Patents by Inventor Patrick Hayes

Patrick Hayes has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).

  • Publication number: 20210034924
    Abstract: Systems and methods for tuning hyperparameters of a model include receiving a tuning request for tuning hyperparameters, the tuning request includes a first and a second objective function for the machine learning model. The first and second objective functions may output metric values that do not improve uniformly. Systems and methods additionally include defining a joint tuning function that is based on a combination of the first and second objective functions; executing a tuning operation; identifying a Pareto efficient frontier curve defined by a plurality of distinct hyperparameter values; applying metric thresholds to the Pareto efficient frontier curve; demarcating the Pareto efficient frontier curve into at least a first infeasible section and a second feasible section; searching the second feasible section of the Pareto efficient frontier curve for one or more proposed hyperparameter values; and identifying at least a first set of proposed hyperparameter values based on the search.
    Type: Application
    Filed: July 30, 2020
    Publication date: February 4, 2021
    Inventors: Michael McCourt, Bolong Cheng, Taylor Jackle Spriggs, Halley Vance, Olivia Kim, Ben Hsu, Sarth Frey, Patrick Hayes, Scott Clark
  • Publication number: 20200378450
    Abstract: Systems, apparatus, and methods to control fluid associated with vehicle clutches are disclosed. A disclosed apparatus includes a drive unit assembly for a vehicle. The drive unit assembly includes a housing and a clutch in a cavity of the housing. Rotation of a drum of the clutch expels a fluid from the cavity. The apparatus also includes a vehicle controller configured to disengage the clutch via an actuator. Actuation of the actuator reduces a flow of the fluid into the cavity.
    Type: Application
    Filed: May 29, 2019
    Publication date: December 3, 2020
    Applicant: JTEKT AUTOMOTIVE NORTH AMERICA, INC.
    Inventors: Patrick DESING, Shun ONO, Evan SWINGER, Sean HAYES, Masaki MITA
  • Publication number: 20200362924
    Abstract: Piston apparatus for use with vehicle clutches are disclosed. A disclosed drive unit assembly for a vehicle includes a housing defining a first cavity and a second cavity fluidly coupled together. The drive unit assembly also includes a clutch positioned in the first cavity. Rotation of the clutch conveys a fluid from the first cavity to the second cavity. The drive unit assembly also includes a port extending from the second cavity to the first cavity to receive the fluid. The drive unit assembly also includes a piston positioned in the first cavity proximate to the port and configured to operate the clutch. Movement of the piston relative to the port controls a flow of the fluid through the port from the second cavity to the first cavity.
    Type: Application
    Filed: May 15, 2019
    Publication date: November 19, 2020
    Applicant: JTEKT AUTOMOTIVE NORTH AMERICA, INC.
    Inventors: Patrick DESING, Shun ONO, Evan SWINGER, Sean HAYES
  • Publication number: 20200327963
    Abstract: The disclosure enables latent space exploration of a dataset based on drug molecular-structure data and drug biological-treatment data for a set of drug compounds in order to determine optimal drug compounds for treating diseases. Regional interpolation, including a linear interpolation (LERP) operation and a non-linear interpolation operation such as a spherical linear interpolation (SLERP), along with quantitative structure-activity relationship (QSAR) models may be utilized to navigate through a latent space generated from a variational auto-encoder (VAE), in accordance with certain embodiments.
    Type: Application
    Filed: June 19, 2019
    Publication date: October 15, 2020
    Applicant: ACCENTURE GLOBAL SOLUTIONS LIMITED
    Inventors: Qurrat Ul Ain, Nicholas McCarthy, Jeremiah Hayes, Philip O'Kelly, Patrick Moreau
  • Publication number: 20200327412
    Abstract: A system and method for tuning hyperparameters and training a model includes implementing a hyperparameter tuning service that tunes hyperparameters of a model that includes receiving, via an API, a tuning request that includes: (i) a first part comprising tuning parameters for generating tuned hyperparameter values for hyperparameters of the model; and (ii) a second part comprising model training control parameters for monitoring and controlling a training of the model, wherein the model training control parameters include criteria for generating instructions for curtailing a training run of the model; monitoring the training run for training the model based on the second part of the tuning request, wherein the monitoring of the training run includes periodically collecting training run data; and computing an advanced training curtailment instruction based on the training run data that automatically curtails the training run prior to a predefined maximum training schedule of the training run.
    Type: Application
    Filed: April 15, 2020
    Publication date: October 15, 2020
    Inventors: Michael McCourt, Taylor Jackie Springs, Ben Hsu, Simon Howey, Halley Nicki Vance, James Blomo, Patrick Hayes, Scott Clark
  • Patent number: 10793757
    Abstract: Predominately bio-sourced polymer compositions that may be used as hot-melt adhesives are disclosed herein. The polymer compositions may contain a polymer that has the following structure: G1 and G2 are independently (CH2)x. Variable x is an integer ranging between 1 and 10. Variable y is an integer ranging between about 50 and about 500. Variable z is an integer ranging between about 100 and about 600. Variable n is an integer ranging between about 5 and about 10,000. X is H, a functionalized alkylene polymer block containing alcohol functional groups, or a mixture thereof. Y is H, an acyl group, a functionalized alkylene polymer containing carboxylic acid functional groups, or a mixture thereof.
    Type: Grant
    Filed: November 16, 2016
    Date of Patent: October 6, 2020
    Assignees: Henkel IP & Holding GmbH, Danimer Bioplastics, Inc.
    Inventors: Patrick Hayes, Daniel Carraway, Steven Wann, Rachelle Arnold, Joe B. Grubbs, III
  • Publication number: 20200302342
    Abstract: Systems and methods for tuning hyperparameters of a model includes: receiving a multi-criteria tuning work request for tuning hyperparameters of the model of the subscriber to the remote tuning service, wherein the multi-criteria tuning work request includes: a first objective function of the model to be optimized by the remote tuning service; a second objective function to be optimized by the remote tuning service, the second objective function being distinct from the first objective function; computing a joint tuning function based on a combination of the first objective function and the second objective function; executing a tuning operation of the hyperparameters for the model based on a tuning of the joint function; and identifying one or more proposed hyperparameter values based on one or more hyperparameter-based points along a convex Pareto optimal curve.
    Type: Application
    Filed: June 8, 2020
    Publication date: September 24, 2020
    Inventors: Bolong Cheng, Olivia Kim, Michael McCourt, Patrick Hayes, Scott Clark
  • Patent number: 10740695
    Abstract: Systems and methods for tuning hyperparameters of a model includes: receiving a multi-criteria tuning work request for tuning hyperparameters of the model of the subscriber to the remote tuning service, wherein the multi-criteria tuning work request includes: a first objective function of the model to be optimized by the remote tuning service; a second objective function to be optimized by the remote tuning service, the second objective function being distinct from the first objective function; computing a joint tuning function based on a combination of the first objective function and the second objective function; executing a tuning operation of the hyperparameters for the model based on a tuning of the joint function; and identifying one or more proposed hyperparameter values based on one or more hyperparameter-based points along a convex Pareto optimal curve.
    Type: Grant
    Filed: November 26, 2019
    Date of Patent: August 11, 2020
    Assignee: SigOpt, Inc.
    Inventors: Bolong Cheng, Olivia Kim, Michael McCourt, Patrick Hayes, Scott Clark
  • Publication number: 20200202254
    Abstract: A system and method includes receiving a tuning work request for tuning an external machine learning model; implementing a plurality of distinct queue worker machines that perform various tuning operations based on the tuning work data of the tuning work request; implementing a plurality of distinct tuning sources that generate values for each of the one or more hyperparameters of the tuning work request; selecting, by one or more queue worker machines of the plurality of distinct queue worker machines, one or more tuning sources of the plurality of distinct tuning sources for tuning the one or more hyperparameters; and using the selected one or more tuning sources to generate one or more suggestions for the one or more hyperparameters, the one or more suggestions comprising values for the one or more hyperparameters of the tuning work request.
    Type: Application
    Filed: February 20, 2020
    Publication date: June 25, 2020
    Inventors: Patrick Hayes, Michael McCourt, Alexandra Johnson, George Ke, Scott Clark
  • Patent number: 10691922
    Abstract: A system detecting counterfeit items based on machine learning and analysis of visual and textual data is disclosed. The system may comprise a data access interface to receive product data associated with a protected product from a user device. The product data may comprise multimodal data that describes the protected product. The system may also comprise a search term generator to generate search terms based on the received product data. The system may comprise a processor to identify one or more potential counterfeit items from the at least one web source using a crawling technique to obtain data associated with to similar products from the at least one web source, identifying at least one match for similar products, and using image processing and analysis to determine if the at least one match for similar products comprises at least one or more potential counterfeit items.
    Type: Grant
    Filed: May 17, 2018
    Date of Patent: June 23, 2020
    Assignee: ACCENTURE GLOBAL SOLUTIONS LIMITED
    Inventors: Julianne Madeleine Chaloux, Jeremiah Patrick Hayes, Mohit Aggarwal, Penelope Daphne Tsatsoulis
  • Publication number: 20200190434
    Abstract: The present disclosure relates generally to cleaning compositions and, more specifically, to cleaning compositions containing an etheramine that is suitable for removal of stains from soiled materials.
    Type: Application
    Filed: February 21, 2020
    Publication date: June 18, 2020
    Inventors: Stefano Scialla, Brian Joseph Loughnane, Karie Marie Henke, J. Frank Nash, JR., Michael Patrick Hayes, Bjoern Ludolph, Sophia Rosa Ebert, Christian Eidamhaus
  • Publication number: 20200193079
    Abstract: The present disclosure relates generally to cleaning compositions and, more specifically, to cleaning compositions containing an etheramine that is suitable for removal of stains from soiled materials.
    Type: Application
    Filed: February 20, 2020
    Publication date: June 18, 2020
    Inventors: Stefano SCIALLA, Brian Joseph LOUGHNANE, Karie Marie HENKE, Gayle Marie FRANKENBACH, J. Frank NASH, JR., Michael Patrick HAYES, Manuel G. VENEGAS, Bjoern LUDOLPH, Sophia Rosa EBERT, Christian EIDAMSHAUS, Jan Richard DAVIS, Neil Thomas FAIRWEATHER
  • Publication number: 20200151029
    Abstract: Systems and methods for implementing an application programming interface (API) that controls operations of a machine learning tuning service for tuning a machine learning model for improved accuracy and computational performance includes an API that is in control communication the tuning service that: executes a first API call function that includes an optimization work request that sets tuning parameters for tuning hyperparameters of a machine learning model; and initializes an operation of distinct tuning worker instances of the service that each execute distinct tuning tasks for tuning the hyperparameters; executes a second API call function that identifies raw values for the hyperparameters; and generates suggestions comprising proposed hyperparameter values selected from the plurality of raw values for each of the hyperparameters; and executes a third API call function that returns performance metrics relating to a real-world performance of the subscriber machine learning model executed with the propose
    Type: Application
    Filed: January 14, 2020
    Publication date: May 14, 2020
    Inventors: Alexandra Johnson, Patrick Hayes, Scott Clark
  • Patent number: 10621514
    Abstract: Systems and methods for tuning hyperparameters of a model includes: receiving at a remote tuning service a multi-criteria tuning work request for tuning hyperparameters of the model of a subscriber, wherein the multi-criteria tuning work request includes: a first objective function of the model to be optimized by the remote tuning service; a second objective function to be optimized by the remote tuning service, the second objective function being distinct from the first objective function; computing a first conditionally constrained joint function for the model based on subjecting the first objective function to the second objective function; a second conditionally constrained joint function for the model based on subjecting the second objective function to the first objective function of the model; executing a tuning operation of the hyperparameters for the model; and identifying proposed hyperparameter values based on one or more hyperparameter-based points along a non-convex Pareto optimal curve.
    Type: Grant
    Filed: November 26, 2019
    Date of Patent: April 14, 2020
    Assignee: SigOpt, Inc.
    Inventors: Bolong Cheng, Olivia Kim, Michael McCourt, Patrick Hayes, Scott Clark
  • Patent number: 10613159
    Abstract: A magnetic field measuring method using a magnetoelectric composite element as an oscillator, in which a time-dependent measurement magnetic field acts on the magnetostrictive phase of the composite element, and an electrical measurement voltage is tapped off across the piezoelectric phase of the composite element and is used to infer the measurement magnetic field. At least one dielectric phase is connected to the magnetostrictive phase of the composite element by a material bond. When an electrical voltage is applied, the dielectric phase exhibits a change in length, the magnitude of which depends in a non-linear manner on the magnitude of the voltage, and a temporally periodic electrical modulation voltage is applied to the dielectric phase.
    Type: Grant
    Filed: May 31, 2016
    Date of Patent: April 7, 2020
    Assignee: Christian-Albrechts-Universitaet zu Kiel
    Inventors: Patrick Hayes, Andre Piorra, Reinhard Knoechel, Eckhard Quandt
  • Patent number: 10607159
    Abstract: A system and method includes receiving a tuning work request for tuning an external machine learning model; implementing a plurality of distinct queue worker machines that perform various tuning operations based on the tuning work data of the tuning work request; implementing a plurality of distinct tuning sources that generate values for each of the one or more hyperparameters of the tuning work request; selecting, by one or more queue worker machines of the plurality of distinct queue worker machines, one or more tuning sources of the plurality of distinct tuning sources for tuning the one or more hyperparameters; and using the selected one or more tuning sources to generate one or more suggestions for the one or more hyperparameters, the one or more suggestions comprising values for the one or more hyperparameters of the tuning work request.
    Type: Grant
    Filed: January 9, 2019
    Date of Patent: March 31, 2020
    Assignee: SigOpt, Inc.
    Inventors: Patrick Hayes, Michael McCourt, Alexandra Johnson, George Ke, Scott Clark
  • Patent number: 10604049
    Abstract: A vehicle headrest includes a carriage with support rods, an outer headrest connected to the carriage, a vertical locking arrangement with a locking element having a locked state and a released state relative to a support rod locking interface. Release levers, accessible from respective sides, move essentially along a vehicle direction of travel. Release carriers, moveably mounted to the carriage, moves essentially along a vehicle inboard/outboard direction and moves the locking element into the released state. Each release linkage activates the movement of the release carrier. The headrest also includes a forward and rearward locking arrangement for movement of the outer headrest relative to the carriage with support rods with at least some forward and/or rearward movement component. The movement arrangement, for movement of the outer headrest relative to the carriage, does not interrupt the release linkage connection for activating the movement of the release carrier.
    Type: Grant
    Filed: February 3, 2017
    Date of Patent: March 31, 2020
    Assignee: Adient Luxembourg Holding S.à r.l.
    Inventors: John Gomez, James Biebel, Tyler Rusnak, David Hayes, Patrick Donnelly, Srinivasa N Sanku
  • Publication number: 20200097855
    Abstract: Systems and methods for tuning hyperparameters of a model includes: receiving a multi-criteria tuning work request for tuning hyperparameters of the model of the subscriber to the remote tuning service, wherein the multi-criteria tuning work request includes: a first objective function of the model to be optimized by the remote tuning service; a second objective function to be optimized by the remote tuning service, the second objective function being distinct from the first objective function; computing a joint tuning function based on a combination of the first objective function and the second objective function; executing a tuning operation of the hyperparameters for the model based on a tuning of the joint function; and identifying one or more proposed hyperparameter values based on one or more hyperparameter-based points along a convex Pareto optimal curve.
    Type: Application
    Filed: November 26, 2019
    Publication date: March 26, 2020
    Inventors: Bolong Cheng, Olivia Kim, Michael McCourt, Patrick Hayes, Scott Clark
  • Publication number: 20200097856
    Abstract: Systems and methods for tuning hyperparameters of a model includes: receiving at a remote tuning service a multi-criteria tuning work request for tuning hyperparameters of the model of a subscriber, wherein the multi-criteria tuning work request includes: a first objective function of the model to be optimized by the remote tuning service; a second objective function to be optimized by the remote tuning service, the second objective function being distinct from the first objective function; computing a first conditionally constrained joint function for the model based on subjecting the first objective function to the second objective function; a second conditionally constrained joint function for the model based on subjecting the second objective function to the first objective function of the model; executing a tuning operation of the hyperparameters for the model; and identifying proposed hyperparameter values based on one or more hyperparameter-based points along a non-convex Pareto optimal curve.
    Type: Application
    Filed: November 26, 2019
    Publication date: March 26, 2020
    Inventors: Bolong Cheng, Olivia Kim, Michael McCourt, Patrick Hayes, Scott Clark
  • Publication number: 20200065705
    Abstract: Systems and methods for tuning hyperparameters of a model includes: receiving at a remote tuning service a multi-criteria tuning work request for tuning hyperparameters of the model of a subscriber, wherein the multi-criteria tuning work request includes: a first objective function of the model to be optimized by the remote tuning service; a second objective function to be optimized by the remote tuning service, the second objective function being distinct from the first objective function; computing a first conditionally constrained joint function for the model based on subjecting the first objective function to the second objective function; a second conditionally constrained joint function for the model based on subjecting the second objective function to the first objective function of the model; executing a tuning operation of the hyperparameters for the model; and identifying proposed hyperparameter values based on one or more hyperparameter-based points along a non-convex Pareto optimal curve.
    Type: Application
    Filed: July 31, 2019
    Publication date: February 27, 2020
    Inventors: Bolong Cheng, Olivia Kim, Michael McCourt, Patrick Hayes, Scott Clark