公开(公告)号：US20200050178A1

公开(公告)日：2020-02-13

申请号：US16654978

申请日：2019-10-16

Applicant: Google LLC

Inventor： Jim Gao ,  Christopher Gamble ,  Amanda Gasparik ,  Vedavyas Panneershelvam ,  David Barker ,  Dustin Reishus ,  Abigail Ward ,  Jerry Luo ,  Brian Kim ,  Mark Schwabacher ,  Stephen Webster ,  Timothy Jason Kieper ,  Daniel Fuenffinger ,  Zakerey Bennett

IPC: G05B19/4155 ,  G06N20/00

Abstract: Methods, systems, apparatus and computer program products for implementing machine learning within control systems are disclosed. An industrial facility setting slate can be received from a machine learning system and a determination can be made as to whether to adopt the settings in the industrial facility setting slate. The machine learning model can be a neural network, e.g., a deep neural network, that has been trained, e.g., using reinforcement learning to predict a data setting slate that is predicted to optimize an efficiency of a data center.

公开(公告)号：US11809164B2

公开(公告)日：2023-11-07

申请号：US17681652

申请日：2022-02-25

Applicant: Google LLC

Inventor： Jim Gao ,  Christopher Gamble ,  Amanda Gasparik ,  Vedavyas Panneershelvam ,  David Barker ,  Dustin Reishus ,  Abigail Ward ,  Jerry Luo ,  Brian Kim ,  Mark Schwabacher ,  Stephen Webster ,  Timothy Jason Kieper ,  Daniel Fuenffinger ,  Zakerey Bennett

IPC: H02J3/46 ,  G06Q10/04 ,  G06Q10/10 ,  G05B19/4155 ,  G06N20/00

CPC classification number: G05B19/4155 ,  G06N20/00 ,  G05B2219/40499

Abstract: Methods, systems, apparatus and computer program products for implementing machine learning within control systems are disclosed. An industrial facility setting slate can be received from a machine learning system and a determination can be made as to whether to adopt the settings in the industrial facility setting slate. The machine learning model can be a neural network, e.g., a deep neural network, that has been trained, e.g., using reinforcement learning to predict a data setting slate that is predicted to optimize an efficiency of a data center.

公开(公告)号：US20220179401A1

公开(公告)日：2022-06-09

申请号：US17681652

申请日：2022-02-25

Applicant: Google LLC

Inventor： Jim Gao ,  Christopher Gamble ,  Amanda Gasparik ,  Vedavyas Panneershelvam ,  David Barker ,  Dustin Reishus ,  Abigail Ward ,  Jerry Luo ,  Brian Kim ,  Mark Schwabacher ,  Stephen Webster ,  Timothy Jason Kieper ,  Daniel Fuenffinger ,  Zakerey Bennett

IPC: G05B19/4155 ,  G06N20/00

Abstract: Methods, systems, apparatus and computer program products for implementing machine learning within control systems are disclosed. An industrial facility setting slate can be received from a machine learning system and a determination can be made as to whether to adopt the settings in the industrial facility setting slate. The machine learning model can be a neural network, e.g., a deep neural network, that has been trained, e.g., using reinforcement learning to predict a data setting slate that is predicted to optimize an efficiency of a data center.

公开(公告)号：US20210368604A1

公开(公告)日：2021-11-25

申请号：US17394516

申请日：2021-08-05

Applicant: Google LLC

Inventor： Thomas Degris ,  Benjamin Hal Murdoch ,  Norman Casagrande ,  Peeyush Agarwal ,  Christopher Gamble ,  Christopher Sigurd Fougner

IPC: H05B47/105 ,  G09G3/36

Abstract: A computer-implemented method for adaptive display brightness adjustment, the method comprising: obtaining current state data characterizing a current state of a device having a display with an adjustable brightness; providing the current state data as input to a brightness prediction machine learning model, wherein the model is configured to process the current state data in accordance with current values of a set of model parameters to generate as output a proposed display brightness for the display of the device; setting the brightness of the display to a brightness that is lower than the proposed display brightness in accordance with an exploration policy; determining whether a user of the device manually adjusts the display brightness; and in response to determining that the user did not manually adjust the display brightness, using the lower brightness as a target output for adjusting the current values of the set of model parameters.

公开(公告)号：US11096259B2

公开(公告)日：2021-08-17

申请号：US16754639

申请日：2017-12-15

Applicant: Google LLC

Inventor： Thomas Degris ,  Benjamin Hal Murdoch ,  Norman Casagrande ,  Peeyush Agarwal ,  Christopher Gamble ,  Christopher Sigurd Fougner

IPC: H05B47/105 ,  G09G3/36

Abstract: A computer-implemented method for adaptive display brightness adjustment, the method comprising: obtaining current state data characterizing a current state of a device having a display with an adjustable brightness; providing the current state data as input to a brightness prediction machine learning model, wherein the model is configured to process the current state data in accordance with current values of a set of model parameters to generate as output a proposed display brightness for the display of the device; setting the brightness of the display to a brightness that is lower than the proposed display brightness in accordance with an exploration policy; determining whether a user of the device manually adjusts the display brightness; and in response to determining that the user did not manually adjust the display brightness, using the lower brightness as a target output for adjusting the current values of the set of model parameters.

公开(公告)号：US11419197B2

公开(公告)日：2022-08-16

申请号：US17394516

申请日：2021-08-05

Applicant: Google LLC

Inventor： Thomas Degris ,  Benjamin Hal Murdoch ,  Norman Casagrande ,  Peeyush Agarwal ,  Christopher Gamble ,  Christopher Sigurd Fougner

IPC: H05B47/105 ,  G09G3/36

Abstract: A computer-implemented method for adaptive display brightness adjustment, the method comprising: obtaining current state data characterizing a current state of a device having a display with an adjustable brightness; providing the current state data as input to a brightness prediction machine learning model, wherein the model is configured to process the current state data in accordance with current values of a set of model parameters to generate as output a proposed display brightness for the display of the device; setting the brightness of the display to a brightness that is lower than the proposed display brightness in accordance with an exploration policy; determining whether a user of the device manually adjusts the display brightness; and in response to determining that the user did not manually adjust the display brightness, using the lower brightness as a target output for adjusting the current values of the set of model parameters.

公开(公告)号：US20200314985A1

公开(公告)日：2020-10-01

申请号：US16754639

申请日：2017-12-15

Applicant: Google LLC

Inventor： Thomas Degris ,  Benjamin Hal Murdoch ,  Norman Casagrande ,  Peeyush Agarwal ,  Christopher Gamble ,  Christopher Sigurd Fougner

IPC: H05B47/105 ,  G09G3/36

Abstract: A computer-implemented method for adaptive display brightness adjustment, the method comprising: obtaining current state data characterizing a current state of a device having a display with an adjustable brightness; providing the current state data as input to a brightness prediction machine learning model, wherein the model is configured to process the current state data in accordance with current values of a set of model parameters to generate as output a proposed display brightness for the display of the device; setting the brightness of the display to a brightness that is lower than the proposed display brightness in accordance with an exploration policy; determining whether a user of the device manually adjusts the display brightness; and in response to determining that the user did not manually adjust the display brightness, using the lower brightness as a target output for adjusting the current values of the set of model parameters.