Patents by Inventor Alexander Krizhevsky
Alexander Krizhevsky 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).
-
Patent number: 11928577Abstract: A parallel convolutional neural network is provided. The CNN is implemented by a plurality of convolutional neural networks each on a respective processing node. Each CNN has a plurality of layers. A subset of the layers are interconnected between processing nodes such that activations are fed forward across nodes. The remaining subset is not so interconnected.Type: GrantFiled: April 27, 2020Date of Patent: March 12, 2024Assignee: Google LLCInventors: Alexander Krizhevsky, Ilya Sutskever, Geoffrey E. Hinton
-
Patent number: 11928866Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for selecting locations in an environment of a vehicle where objects are likely centered and determining properties of those objects. One of the methods includes receiving an input characterizing an environment external to a vehicle. For each of a plurality of locations in the environment, a respective first object score that represents a likelihood that a center of an object is located at the location is determined. Based on the first object scores, one or more locations from the plurality of locations are selected as locations in the environment at which respective objects are likely centered. Object properties of the objects that are likely centered at the selected locations are also determined.Type: GrantFiled: January 3, 2022Date of Patent: March 12, 2024Assignee: Waymo LLCInventors: Abhijit Ogale, Alexander Krizhevsky
-
Patent number: 11829882Abstract: A system for training a neural network. A switch is linked to feature detectors in at least some of the layers of the neural network. For each training case, the switch randomly selectively disables each of the feature detectors in accordance with a preconfigured probability. The weights from each training case are then normalized for applying the neural network to test data.Type: GrantFiled: April 9, 2021Date of Patent: November 28, 2023Assignee: Google LLCInventors: Geoffrey E. Hinton, Alexander Krizhevsky, Ilya Sutskever, Nitish Srivastava
-
Patent number: 11783180Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating object predictions using a neural network. One of the methods includes receiving respective projections of a plurality of channels of input sensor data, wherein each channel of input sensor data represents different respective characteristics of electromagnetic radiation reflected off of one or more objects. Each of the projections of the plurality of channels of input sensor data are provided to a neural network subsystem trained to receive projections of input sensor data as input and to provide an object prediction as an output. At the output of the neural network subsystem, an object prediction that predicts a region of space that is likely to be occupied by an object is received.Type: GrantFiled: August 3, 2020Date of Patent: October 10, 2023Assignee: Waymo LLCInventors: Abhijit Ogale, Alexander Krizhevsky, Wan-Yen Lo
-
Patent number: 11531894Abstract: A neural network system for identifying positions of objects in an input image can include an object detector neural network, a memory interface subsystem, and an external memory. The object detector neural network is configured to, at each time step of multiple successive time steps, (i) receive a first neural network input that represents the input image and a second neural network input that identifies a first set of positions of the input image that have each been classified as showing a respective object of the set of objects, and (ii) process the first and second inputs to generate a set of output scores that each represents a respective likelihood that an object that is not one of the objects shown at any of the positions in the first set of positions is shown at a respective position of the input image that corresponds to the output score.Type: GrantFiled: September 4, 2020Date of Patent: December 20, 2022Assignee: Waymo LLCInventors: Abhijit Ogale, Alexander Krizhevsky, Wan-Yen Lo
-
Publication number: 20220198807Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for selecting locations in an environment of a vehicle where objects are likely centered and determining properties of those objects. One of the methods includes receiving an input characterizing an environment external to a vehicle. For each of a plurality of locations in the environment, a respective first object score that represents a likelihood that a center of an object is located at the location is determined. Based on the first object scores, one or more locations from the plurality of locations are selected as locations in the environment at which respective objects are likely centered. Object properties of the objects that are likely centered at the selected locations are also determined.Type: ApplicationFiled: January 3, 2022Publication date: June 23, 2022Inventors: Abhijit Ogale, Alexander Krizhevsky
-
Patent number: 11256983Abstract: Systems, methods, devices, and other techniques for training a trajectory planning neural network system to determine waypoints for trajectories of vehicles. A neural network training system can train the trajectory planning neural network system on the multiple training data sets. Each training data set can include: (i) a first training input that characterizes a set of waypoints that represent respective locations of a vehicle at each of a series of first time steps, (ii) a second training input that characterizes at least one of (a) environmental data that represents a current state of an environment of the vehicle or (b) navigation data that represents a planned navigation route for the vehicle, and (iii) a target output characterizing a waypoint that represents a target location of the vehicle at a second time step that follows the series of first time steps.Type: GrantFiled: July 27, 2017Date of Patent: February 22, 2022Assignee: Waymo LLCInventors: Abhijit Ogale, Mayank Bansal, Alexander Krizhevsky
-
Patent number: 11216674Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for selecting locations in an environment of a vehicle where objects are likely centered and determining properties of those objects. One of the methods includes receiving an input characterizing an environment external to a vehicle. For each of a plurality of locations in the environment, a respective first object score that represents a likelihood that a center of an object is located at the location is determined. Based on the first object scores, one or more locations from the plurality of locations are selected as locations in the environment at which respective objects are likely centered. Object properties of the objects that are likely centered at the selected locations are also determined.Type: GrantFiled: April 20, 2020Date of Patent: January 4, 2022Assignee: Waymo LLCInventors: Abhijit Ogale, Alexander Krizhevsky
-
Publication number: 20210224659Abstract: A system for training a neural network. A switch is linked to feature detectors in at least some of the layers of the neural network. For each training case, the switch randomly selectively disables each of the feature detectors in accordance with a preconfigured probability. The weights from each training case are then normalized for applying the neural network to test data.Type: ApplicationFiled: April 9, 2021Publication date: July 22, 2021Inventors: Geoffrey E. Hinton, Alexander Krizhevsky, Ilya Sutskever, Nitish Srivastava
-
Patent number: 10977557Abstract: A system for training a neural network. A switch is linked to feature detectors in at least some of the layers of the neural network. For each training case, the switch randomly selectively disables each of the feature detectors in accordance with a preconfigured probability. The weights from each training case are then normalized for applying the neural network to test data.Type: GrantFiled: July 26, 2019Date of Patent: April 13, 2021Assignee: Google LLCInventors: Geoffrey E. Hinton, Alexander Krizhevsky, Ilya Sutskever, Nitish Srivastava
-
Patent number: 10883844Abstract: Systems, methods, devices, and other techniques for planning a trajectory of a vehicle. A computing system can implement a trajectory planning neural network configured to, at each time step of multiple time steps: obtain a first neural network input and a second neural network input. The first neural network input can characterize a set of waypoints indicated by the waypoint data, and the second neural network input can characterize (a) environmental data that represents a current state of an environment of the vehicle and (b) navigation data that represents a planned navigation route for the vehicle. The trajectory planning neural network may process the first neural network input and the second neural network input to generate a set of output scores, where each output score in the set of output scores corresponds to a different location of a set of possible locations in a vicinity of the vehicle.Type: GrantFiled: July 27, 2017Date of Patent: January 5, 2021Assignee: Waymo LLCInventors: Abhijit Ogale, Mayank Bansal, Alexander Krizhevsky
-
Publication number: 20200327391Abstract: A parallel convolutional neural network is provided. The CNN is implemented by a plurality of convolutional neural networks each on a respective processing node. Each CNN has a plurality of layers. A subset of the layers are interconnected between processing nodes such that activations are fed forward across nodes. The remaining subset is not so interconnected.Type: ApplicationFiled: April 27, 2020Publication date: October 15, 2020Inventors: Alexander Krizhevsky, Ilya Sutskever, Geoffrey E. Hinton
-
Patent number: 10769809Abstract: A neural network system for identifying positions of objects in an input image can include an object detector neural network, a memory interface subsystem, and an external memory. The object detector neural network is configured to, at each time step of multiple successive time steps, (i) receive a first neural network input that represents the input image and a second neural network input that identifies a first set of positions of the input image that have each been classified as showing a respective object of the set of objects, and (ii) process the first and second inputs to generate a set of output scores that each represents a respective likelihood that an object that is not one of the objects shown at any of the positions in the first set of positions is shown at a respective position of the input image that corresponds to the output score.Type: GrantFiled: June 29, 2018Date of Patent: September 8, 2020Assignee: Waymo LLCInventors: Abhijit Ogale, Alexander Krizhevsky, Wan-Yen Lo
-
Patent number: 10733506Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating object predictions using a neural network. One of the methods includes receiving respective projections of a plurality of channels of input sensor data, wherein each channel of input sensor data represents different respective characteristics of electromagnetic radiation reflected off of one or more objects. Each of the projections of the plurality of channels of input sensor data are provided to a neural network subsystem trained to receive projections of input sensor data as input and to provide an object prediction as an output. At the output of the neural network subsystem, an object prediction that predicts a region of space that is likely to be occupied by an object is received.Type: GrantFiled: December 14, 2016Date of Patent: August 4, 2020Assignee: Waymo LLCInventors: Abhijit Ogale, Alexander Krizhevsky, Wan-Yen Lo
-
Publication number: 20200242375Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for selecting locations in an environment of a vehicle where objects are likely centered and determining properties of those objects. One of the methods includes receiving an input characterizing an environment external to a vehicle. For each of a plurality of locations in the environment, a respective first object score that represents a likelihood that a center of an object is located at the location is determined. Based on the first object scores, one or more locations from the plurality of locations are selected as locations in the environment at which respective objects are likely centered. Object properties of the objects that are likely centered at the selected locations are also determined.Type: ApplicationFiled: April 20, 2020Publication date: July 30, 2020Inventors: Abhijit Ogale, Alexander Krizhevsky
-
Publication number: 20200174490Abstract: Systems, methods, devices, and other techniques for planning a trajectory of a vehicle. A computing system can implement a trajectory planning neural network configured to, at each time step of multiple time steps: obtain a first neural network input and a second neural network input. The first neural network input can characterize a set of waypoints indicated by the waypoint data, and the second neural network input can characterize (a) environmental data that represents a current state of an environment of the vehicle and (b) navigation data that represents a planned navigation route for the vehicle. The trajectory planning neural network may process the first neural network input and the second neural network input to generate a set of output scores, where each output score in the set of output scores corresponds to a different location of a set of possible locations in a vicinity of the vehicle.Type: ApplicationFiled: July 27, 2018Publication date: June 4, 2020Inventors: Abhijit Ogale, Mayank Bansal, Alexander Krizhevsky
-
Patent number: 10635966Abstract: A parallel convolutional neural network is provided. The CNN is implemented by a plurality of convolutional neural networks each on a respective processing node. Each CNN has a plurality of layers. A subset of the layers are interconnected between processing nodes such that activations are fed forward across nodes. The remaining subset is not so interconnected.Type: GrantFiled: January 24, 2017Date of Patent: April 28, 2020Assignee: Google LLCInventors: Alexander Krizhevsky, Ilya Sutskever, Geoffrey E. Hinton
-
Patent number: 10628686Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for selecting locations in an environment of a vehicle where objects are likely centered and determining properties of those objects. One of the methods includes receiving an input characterizing an environment external to a vehicle. For each of a plurality of locations in the environment, a respective first object score that represents a likelihood that a center of an object is located at the location is determined. Based on the first object scores, one or more locations from the plurality of locations are selected as locations in the environment at which respective objects are likely centered. Object properties of the objects that are likely centered at the selected locations are also determined.Type: GrantFiled: March 12, 2018Date of Patent: April 21, 2020Assignee: Waymo LLCInventors: Abhijit Ogale, Alexander Krizhevsky
-
Patent number: 10540587Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training a convolutional neural network (CNN). The system includes a plurality of workers, wherein each worker is configured to maintain a respective replica of each of the convolutional layers of the CNN and a respective disjoint partition of each of the fully-connected layers of the CNN, wherein each replica of a convolutional layer includes all of the nodes in the convolutional layer, and wherein each disjoint partition of a fully-connected layer includes a portion of the nodes of the fully-connected layer.Type: GrantFiled: April 10, 2015Date of Patent: January 21, 2020Assignee: Google LLCInventor: Alexander Krizhevsky
-
Publication number: 20190347558Abstract: A system for training a neural network. A switch is linked to feature detectors in at least some of the layers of the neural network. For each training case, the switch randomly selectively disables each of the feature detectors in accordance with a preconfigured probability. The weights from each training case are then normalized for applying the neural network to test data.Type: ApplicationFiled: July 26, 2019Publication date: November 14, 2019Inventors: Geoffrey E. Hinton, Alexander Krizhevsky, Ilya Sutskever, Nitish Srivastava