherently by interfering the spectrally multiplexed weights with spectrally multiplexed activations or incoherently by modulating the weight signal from the weight server with the activations.

公开(公告)号：US20250111218A1

公开(公告)日：2025-04-03

申请号：US18863245

申请日：2023-05-15

Applicant: Massachusetts Institute of Technology

Inventor： Zaijun Chen ,  Ryan HAMERLY ,  Dirk Robert ENGLUND

IPC: G06N3/067

Abstract: The exponential growth in deep learning models is challenging existing computing hardware. Optical neural networks (ONNs) accelerate machine learning tasks with potentially ultrahigh bandwidth and nearly no loss in data movement. Scaling up ONNs involves improving scalability, energy efficiency, compute density, and inline nonlinearity. However, realizing all these criteria remains an unsolved challenge. Here, we demonstrate a three-dimensional spatial time-multiplexed ONN architecture based on dense arrays of microscale vertical cavity surface emitting lasers (VCSELs). The VCSELs, coherently injection-locked to a leader laser, operate at gigahertz data rates with a 7T-phase-shift voltage on the 10-millivolt level. Optical nonlinearity is incorporated into the ONN with no added energy cost using coherent detection of optical interference between VCSELs.

公开(公告)号：US20240244354A1

公开(公告)日：2024-07-18

申请号：US18561985

申请日：2022-05-20

Applicant: Massachusetts Institute of Technology

Inventor： Manya Ghobadi ,  Zhizhen Zhong ,  Weiyang Wang ,  Liane Sarah Beland Bernstein ,  Alexander Sludds ,  Ryan HAMERLY ,  Dirk Robert ENGLUND

IPC: H04Q11/00 ,  G06N5/04 ,  H04B10/524

CPC classification number: H04Q11/0005 ,  G06N5/04 ,  H04B10/524 ,  H04Q2011/0039 ,  H04Q2011/0041

Abstract: In-network Optical Inference (IOI) provides low-latency machine learning inference by leveraging programmable switches and optical matrix multiplication. IOI uses a transceiver module, called a Neuro Transceiver, with an optical processor to perform linear operations, such as matrix multiplication, in the optical domain. IOI's transceiver modules can be plugged into programmable packet switches, which are programmed to perform non-linear activations in the electronic domain and to respond to inference queries. Processing inference queries at the programmable packet switches inside the network, without sending them to cloud or edge inference servers, significantly reduces end-to-end inference latency experienced by users.

公开(公告)号：US20250085100A1

公开(公告)日：2025-03-13

申请号：US18956238

申请日：2024-11-22

Applicant: Massachusetts Institute of Technology ,  NTT Research, Incorporated

Inventor： Ryan HAMERLY ,  Saumil Bandyopadhyay ,  Dirk Robert ENGLUND

IPC: G01B9/02055 ,  G01B9/02001

Abstract: Component errors prevent linear photonic circuits from being scaled to large sizes. These errors can be compensated by programming the components in an order corresponding to nulling operations on a target matrix X through Givens rotations X→T†X, X→XT†. Nulling is implemented on hardware through measurements with feedback, in a way that builds up the target matrix even in the presence of hardware errors. This programming works with unknown errors and without internal sources or detectors in the circuit. Modifying the photonic circuit architecture can reduce the effect of errors still further, in some cases even rendering the hardware asymptotically perfect in the large-size limit. These modifications include adding a third directional coupler or crossing after each Mach-Zehnder interferometer in the circuit and a photonic implementation of the generalized FFT fractal. The configured photonic circuit can be used for machine learning, quantum photonics, prototyping, optical switching/multicast networks, microwave photonics, or signal processing.