Patents Assigned to Lightmatter, Inc
  • Publication number: 20210157547
    Abstract: Photonic processors are described. The photonic processors described herein are configured to perform matrix-matrix (e.g., matrix-vector) multiplication. Some embodiments relate to photonic processors arranged according to a dual-rail architecture, in which numeric values are encoded in the difference between a pair optical signals (e.g., in the difference between the powers of the optical signals). Relative to other architectures, these photonic processors exhibit increased immunity to noise. Some embodiments relate to photonic processors including modulatable detector-based multipliers. Modulatable detectors are detectors designed so that the photocurrent can be modulated according to an electrical control signal. Photonic processors designed using modulatable detector-based multipliers are significantly more compact than other types of photonic processors.
    Type: Application
    Filed: November 20, 2020
    Publication date: May 27, 2021
    Applicant: Lightmatter, Inc.
    Inventors: Darius Bunandar, Nicholas C. Harris, Michael Gould, Carl Ramey, Shashank Gupta, Carlos Dorta-Quinones
  • Publication number: 20210157878
    Abstract: Photonic processors are described. The photonic processors described herein are configured to perform matrix-matrix (e.g., matrix-vector) multiplication. Some embodiments relate to photonic processors arranged according to a dual-rail architecture, in which numeric values are encoded in the difference between a pair optical signals (e.g., in the difference between the powers of the optical signals). Relative to other architectures, these photonic processors exhibit increased immunity to noise. Some embodiments relate to photonic processors including modulatable detector-based multipliers. Modulatable detectors are detectors designed so that the photocurrent can be modulated according to an electrical control signal. Photonic processors designed using modulatable detector-based multipliers are significantly more compact than other types of photonic processors.
    Type: Application
    Filed: November 23, 2020
    Publication date: May 27, 2021
    Applicant: Lightmatter, Inc.
    Inventors: Darius Bunandar, Nicholas C. Harris, Michael Gould, Carl Ramey, Shashank Gupta, Carlos Dorta-Quinones
  • Publication number: 20210125066
    Abstract: Described herein are techniques for determining an architecture of a machine learning model that optimizes the machine learning model. The system obtains a machine learning model configured with a first architecture of a plurality of architectures. The machine learning model has a first set of parameters. The system determines a second architecture using a quantization of the parameters of the machine learning model. The system updates the machine learning model to obtain a machine learning model configured with the second architecture.
    Type: Application
    Filed: October 27, 2020
    Publication date: April 29, 2021
    Applicant: Lightmatter, Inc.
    Inventor: Tomo Lazovich
  • Publication number: 20210089906
    Abstract: Methods and apparatus for pre-processing first data for use with a trained machine learning model. In some embodiments, the method may comprise accessing the first data, wherein the first data has a first precision; generating, based on at least a first portion of the first data, second data having a second precision lower than the first precision; and providing the second data as input to the trained machine learning model to generate model output.
    Type: Application
    Filed: September 22, 2020
    Publication date: March 25, 2021
    Applicant: Lightmatter, Inc.
    Inventor: Tomo Lazovich
  • Publication number: 20210036783
    Abstract: Systems and methods for performing signed matrix operations using a linear photonic processor are provided. The linear photonic processor is formed as an array of first amplitude modulators and second amplitude modulators, the first amplitude modulators configured to encode elements of a vector into first optical signals and the second amplitude modulators configured to encode a product between the vector elements and matrix elements into second optical signals. An apparatus may be used to implement a signed value of an output of the linear processor. The linear photonic processor may be configured to perform matrix-vector and/or matrix-matrix operations.
    Type: Application
    Filed: July 28, 2020
    Publication date: February 4, 2021
    Applicant: Lightmatter, Inc.
    Inventors: Darius Bunandar, Nicholas C. Harris, Michael Gould, Carl Ramey, Tomo Lazovich
  • Publication number: 20210003904
    Abstract: Methods and apparatus for tuning a photonics-based component. An opto-electrical detector is configured to output an electrical signal based on a measurement of light intensity of the photonics-based component, the light intensity being proportional to an amount of detuning of the photonics-based component. Analog-to-digital conversion (ADC) circuitry is configured to output a digital signal based on the electrical signal output from the opto-electrical detector. Feedback control circuitry is configured to tune the photonics-based component based, at least in part, on the digital signal output from the ADC circuitry.
    Type: Application
    Filed: July 1, 2020
    Publication date: January 7, 2021
    Applicant: Lightmatter, Inc.
    Inventors: Carlos Dorta-Quinones, Carl Ramey, Omer Ozgur Yildirim, Chithira Ravi, Shashank Gupta, Nicholas C. Horris
  • Patent number: 10884313
    Abstract: A nano-opto-electro-mechanical System (NOEMS) phase shifter is described. The NOEMS may include a multi-slot waveguide structure suspended in air. The multi-slot waveguide structure may include three or more waveguides separated from each other by slots. The width of the slots may be sufficiently small to support slot modes, where a substantial portion of the mode energy is within the slots. For example, the slots may have widths less than 200 nm or less than 100 nm. The multi-slot waveguide structure may be disposed in a trench formed though the upper cladding of a substrate. An undercut may be formed under the multi-slot waveguide structure to enable free motion of the structure. NOEMS phase modulators of the types described herein may be used in connection with photonic processing systems, telecom/datacom systems, analog systems, etc.
    Type: Grant
    Filed: May 14, 2019
    Date of Patent: January 5, 2021
    Assignee: Lightmatter, Inc.
    Inventor: Michael Gould
  • Publication number: 20200396007
    Abstract: Aspects relate to a photonic processing system, a photonic processor, and a method of performing matrix-vector multiplication. An optical encoder may encode an input vector into a first plurality of optical signals. A photonic processor may receive the first plurality of optical signals; perform a plurality of operations on the first plurality of optical signals, the plurality of operations implementing a matrix multiplication of the input vector by a matrix; and output a second plurality of optical signals representing an output vector. An optical receiver may detect the second plurality of optical signals and output an electrical digital representation of the output vector.
    Type: Application
    Filed: August 6, 2020
    Publication date: December 17, 2020
    Applicant: Lightmatter, Inc.
    Inventors: Darius Bunandar, Nicholas C. Harris, Carl Ramey
  • Publication number: 20200380217
    Abstract: Techniques for computing matrix operations for arbitrarily large matrices on a finite-sized hybrid analog-digital matrix processor are described. Techniques for gain adjustment in a finite-sized hybrid analog-digital matrix processor are described which enable the system to obtain higher energy efficiencies, greater physical density and improved numerical accuracy. In some embodiments, these techniques enable maximization of the predictive accuracy of a GEMM-based convolutional neural network using low-precision data representations.
    Type: Application
    Filed: August 17, 2020
    Publication date: December 3, 2020
    Applicant: Lightmatter, Inc.
    Inventors: Tyler J. Kenney, Martin B.Z. Forsythe, Tomo Lazovich, Darius Bunandar
  • Publication number: 20200334576
    Abstract: Methods and apparatus for training a matrix-based differentiable program using a photonics-based processor. The matrix-based differentiable program includes at least one matrix-valued variable associated with a matrix of values in a Euclidean vector space. The method comprises configuring components of the photonics-based processor to represent the matrix of values as an angular representation, processing, using the components of the photonics-based processor, training data to compute an error vector, determining in parallel, at least some gradients of parameters of the angular representation, wherein the determining is based on the error vector and a current input training vector, and updating the matrix of values by updating the angular representation based on the determined gradients.
    Type: Application
    Filed: June 29, 2020
    Publication date: October 22, 2020
    Applicant: Lightmatter, Inc.
    Inventors: Tomo Lazovich, Darius Bunandar, Nicholas C. Harris, Martin B.Z. Forsythe
  • Patent number: 10803259
    Abstract: Techniques for computing matrix operations for arbitrarily large matrices on a finite-sized hybrid analog-digital matrix processor are described. Techniques for gain adjustment in a finite-sized hybrid analog-digital matrix processor are described which enable the system to obtain higher energy efficiencies, greater physical density and improved numerical accuracy. In some embodiments, these techniques enable maximization of the predictive accuracy of a GEMM-based convolutional neural network using low-precision data representations.
    Type: Grant
    Filed: February 25, 2020
    Date of Patent: October 13, 2020
    Assignee: Lightmatter, Inc.
    Inventors: Tyler J. Kenney, Martin B. Z. Forsythe, Tomo Lazovich, Darius Bunandar
  • Patent number: 10803258
    Abstract: Techniques for computing matrix operations for arbitrarily large matrices on a finite-sized hybrid analog-digital matrix processor are described. Techniques for gain adjustment in a finite-sized hybrid analog-digital matrix processor are described which enable the system to obtain higher energy efficiencies, greater physical density and improved numerical accuracy. In some embodiments, these techniques enable maximization of the predictive accuracy of a GEMM-based convolutional neural network using low-precision data representations.
    Type: Grant
    Filed: February 25, 2020
    Date of Patent: October 13, 2020
    Assignee: Lightmatter, Inc.
    Inventors: Tyler J. Kenney, Martin B. Z. Forsythe, Tomo Lazovich, Darius Bunandar
  • Publication number: 20200284981
    Abstract: Described herein are photonic communication platforms that can overcome the memory bottleneck problem, thereby enabling scaling of memory capacity and bandwidth well beyond what is possible with conventional computing systems. Some embodiments provide photonic communication platforms that involve use of photonic modules. Each photonic module includes programmable photonic circuits for placing the module in optical communication with other modules based on the needs of a particular application. The architecture developed by the inventors relies on the use of common photomask sets (or at least one common photomask) to fabricate multiple photonic modules in a single wafer. Photonic modules in multiple wafers can be linked together into a communication platform using optical or electronic means.
    Type: Application
    Filed: March 5, 2020
    Publication date: September 10, 2020
    Applicant: Lightmatter, Inc.
    Inventors: Nicholas C. Harris, Carl Ramey, Michael Gould, Thomas Graham, Darius Bunandar, Ryan Braid, Mykhailo Tymchenko
  • Patent number: 10763974
    Abstract: Aspects relate to a photonic processing system, a photonic processor, and a method of performing matrix-vector multiplication. An optical encoder may encode an input vector into a first plurality of optical signals. A photonic processor may receive the first plurality of optical signals; perform a plurality of operations on the first plurality of optical signals, the plurality of operations implementing a matrix multiplication of the input vector by a matrix; and output a second plurality of optical signals representing an output vector. An optical receiver may detect the second plurality of optical signals and output an electrical digital representation of the output vector.
    Type: Grant
    Filed: May 14, 2019
    Date of Patent: September 1, 2020
    Assignee: Lightmatter, Inc.
    Inventors: Darius Bunandar, Nicholas C. Harris, Carl Ramey
  • Publication number: 20200272195
    Abstract: Systems and methods for performing matrix operations using a path-number balanced optical network are provided. The optical network is formed as an array including active optical components and passive optical components arranged at a substantially central location of the array. The optical network includes at least NM active optical components which are used to implement a first matrix of any size N×M by embedding the first matrix in a second matrix of a larger size. The optical network performs matrix-vector and matrix-matrix operations by propagating one or more pluralities of optical signals corresponding to an input vector through the optical network.
    Type: Application
    Filed: February 24, 2020
    Publication date: August 27, 2020
    Applicant: Lightmatter, Inc.
    Inventors: Darius Bunandar, Martin B.Z. Forsythe, Michael Gould, Tomo Lazovich
  • Publication number: 20200272794
    Abstract: Techniques for computing matrix operations for arbitrarily large matrices on a finite-sized hybrid analog-digital matrix processor are described. Techniques for gain adjustment in a finite-sized hybrid analog-digital matrix processor are described which enable the system to obtain higher energy efficiencies, greater physical density and improved numerical accuracy. In some embodiments, these techniques enable maximization of the predictive accuracy of a GEMM-based convolutional neural network using low-precision data representations.
    Type: Application
    Filed: February 25, 2020
    Publication date: August 27, 2020
    Applicant: Lightmatter, Inc.
    Inventors: Tyler J. Kenney, Martin B.Z. Forsythe, Tomo Lazovich, Darius Bunandar
  • Publication number: 20200272795
    Abstract: Techniques for computing matrix operations for arbitrarily large matrices on a finite-sized hybrid analog-digital matrix processor are described. Techniques for gain adjustment in a finite-sized hybrid analog-digital matrix processor are described which enable the system to obtain higher energy efficiencies, greater physical density and improved numerical accuracy. In some embodiments, these techniques enable maximization of the predictive accuracy of a GEMM-based convolutional neural network using low-precision data representations.
    Type: Application
    Filed: February 25, 2020
    Publication date: August 27, 2020
    Applicant: Lightmatter, Inc.
    Inventors: Tyler J. Kenney, Martin B.Z. Forsythe, Tomo Lazovich, Darius Bunandar
  • Patent number: 10740693
    Abstract: Methods and apparatus for training a matrix-based differentiable program using a photonics-based processor. The matrix-based differentiable program includes at least one matrix-valued variable associated with a matrix of values in a Euclidean vector space. The method comprises configuring components of the photonics-based processor to represent the matrix of values as an angular representation, processing, using the components of the photonics-based processor, training data to compute an error vector, determining in parallel, at least some gradients of parameters of the angular representation, wherein the determining is based on the error vector and a current input training vector, and updating the matrix of values by updating the angular representation based on the determined gradients.
    Type: Grant
    Filed: May 14, 2019
    Date of Patent: August 11, 2020
    Assignee: Lightmatter, Inc.
    Inventors: Tomo Lazovich, Darius Bunandar, Nicholas C. Harris, Martin Forsythe
  • Publication number: 20200225555
    Abstract: A nano-opto-electro-mechanical System (NOEMS) phase shifter is described. The NOEMS may include a multi-slot waveguide structure suspended in air. The multi-slot waveguide structure may include three or more waveguides separated from each other by slots. The width of the slots may be sufficiently small to support slot modes, where a substantial portion of the mode energy is within the slots. For example, the slots may have widths less than 200 nm or less than 100 nm. The multi-slot waveguide structure may be disposed in a trench formed though the upper cladding of a substrate. An undercut may be formed under the multi-slot waveguide structure to enable free motion of the structure. NOEMS phase modulators of the types described herein may be used in connection with photonic processing systems, telecom/datacom systems, analog systems, etc.
    Type: Application
    Filed: May 14, 2019
    Publication date: July 16, 2020
    Applicant: Lightmatter, Inc.
    Inventor: Michael Gould
  • Publication number: 20200228077
    Abstract: Low-noise optical differential receivers are described. Such differential receivers may include a differential amplifier having first and second inputs and first and second outputs, and four photodetectors. A first and a second of such photodetectors are coupled to the first input of the differential amplifier, and a third and a fourth of such photodetectors are coupled to the second input of the differential amplifier. The anode of the first photodetector and the cathode of the second photodetector are coupled to the first input of the differential amplifier. The cathode of the third photodetector and the anode of the fourth photodetector are coupled to the second input of the differential amplifier. The optical receiver may involve two stages of signal subtraction, which may significantly increase noise immunity.
    Type: Application
    Filed: May 14, 2019
    Publication date: July 16, 2020
    Applicant: Lightmatter, Inc.
    Inventors: Nicholas C. Harris, Michael Gould, Omer Ozgur Yildirim