Patrick Joseph Hayes

US Patent:

8254352, Aug 28, 2012

Filed:

Jun 28, 2007

Appl. No.:

11/823737

Inventors:

Eric Negron - San Francisco CA, US
Patrick H. Hayes - Mission Viejo CA, US

Assignee:

Universal Electronics Inc. - Cypress CA

International Classification:

H04W 4/00

US Classification:

370338, 709222

Abstract:

A controlling device is used to configure an appliance for wireless network communications through use of a setup wizard installed on a computing device. The setup wizard is used to obtain from a user information required to perform communications on a wireless network via a wireless network router and a digital representation of the information obtained from the user through use of the setup wizard is provided to the controlling device. The controlling device is then used to transfer the digital representation of the information to the appliance whereupon the appliance will use the digital representation of the information to configure itself for wireless network communications.

US Patent:

8385304, Feb 26, 2013

Filed:

Apr 5, 2012

Appl. No.:

13/440607

Inventors:

Eric Negron - San Francisco CA, US
Patrick H. Hayes - Mission Viejo CA, US

Assignee:

Universal Electronics Inc. - Santa Ana CA

International Classification:

H04W 4/00

US Classification:

370338, 709222

Abstract:

A controlling device is used to configure an appliance for wireless network communications through use of a setup wizard installed on a computing device. The setup wizard is used to obtain from a user information required to perform communications on a wireless network via a wireless network router and a digital representation of the information obtained from the user through use of the setup wizard is provided to the controlling device. The controlling device is then used to transfer the digital representation of the information to the appliance whereupon the appliance will use the digital representation of the information to configure itself for wireless network communications.

US Patent:

20220188677, Jun 16, 2022

Filed:

Mar 4, 2022

Appl. No.:

17/687362

Inventors:

- Santa Clara CA, US
Michael McCourt - San Francisco CA, US
Patrick Hayes - San Francisco CA, US
Scott Clark - San Francisco CA, US

International Classification:

G06N 7/00
G06N 20/00

Abstract:

Disclosed examples include after a first tuning of hyperparameters in a hyperparameter space, selecting first hyperparameter values for respective ones of the hyperparameters; generating a polygonal shaped failure region in the hyperparameter space based on the first hyperparameter values; setting the first hyperparameter values to failure before a second tuning of the hyperparameters; and selecting second hyperparameter values for the respective ones of the hyperparameters in a second tuning region after the second tuning of the hyperparameters in the second tuning region, the second tuning region separate from the polygonal shaped failure region.

US Patent:

20210142224, May 13, 2021

Filed:

Oct 15, 2020

Appl. No.:

17/071929

Inventors:

- San Francisco CA, US
Ben Hsu - San Francisco CA, US
Patrick Hayes - San Francisco CA, US
Scott Clark - San Francisco CA, US

International Classification:

G06N 20/20
G06K 9/62

Abstract:

Systems and methods for an accelerated tuning of hyperparameters of a model supported with prior learnings data include assessing subject models associated with a plurality of distinct sources of transfer tuning data, wherein the assessing includes implementing of: [1] a model relatedness assessment for each of a plurality of distinct pairwise subject models, and [2] a model coherence assessment for each of the plurality of distinct pairwise subject models; constructing a plurality of distinct prior mixture models based on the relatedness metric value and the coherence metric value for each of the plurality of distinct pairwise subject models, identifying sources of transfer tuning data based on identifying a distinct prior mixture model having a satisfactory model evidence fraction; and accelerating a tuning of hyperparameters of the target model based on transfer tuning data associated with the distinct prior mixture model having the satisfactory model evidence fraction.

US Patent:

20210034924, Feb 4, 2021

Filed:

Jul 30, 2020

Appl. No.:

16/943643

Inventors:

- San Francisco CA, US
Bolong Cheng - San Francisco CA, US
Taylor Jackle Spriggs - San Francisco CA, US
Halley Vance - San Francisco CA, US
Olivia Kim - San Francisco CA, US
Ben Hsu - San Francisco CA, US
Sarth Frey - San Francisco CA, US
Patrick Hayes - San Francisco CA, US
Scott Clark - San Francisco CA, US

International Classification:

G06K 9/62
G06N 20/20
G06F 9/54

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.

US Patent:

20200327412, Oct 15, 2020

Filed:

Apr 15, 2020

Appl. No.:

16/849422

Inventors:

- San Francisco CA, US
Taylor Jackie Springs - San Francisco CA, US
Ben Hsu - San Francisco CA, US
Simon Howey - San Francisco CA, US
Halley Nicki Vance - San Francisco CA, US
James Blomo - San Francisco CA, US
Patrick Hayes - San Francisco CA, US
Scott Clark - San Francisco CA, US

International Classification:

G06N 3/08

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.

US Patent:

20200302342, Sep 24, 2020

Filed:

Jun 8, 2020

Appl. No.:

16/895099

Inventors:

- San Francisco CA, US
Olivia Kim - San Francisco CA, US
Michael McCourt - San Francisco CA, US
Patrick Hayes - San Francisco CA, US
Scott Clark - San Francisco CA, US

International Classification:

G06N 20/00
G06F 17/10

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.

US Patent:

20200097855, Mar 26, 2020

Filed:

Nov 26, 2019

Appl. No.:

16/696355

Inventors:

- San Francisco CA, US
Olivia Kim - San Francisco CA, US
Michael McCourt - San Francisco CA, US
Patrick Hayes - San Francisco CA, US
Scott Clark - San Francisco CA, US

International Classification:

G06N 20/00

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.