Patents by Inventor Robert Dunning
Robert Dunning 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: 20240127060Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training an action selection neural network used to select actions to be performed by an agent interacting with an environment. In one aspect, a system comprises a plurality of actor computing units and a plurality of learner computing units. The actor computing units generate experience tuple trajectories that are used by the learner computing units to update learner action selection neural network parameters using a reinforcement learning technique. The reinforcement learning technique may be an off-policy actor critic reinforcement learning technique.Type: ApplicationFiled: October 16, 2023Publication date: April 18, 2024Inventors: Hubert Josef Soyer, Lasse Espeholt, Karen Simonyan, Yotam Doron, Vlad Firoiu, Volodymyr Mnih, Koray Kavukcuoglu, Remi Munos, Thomas Ward, Timothy James Alexander Harley, Iain Robert Dunning
-
Patent number: 11868894Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training an action selection neural network used to select actions to be performed by an agent interacting with an environment. In one aspect, a system comprises a plurality of actor computing units and a plurality of learner computing units. The actor computing units generate experience tuple trajectories that are used by the learner computing units to update learner action selection neural network parameters using a reinforcement learning technique. The reinforcement learning technique may be an off-policy actor critic reinforcement learning technique.Type: GrantFiled: January 4, 2023Date of Patent: January 9, 2024Assignee: DeepMind Technologies LimitedInventors: Hubert Josef Soyer, Lasse Espeholt, Karen Simonyan, Yotam Doron, Vlad Firoiu, Volodymyr Mnih, Koray Kavukcuoglu, Remi Munos, Thomas Ward, Timothy James Alexander Harley, Iain Robert Dunning
-
Patent number: 11842261Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for reinforcement learning. One of the methods includes selecting an action to be performed by the agent using both a slow updating recurrent neural network and a fast updating recurrent neural network that receives a fast updating input that includes the hidden state of the slow updating recurrent neural network.Type: GrantFiled: December 14, 2020Date of Patent: December 12, 2023Assignee: DeepMind Technologies LimitedInventors: Iain Robert Dunning, Wojciech Czarnecki, Maxwell Elliot Jaderberg
-
Patent number: 11783235Abstract: A machine learning system that includes one or more machine learning models implemented in one or more hardware processors, a first-level feature creation module, and a combination module provides an output based on one or more channel inputs. Each of the one or more machine learning models receives the channel inputs and additional feature inputs based on the channel inputs to produce the output. The first-level feature creation module receives the channel inputs, performs a feature creation operation, creates the additional feature inputs, and provides the additional feature inputs to at least one of the machine learning models. The first-level feature creation operation performs a calculation on one or more aspects of the channel inputs, and the combination module receives the one or more machine learning model outputs and produce a machine learning channel output.Type: GrantFiled: December 16, 2019Date of Patent: October 10, 2023Assignee: Hamilton Sundstrand CorporationInventors: Kirk A. Lillestolen, Kanwalpreet Reen, Richard A. Poisson, Joshua Robert Dunning
-
Publication number: 20230153617Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training an action selection neural network used to select actions to be performed by an agent interacting with an environment. In one aspect, a system comprises a plurality of actor computing units and a plurality of learner computing units. The actor computing units generate experience tuple trajectories that are used by the learner computing units to update learner action selection neural network parameters using a reinforcement learning technique. The reinforcement learning technique may be an off-policy actor critic reinforcement learning technique.Type: ApplicationFiled: January 4, 2023Publication date: May 18, 2023Inventors: Hubert Josef Soyer, Lasse Espeholt, Karen Simonyan, Yotam Doron, Vlad Firoiu, Volodymyr Mnih, Koray Kavukcuoglu, Remi Munos, Thomas Ward, Timothy James Alexander Harley, Iain Robert Dunning
-
Patent number: 11593646Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training an action selection neural network used to select actions to be performed by an agent interacting with an environment. In one aspect, a system comprises a plurality of actor computing units and a plurality of learner computing units. The actor computing units generate experience tuple trajectories that are used by the learner computing units to update learner action selection neural network parameters using a reinforcement learning technique. The reinforcement learning technique may be an off-policy actor critic reinforcement learning technique.Type: GrantFiled: February 5, 2019Date of Patent: February 28, 2023Assignee: DeepMind Technologies LimitedInventors: Hubert Josef Soyer, Lasse Espeholt, Karen Simonyan, Yotam Doron, Vlad Firoiu, Volodymyr Mnih, Koray Kavukcuoglu, Remi Munos, Thomas Ward, Timothy James Alexander Harley, Iain Robert Dunning
-
Patent number: 11429069Abstract: A machine learning system that includes three machine learning models implemented in a hardware processor, a first-level feature creation module, and a combination module provides an output based on one or more channel inputs. Each of the three machine learning models receives the channel inputs and additional feature inputs based on the channel inputs to produce the output. The first-level feature creation module is implemented in hardware and receives the channel inputs, performs a feature creation operation, creates the additional feature inputs, and provides the additional feature inputs to at least one of the machine learning models. The first-level feature creation operation performs a calculation on one or more aspects of the channel inputs, and the combination module receives the one or more machine learning model outputs and produce a machine learning channel output.Type: GrantFiled: December 16, 2019Date of Patent: August 30, 2022Assignee: Hamilton Sundstrand CorporationInventors: Kirk A. Lillestolen, Kanwalpreet Reen, Richard A. Poisson, Joshua Robert Dunning
-
Publication number: 20210182737Abstract: A machine learning system that includes one or more machine learning models implemented in one or more hardware processors, a first-level feature creation module, and a combination module provides an output based on one or more channel inputs. Each of the one or more machine learning models receives the channel inputs and additional feature inputs based on the channel inputs to produce the output. The first-level feature creation module receives the channel inputs, performs a feature creation operation, creates the additional feature inputs, and provides the additional feature inputs to at least one of the machine learning models. The first-level feature creation operation performs a calculation on one or more aspects of the channel inputs, and the combination module receives the one or more machine learning model outputs and produce a machine learning channel output.Type: ApplicationFiled: December 16, 2019Publication date: June 17, 2021Inventors: Kirk A. Lillestolen, Kanwalpreet Reen, Richard A. Poisson, Joshua Robert Dunning
-
Publication number: 20210181694Abstract: A machine learning system that includes three machine learning models implemented in a hardware processor, a first-level feature creation module, and a combination module provides an output based on one or more channel inputs. Each of the three machine learning models receives the channel inputs and additional feature inputs based on the channel inputs to produce the output. The first-level feature creation module is implemented in hardware and receives the channel inputs, performs a feature creation operation, creates the additional feature inputs, and provides the additional feature inputs to at least one of the machine learning models. The first-level feature creation operation performs a calculation on one or more aspects of the channel inputs, and the combination module receives the one or more machine learning model outputs and produce a machine learning channel output.Type: ApplicationFiled: December 16, 2019Publication date: June 17, 2021Inventors: Kirk A. Lillestolen, Kanwalpreet Reen, Richard A. Poisson, Joshua Robert Dunning
-
Publication number: 20210097373Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for reinforcement learning. One of the methods includes selecting an action to be performed by the agent using both a slow updating recurrent neural network and a fast updating recurrent neural network that receives a fast updating input that includes the hidden state of the slow updating recurrent neural network.Type: ApplicationFiled: December 14, 2020Publication date: April 1, 2021Inventors: Iain Robert Dunning, Wojciech Czarnecki, Maxwell Elliot Jaderberg
-
Publication number: 20210034970Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training an action selection neural network used to select actions to be performed by an agent interacting with an environment. In one aspect, a system comprises a plurality of actor computing units and a plurality of learner computing units. The actor computing units generate experience tuple trajectories that are used by the learner computing units to update learner action selection neural network parameters using a reinforcement learning technique. The reinforcement learning technique may be an off-policy actor critic reinforcement learning technique.Type: ApplicationFiled: February 5, 2019Publication date: February 4, 2021Inventors: Hubert Josef Soyer, Lasse Espeholt, Karen Simonyan, Yotam Doron, Vlad Firoiu, Volodymyr Mnih, Koray Kavukcuoglu, Remi Munos, Thomas Ward, Timothy James Alexander Harley, Iain Robert Dunning
-
Patent number: 10872293Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for reinforcement learning. One of the methods includes selecting an action to be performed by the agent using both a slow updating recurrent neural network and a fast updating recurrent neural network that receives a fast updating input that includes the hidden state of the slow updating recurrent neural network.Type: GrantFiled: May 29, 2019Date of Patent: December 22, 2020Assignee: DeepMind Technologies LimitedInventors: Iain Robert Dunning, Wojciech Czarnecki, Maxwell Elliot Jaderberg
-
Publication number: 20190370637Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for reinforcement learning. One of the methods includes selecting an action to be performed by the agent using both a slow updating recurrent neural network and a fast updating recurrent neural network that receives a fast updating input that includes the hidden state of the slow updating recurrent neural network.Type: ApplicationFiled: May 29, 2019Publication date: December 5, 2019Inventors: Iain Robert Dunning, Wojciech Czarnecki, Maxwell Elliot Jaderberg
-
Patent number: 8344826Abstract: A phased-array antenna filter and diplexer for a super economical broadcast system are provided. The filter and diplexer includes a signal divider tee diplexer, a receive filter and a transmit filter. The diplexer includes a tee branch point, an antenna port, a transmit port and a receive port. The receive filter includes a flat, multi-pole bandpass filter, an input port and an output port, where the input port is coupled to the diplexer receive port to define a receive signal path, from the tee branch point to the receive input port, that has a length of approximately one quarter receive wavelength. The transmit filter includes a folded, multi-pole bandpass filter, an input port and an output port, where the output port is coupled to the diplexer transmit port to define a transmit signal path, from the tee branch point to the transmit output port, that has a length of approximately one quarter transmit wavelength.Type: GrantFiled: April 21, 2009Date of Patent: January 1, 2013Assignee: SPX CorporationInventors: Chris Rossiter, Robert Dunning, Torbjorn Johnson
-
Patent number: 8063723Abstract: A filter includes a cross-coupling link which includes a crossbar, a first vertical support attached to one end of the crossbar, a second vertical support attached to another end of the crossbar, a first coupling arm attached to the first vertical support, a second coupling arm attached to the second vertical support, a first adjustable support attached to the first coupling arm at one end and grounded at another end, and a second adjustable support attached to the second coupling arm at one end and grounded at another end.Type: GrantFiled: July 1, 2009Date of Patent: November 22, 2011Assignee: SPX CorporationInventors: Christopher Rossiter, Robert Dunning
-
Publication number: 20110001583Abstract: A filter includes a cross-coupling link which includes a crossbar, a first vertical support attached to one end of the crossbar, a second vertical support attached to another end of the crossbar, a first coupling arm attached to the first vertical support, a second coupling arm attached to the second vertical support, a first adjustable support attached to the first coupling arm at one end and grounded at another end, and a second adjustable support attached to the second coupling arm at one end and grounded at another end.Type: ApplicationFiled: July 1, 2009Publication date: January 6, 2011Applicant: SPX CorporationInventors: Christopher Rossiter, Robert Dunning
-
Publication number: 20090284325Abstract: A phased-array antenna filter and diplexer for a super economical broadcast system are provided. The filter and diplexer includes a signal divider tee diplexer, a receive filter and a transmit filter. The diplexer includes a tee branch point, an antenna port, a transmit port and a receive port. The receive filter includes a flat, multi-pole bandpass filter, an input port and an output port, where the input port is coupled to the diplexer receive port to define a receive signal path, from the tee branch point to the receive input port, that has a length of approximately one quarter receive wavelength. The transmit filter includes a folded, multi-pole bandpass filter, an input port and an output port, where the output port is coupled to the diplexer transmit port to define a transmit signal path, from the tee branch point to the transmit output port, that has a length of approximately one quarter transmit wavelength.Type: ApplicationFiled: April 21, 2009Publication date: November 19, 2009Applicant: SPX CorporationInventors: Chris Rossiter, Torbjorn Johnson, Robert Dunning
-
Patent number: 7559945Abstract: A multi-spectra photon therapy device and method of use for providing treatment to a subject in need thereof is described. A multi-spectra photon therapy device comprising an array of LEDs having at least two sets of LEDs configured according to a predetermined pattern, with a first set of LEDs emitting light in the about red wavelength and at least a second set of LEDs emitting light in the about infrared wavelength; a frequency generator for modulating a signal to the LED array; and a controller for selecting the frequency applied to the signal and the duration during which the signal is modulated at the selected frequency; a protocol database including a plurality of predetermined sequences of frequencies and durations of time specific to treat or ameliorate predetermined diseases or conditions.Type: GrantFiled: January 13, 2006Date of Patent: July 14, 2009Assignee: Clarimedix Inc.Inventors: Harold Richard Breden, Richard Samuel Murdoch, John Robert Dunning, Thomas M. Lopez
-
Patent number: 6697589Abstract: A fuser latch system suitable for a customer replaceable fuser unit. Front holders include datum receivers on a base machine frame and datums on the fuser frame. Rear latches include retainers connected to the base machine frame, and axially translatable and rotatable shafts connected to the fuser frame. An end of the shaft is received in a retainer upon axial translation of the shaft, and locked in place upon rotation of the shaft. The rear latches bias the fuser frame for proper gear mesh and paper path alignment.Type: GrantFiled: March 12, 2001Date of Patent: February 24, 2004Assignee: Lexmark International, Inc.Inventors: Gordon Robert Dunning, Paul Douglas Horrall, Edward Alan Rush
-
Patent number: 6535236Abstract: An imaging apparatus includes a machine frame, a printhead housing containing a printhead for generating a laser beam, and a position sensing device. The position sensing device includes a position sensing device frame and a position sensor for sensing a position of the laser beam. The position sensing device frame is interposed between the machine frame and the printhead housing. Each of the machine frame, the printhead housing and the position sensing device frame include at least one reference feature that in combination accurately reference the position of the printhead housing to the machine frame.Type: GrantFiled: November 9, 2000Date of Patent: March 18, 2003Assignee: Lexmark International, Inc.Inventors: Billy Carl Chappel, Christopher Gregory Chee, Gordon Robert Dunning, Paul Douglas Horrall