Patents by Inventor Anatoly Gorshechnikov
Anatoly Gorshechnikov 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: 11928602Abstract: Lifelong Deep Neural Network (L-DNN) technology revolutionizes Deep Learning by enabling fast, post-deployment learning without extensive training, heavy computing resources, or massive data storage. It uses a representation-rich, DNN-based subsystem (Module A) with a fast-learning subsystem (Module B) to learn new features quickly without forgetting previously learned features. Compared to a conventional DNN, L-DNN uses much less data to build robust networks, dramatically shorter training time, and learning on-device instead of on servers. It can add new knowledge without re-training or storing data. As a result, an edge device with L-DNN can learn continuously after deployment, eliminating massive costs in data collection and annotation, memory and data storage, and compute power. This fast, local, on-device learning can be used for security, supply chain monitoring, disaster and emergency response, and drone-based inspection of infrastructure and properties, among other applications.Type: GrantFiled: May 9, 2018Date of Patent: March 12, 2024Assignee: Neurala, Inc.Inventors: Matthew Luciw, Santiago Olivera, Anatoly Gorshechnikov, Jeremy Wurbs, Heather Marie Ames, Massimiliano Versace
-
Patent number: 11070623Abstract: The system and methods disclosed herein include a runtime architecture that takes a nonspecific set of systems of differential equations, distributes them across the network, and iteratively integrates them through time with a possibility to output the results on every iteration. Embodiments of the disclosed system may be used for neural computation or any other suitable application. Embodiments can be used as a standalone engine or as part of another computational system for massively parallel numerical integration of a data-driven dynamical system.Type: GrantFiled: October 19, 2018Date of Patent: July 20, 2021Assignee: Neurala, Inc.Inventors: Anatoly Gorshechnikov, Massimiliano Versace, Heather Ames Versace, Gennady Livitz
-
Patent number: 10974389Abstract: The systems and methods disclosed herein include a path integration system that calculates optic flow, infers angular velocity from the flow field, and incorporates this velocity estimate into heading calculations. The resulting system fuses heading estimates from accelerometers, 5 gyroscopes, engine torques, and optic flow to determine self-localization. The system also includes a motivational system that implements a reward drive, both positive and negative, into the system. In some implementations, the drives can include: a) a curiosity drive that encourages exploration of new areas, b) a resource drive that attracts the agent towards the recharging base when the battery is low, and c) a mineral reward drive that attracts the agent 10 towards previously explored scientific targets.Type: GrantFiled: April 5, 2019Date of Patent: April 13, 2021Assignee: Neurala, Inc.Inventors: Anatoly Gorshechnikov, Massimiliano Versace
-
Patent number: 10846873Abstract: Sensory processing of visual, auditory, and other sensor information (e.g., visual imagery, LIDAR, RADAR) is conventionally based on “stovepiped,” or isolated processing, with little interactions between modules. Biological systems, on the other hand, fuse multi-sensory information to identify nearby objects of interest more quickly, more efficiently, and with higher signal-to-noise ratios. Similarly, examples of the OpenSense technology disclosed herein use neurally inspired processing to identify and locate objects in a robot's environment. This enables the robot to navigate its environment more quickly and with lower computational and power requirements.Type: GrantFiled: September 24, 2018Date of Patent: November 24, 2020Assignee: Neurala, Inc.Inventors: Massimiliano Versace, Anatoly Gorshechnikov
-
Publication number: 20200151446Abstract: Sensory processing of visual, auditory, and other sensor information (e.g., visual imagery, LIDAR, RADAR) is conventionally based on “stovepiped,” or isolated processing, with little interactions between modules. Biological systems, on the other hand, fuse multi-sensory information to identify nearby objects of interest more quickly, more efficiently, and with higher signal-to-noise ratios. Similarly, examples of the OpenSense technology disclosed herein use neurally inspired processing to identify and locate objects in a robot's environment. This enables the robot to navigate its environment more quickly and with lower computational and power requirements.Type: ApplicationFiled: October 24, 2019Publication date: May 14, 2020Inventors: Massimiliano Versace, Anatoly Gorshechnikov
-
Patent number: 10503976Abstract: Sensory processing of visual, auditory, and other sensor information (e.g., visual imagery, LIDAR, RADAR) is conventionally based on “stovepiped,” or isolated processing, with little interactions between modules. Biological systems, on the other hand, fuse multi-sensory information to identify nearby objects of interest more quickly, more efficiently, and with higher signal-to-noise ratios. Similarly, examples of the OpenSense technology disclosed herein use neurally inspired processing to identify and locate objects in a robot's environment. This enables the robot to navigate its environment more quickly and with lower computational and power requirements.Type: GrantFiled: March 20, 2017Date of Patent: December 10, 2019Assignee: Neurala, Inc.Inventors: Massimiliano Versace, Anatoly Gorshechnikov
-
Patent number: 10469588Abstract: The system and methods disclosed herein include a runtime architecture that takes a nonspecific set of systems of differential equations, distributes them across the network, and iteratively integrates them through time with a possibility to output the results on every iteration. Embodiments of the disclosed system may be used for neural computation or any other suitable application. Embodiments can be used as a standalone engine or as part of another computational system for massively parallel numerical integration of a data-driven dynamical system.Type: GrantFiled: November 20, 2015Date of Patent: November 5, 2019Assignee: Neurala, Inc.Inventors: Anatoly Gorshechnikov, Massimiliano Versace, Heather Ames Versace, Gennady Livitz
-
Publication number: 20190240840Abstract: The systems and methods disclosed herein include a path integration system that calculates optic flow, infers angular velocity from the flow field, and incorporates this velocity estimate into heading calculations. The resulting system fuses heading estimates from accelerometers, 5 gyroscopes, engine torques, and optic flow to determine self-localization. The system also includes a motivational system that implements a reward drive, both positive and negative, into the system. In some implementations, the drives can include: a) a curiosity drive that encourages exploration of new areas, b) a resource drive that attracts the agent towards the recharging base when the battery is low, and c) a mineral reward drive that attracts the agent 10 towards previously explored scientific targets.Type: ApplicationFiled: April 5, 2019Publication date: August 8, 2019Inventors: Anatoly Gorshechnikov, Massimiliano Versace, Tim Barnes
-
Patent number: 10300603Abstract: The systems and methods disclosed herein include a path integration system that calculates optic flow, infers angular velocity from the flow field, and incorporates this velocity estimate into heading calculations. The resulting system fuses heading estimates from accelerometers, gyroscopes, engine torques, and optic flow to determine self-localization. The system also includes a motivational system that implements a reward drive, both positive and negative, into the system. In some implementations, the drives can include: a) a curiosity drive that encourages exploration of new areas, b) a resource drive that attracts the agent towards the recharging base when the battery is low, and c) a mineral reward drive that attracts the agent towards previously explored scientific targets.Type: GrantFiled: November 20, 2015Date of Patent: May 28, 2019Assignee: Neurala, Inc.Inventors: Anatoly Gorshechnikov, Massimiliano Versace, Tim Barnes
-
Publication number: 20190124155Abstract: The system and methods disclosed herein include a runtime architecture that takes a nonspecific set of systems of differential equations, distributes them across the network, and iteratively integrates them through time with a possibility to output the results on every iteration. Embodiments of the disclosed system may be used for neural computation or any other suitable application. Embodiments can be used as a standalone engine or as part of another computational system for massively parallel numerical integration of a data-driven dynamical system.Type: ApplicationFiled: October 19, 2018Publication date: April 25, 2019Inventors: Anatoly Gorshechnikov, Massimiliano Versace, Heather Ames Versace, Gennady Livitz
-
Publication number: 20190087975Abstract: Sensory processing of visual, auditory, and other sensor information (e.g., visual imagery, LIDAR, RADAR) is conventionally based on “stovepiped,” or isolated processing, with little interactions between modules. Biological systems, on the other hand, fuse multi-sensory information to identify nearby objects of interest more quickly, more efficiently, and with higher signal-to-noise ratios. Similarly, examples of the OpenSense technology disclosed herein use neurally inspired processing to identify and locate objects in a robot's environment. This enables the robot to navigate its environment more quickly and with lower computational and power requirements.Type: ApplicationFiled: September 24, 2018Publication date: March 21, 2019Inventors: Massimiliano Versace, Anatoly GORSHECHNIKOV
-
Publication number: 20180330238Abstract: Lifelong Deep Neural Network (L-DNN) technology revolutionizes Deep Learning by enabling fast, post-deployment learning without extensive training, heavy computing resources, or massive data storage. It uses a representation-rich, DNN-based subsystem (Module A) with a fast-learning subsystem (Module B) to learn new features quickly without forgetting previously learned features. Compared to a conventional DNN, L-DNN uses much less data to build robust networks, dramatically shorter training time, and learning on-device instead of on servers. It can add new knowledge without re-training or storing data. As a result, an edge device with L-DNN can learn continuously after deployment, eliminating massive costs in data collection and annotation, memory and data storage, and compute power. This fast, local, on-device learning can be used for security, supply chain monitoring, disaster and emergency response, and drone-based inspection of infrastructure and properties, among other applications.Type: ApplicationFiled: May 9, 2018Publication date: November 15, 2018Inventors: Matthew Luciw, Santiago OLIVERA, Anatoly GORSHECHNIKOV, Jeremy WURBS, Heather Marie AMES, Massimiliano VERSACE
-
Patent number: 10083523Abstract: Sensory processing of visual, auditory, and other sensor information (e.g., visual imagery, LIDAR, RADAR) is conventionally based on “stovepiped,” or isolated processing, with little interactions between modules. Biological systems, on the other hand, fuse multi-sensory information to identify nearby objects of interest more quickly, more efficiently, and with higher signal-to-noise ratios. Similarly, examples of the OpenSense technology disclosed herein use neurally inspired processing to identify and locate objects in a robot's environment. This enables the robot to navigate its environment more quickly and with lower computational and power requirements.Type: GrantFiled: September 12, 2016Date of Patent: September 25, 2018Assignee: Neurala, Inc.Inventors: Massimiliano Versace, Anatoly Gorshechnikov
-
Publication number: 20170193298Abstract: Sensory processing of visual, auditory, and other sensor information (e.g., visual imagery, LIDAR, RADAR) is conventionally based on “stovepiped,” or isolated processing, with little interactions between modules. Biological systems, on the other hand, fuse multi-sensory information to identify nearby objects of interest more quickly, more efficiently, and with higher signal-to-noise ratios. Similarly, examples of the OpenSense technology disclosed herein use neurally inspired processing to identify and locate objects in a robot's environment. This enables the robot to navigate its environment more quickly and with lower computational and power requirements.Type: ApplicationFiled: March 20, 2017Publication date: July 6, 2017Inventors: Massimiliano Versace, Anatoly Gorshechnikov, Gennady Livitz, Jesse Palma
-
Patent number: 9626566Abstract: Sensory processing of visual, auditory, and other sensor information (e.g., visual imagery, LIDAR, RADAR) is conventionally based on “stovepiped,” or isolated processing, with little interactions between modules. Biological systems, on the other hand, fuse multi-sensory information to identify nearby objects of interest more quickly, more efficiently, and with higher signal-to-noise ratios. Similarly, examples of the OpenSense technology disclosed herein use neurally inspired processing to identify and locate objects in a robot's environment. This enables the robot to navigate its environment more quickly and with lower computational and power requirements.Type: GrantFiled: March 19, 2015Date of Patent: April 18, 2017Assignee: Neurala, Inc.Inventors: Massimiliano Versace, Anatoly Gorshechnikov, Gennady Livitz, Jesse Palma
-
Publication number: 20170024877Abstract: Sensory processing of visual, auditory, and other sensor information (e.g., visual imagery, LIDAR, RADAR) is conventionally based on “stovepiped,” or isolated processing, with little interactions between modules. Biological systems, on the other hand, fuse multi-sensory information to identify nearby objects of interest more quickly, more efficiently, and with higher signal-to-noise ratios. Similarly, examples of the OpenSense technology disclosed herein use neurally inspired processing to identify and locate objects in a robot's environment. This enables the robot to navigate its environment more quickly and with lower computational and power requirements.Type: ApplicationFiled: September 12, 2016Publication date: January 26, 2017Inventors: Massimiliano Versace, Anatoly GORSHECHNIKOV
-
Publication number: 20160198000Abstract: The system and methods disclosed herein include a runtime architecture that takes a nonspecific set of systems of differential equations, distributes them across the network, and iteratively integrates them through time with a possibility to output the results on every iteration. Embodiments of the disclosed system may be used for neural computation or any other suitable application. Embodiments can be used as a standalone engine or as part of another computational system for massively parallel numerical integration of a data-driven dynamical system.Type: ApplicationFiled: November 20, 2015Publication date: July 7, 2016Inventors: Anatoly Gorshechnikov, Massimiliano Versace, Heather Ames Versace, Gennady Livitz
-
Publication number: 20160082597Abstract: The systems and methods disclosed herein include a path integration system that calculates optic flow, infers angular velocity from the flow field, and incorporates this velocity estimate into heading calculations. The resulting system fuses heading estimates from accelerometers, gyroscopes, engine torques, and optic flow to determine self-localization. The system also includes a motivational system that implements a reward drive, both positive and negative, into the system. In some implementations, the drives can include: a) a curiosity drive that encourages exploration of new areas, b) a resource drive that attracts the agent towards the recharging base when the battery is low, and c) a mineral reward drive that attracts the agent towards previously explored scientific targets.Type: ApplicationFiled: November 20, 2015Publication date: March 24, 2016Inventors: Anatoly Gorshechnikov, Massimiliano Versace, Tim Barnes
-
Publication number: 20150269439Abstract: Sensory processing of visual, auditory, and other sensor information (e.g., visual imagery, LIDAR, RADAR) is conventionally based on “stovepiped,” or isolated processing, with little interactions between modules. Biological systems, on the other hand, fuse multi-sensory information to identify nearby objects of interest more quickly, more efficiently, and with higher signal-to-noise ratios. Similarly, examples of the OpenSense technology disclosed herein use neurally inspired processing to identify and locate objects in a robot's environment. This enables the robot to navigate its environment more quickly and with lower computational and power requirements.Type: ApplicationFiled: March 19, 2015Publication date: September 24, 2015Inventors: Massimiliano Versace, Anatoly Gorshechnikov, Gennady Livitz, Jesse Palma