Patents by Inventor Vedavyas Panneershelvam
Vedavyas Panneershelvam 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: 20240111260Abstract: Methods and systems are disclosed for determining a plan to optimize key performance indicators (KPIs) of an industrial process. Such a plan is determined based on generating a query for information associated with the KPIs and based on receiving user-provided object information corresponding to the KPIs. The method includes receiving, at a user interface, one or more KPIs associated with an industrial process. The method includes generating, based on the one or more KPIs, at least one query for information associated with the KPI. The method includes receiving, at the user interface, a response to the at least one query. The method includes determining, by an artificial intelligence agent, a plan for optimizing the KPI.Type: ApplicationFiled: December 13, 2023Publication date: April 4, 2024Applicant: Phaidra Inc.Inventors: Jim Jingyue Gao, Vedavyas Panneershelvam, Katherine Elizabeth Hoffman, Paritosh Mohan, Christopher R. Vause
-
Patent number: 11868098Abstract: Methods and systems are disclosed for determining a plan to optimize key performance indicators (KPIs) of an industrial process. Such a plan is determined based on generating a query for information associated with the KPIs and based on receiving user-provided object information corresponding to the KPIs. The method includes receiving, at a user interface, one or more KPIs associated with an industrial process. The method includes generating, based on the one or more KPIs, at least one query for information associated with the KPI. The method includes receiving, at the user interface, a response to the at least one query. The method includes determining, by an artificial intelligence agent, a plan for optimizing the KPI.Type: GrantFiled: November 12, 2021Date of Patent: January 9, 2024Assignee: Phaidra, Inc.Inventors: Jim Jingyue Gao, Vedavyas Panneershelvam, Katherine Elizabeth Hoffman, Paritosh Mohan, Christopher R. Vause
-
Patent number: 11809164Abstract: 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.Type: GrantFiled: February 25, 2022Date of Patent: November 7, 2023Assignee: Google LLCInventors: 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
-
Publication number: 20230152756Abstract: Methods and systems are disclosed for determining a plan to optimize key performance indicators (KPIs) of an industrial process. Such a plan is determined based on generating a query for information associated with the KPIs and based on receiving user-provided object information corresponding to the KPIs. The method includes receiving, at a user interface, one or more KPIs associated with an industrial process. The method includes generating, based on the one or more KPIs, at least one query for information associated with the KPI. The method includes receiving, at the user interface, a response to the at least one query. The method includes determining, by an artificial intelligence agent, a plan for optimizing the KPI.Type: ApplicationFiled: November 12, 2021Publication date: May 18, 2023Inventors: Jim Jingyue Gao, Vedavyas Panneershelvam, Katherine Elizabeth Hoffman, Paritosh Mohan, Christopher R. Vause
-
Patent number: 11507827Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for distributed training of reinforcement learning systems. One of the methods includes receiving, by a learner, current values of the parameters of the Q network from a parameter server, wherein each learner maintains a respective learner Q network replica and a respective target Q network replica; updating, by the learner, the parameters of the learner Q network replica maintained by the learner using the current values; selecting, by the learner, an experience tuple from a respective replay memory; computing, by the learner, a gradient from the experience tuple using the learner Q network replica maintained by the learner and the target Q network replica maintained by the learner; and providing, by the learner, the computed gradient to the parameter server.Type: GrantFiled: October 14, 2019Date of Patent: November 22, 2022Assignee: DeepMind Technologies LimitedInventors: Praveen Deepak Srinivasan, Rory Fearon, Cagdas Alcicek, Arun Sarath Nair, Samuel Blackwell, Vedavyas Panneershelvam, Alessandro De Maria, Volodymyr Mnih, Koray Kavukcuoglu, David Silver, Mustafa Suleyman
-
Publication number: 20220179401Abstract: 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.Type: ApplicationFiled: February 25, 2022Publication date: June 9, 2022Inventors: 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
-
Publication number: 20200117992Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for distributed training of reinforcement learning systems. One of the methods includes receiving, by a learner, current values of the parameters of the Q network from a parameter server, wherein each learner maintains a respective learner Q network replica and a respective target Q network replica; updating, by the learner, the parameters of the learner Q network replica maintained by the learner using the current values; selecting, by the learner, an experience tuple from a respective replay memory; computing, by the learner, a gradient from the experience tuple using the learner Q network replica maintained by the learner and the target Q network replica maintained by the learner; and providing, by the learner, the computed gradient to the parameter server.Type: ApplicationFiled: October 14, 2019Publication date: April 16, 2020Inventors: Praveen Deepak Srinivasan, Rory Fearon, Cagdas Alcicek, Arun Sarath Nair, Samuel Blackwell, Vedavyas Panneershelvam, Alessandro De Maria, Volodymyr Mnih, Koray Kavukcuoglu, David Silver, Mustafa Suleyman
-
Publication number: 20200050178Abstract: 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.Type: ApplicationFiled: October 16, 2019Publication date: February 13, 2020Inventors: 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
-
Patent number: 10445641Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for distributed training of reinforcement learning systems. One of the methods includes receiving, by a learner, current values of the parameters of the Q network from a parameter server, wherein each learner maintains a respective learner Q network replica and a respective target Q network replica; updating, by the learner, the parameters of the learner Q network replica maintained by the learner using the current values; selecting, by the learner, an experience tuple from a respective replay memory; computing, by the learner, a gradient from the experience tuple using the learner Q network replica maintained by the learner and the target Q network replica maintained by the learner; and providing, by the learner, the computed gradient to the parameter server.Type: GrantFiled: February 4, 2016Date of Patent: October 15, 2019Assignee: Deepmind Technologies LimitedInventors: Praveen Deepak Srinivasan, Rory Fearon, Cagdas Alcicek, Arun Sarath Nair, Samuel Blackwell, Vedavyas Panneershelvam, Alessandro De Maria, Volodymyr Mnih, Koray Kavukcuoglu, David Silver, Mustafa Suleyman
-
Publication number: 20160232445Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for distributed training of reinforcement learning systems. One of the methods includes receiving, by a learner, current values of the parameters of the Q network from a parameter server, wherein each learner maintains a respective learner Q network replica and a respective target Q network replica; updating, by the learner, the parameters of the learner Q network replica maintained by the learner using the current values; selecting, by the learner, an experience tuple from a respective replay memory; computing, by the learner, a gradient from the experience tuple using the learner Q network replica maintained by the learner and the target Q network replica maintained by the learner; and providing, by the learner, the computed gradient to the parameter server.Type: ApplicationFiled: February 4, 2016Publication date: August 11, 2016Inventors: Praveen Deepak Srinivasan, Rory Fearon, Cagdas Alcicek, Arun Sarath Nair, Samuel Blackwell, Vedavyas Panneershelvam, Alessandro De Maria, Volodymyr Mnih, Koray Kavukcuoglu, David Silver, Mustafa Suleyman