Patents by Inventor Harsimran Singh Sidhu
Harsimran Singh Sidhu 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: 11893774Abstract: Systems and methods for training machine models with augmented data. An example method includes identifying a set of images captured by a set of cameras while affixed to one or more image collection systems. For each image in the set of images, a training output for the image is identified. For one or more images in the set of images, an augmented image for a set of augmented images is generated. Generating an augmented image includes modifying the image with an image manipulation function that maintains camera properties of the image. The augmented training image is associated with the training output of the image. A set of parameters of the predictive computer model are trained to predict the training output based on an image training set including the images and the set of augmented images.Type: GrantFiled: December 14, 2021Date of Patent: February 6, 2024Assignee: Tesla, Inc.Inventors: Matthew John Cooper, Paras Jagdish Jain, Harsimran Singh Sidhu
-
Publication number: 20230289599Abstract: A model training and implementation pipeline trains models for individual embedded systems. The pipeline iterates through multiple models and estimates the performance of the models. During a model generation stage, the pipeline translates the description of the model together with the model parameters into an intermediate representation in a language that is compatible with a virtual machine. The intermediate representation is agnostic or independent to the configuration of the target platform. During a model performance estimation stage, the pipeline evaluates the performance of the models without training the models. Based on the analysis of the performance of the untrained models, a subset of models is selected. The selected models are then trained and the performance of the trained models are analyzed. Based on the analysis of the performance of the trained models, a single model is selected for deployment to the target platform.Type: ApplicationFiled: March 14, 2023Publication date: September 14, 2023Inventors: Harsimran Singh Sidhu, Paras Jagdish Jain, Daniel Paden Tomasello, Forrest Nelson Iandola
-
Publication number: 20230237331Abstract: A neural network architecture is used that reduces the processing load of implementing the neural network. This network architecture may thus be used for reduced-bit processing devices. The architecture may limit the number of bits used for processing and reduce processing to prevent data overflow at individual calculations of the neural network. To implement this architecture, the number of bits used to represent inputs at levels of the network and the related filter masks may also be modified to ensure the number of bits of the output does not overflow the resulting capacity of the reduced-bit processor. To additionally reduce the load for such a network, the network may implement a “starconv” structure that permits the incorporation of nearby nodes in a layer to balance processing requirements and permit the network to learn from context of other nodes.Type: ApplicationFiled: January 19, 2023Publication date: July 27, 2023Inventors: Forrest Nelson Iandola, Harsimran Singh Sidhu, Yiqi Hou
-
Publication number: 20230177819Abstract: An autonomous control system generates synthetic data that reflect simulated environments. Specifically, the synthetic data is a representation of sensor data of the simulated environment from the perspective of one or more sensors. The system generates synthetic data by introducing one or more simulated modifications to sensor data captured by the sensors or by simulating the sensor data for a virtual environment. The autonomous control system uses the synthetic data to train computer models for various detection and control algorithms. In general, this allows autonomous control systems to augment training data to improve performance of computer models, simulate scenarios that are not included in existing training data, and/or train computer models that remove unwanted effects or occlusions from sensor data of the environment.Type: ApplicationFiled: October 28, 2022Publication date: June 8, 2023Inventors: Forrest Nelson Iandola, Donald Benton MacMillen, Anting Shen, Harsimran Singh Sidhu, Paras Jagdish Jain
-
Patent number: 11636333Abstract: A model training and implementation pipeline trains models for individual embedded systems. The pipeline iterates through multiple models and estimates the performance of the models. During a model generation stage, the pipeline translates the description of the model together with the model parameters into an intermediate representation in a language that is compatible with a virtual machine. The intermediate representation is agnostic or independent to the configuration of the target platform. During a model performance estimation stage, the pipeline evaluates the performance of the models without training the models. Based on the analysis of the performance of the untrained models, a subset of models is selected. The selected models are then trained and the performance of the trained models are analyzed. Based on the analysis of the performance of the trained models, a single model is selected for deployment to the target platform.Type: GrantFiled: July 25, 2019Date of Patent: April 25, 2023Assignee: Tesla, Inc.Inventors: Harsimran Singh Sidhu, Paras Jagdish Jain, Daniel Paden Tomasello, Forrest Nelson Iandola
-
Patent number: 11562231Abstract: A neural network architecture is used that reduces the processing load of implementing the neural network. This network architecture may thus be used for reduced-bit processing devices. The architecture may limit the number of bits used for processing and reduce processing to prevent data overflow at individual calculations of the neural network. To implement this architecture, the number of bits used to represent inputs at levels of the network and the related filter masks may also be modified to ensure the number of bits of the output does not overflow the resulting capacity of the reduced-bit processor. To additionally reduce the load for such a network, the network may implement a “starconv” structure that permits the incorporation of nearby nodes in a layer to balance processing requirements and permit the network to learn from context of other nodes.Type: GrantFiled: September 3, 2019Date of Patent: January 24, 2023Assignee: Tesla, Inc.Inventors: Forrest Nelson Iandola, Harsimran Singh Sidhu, Yiqi Hou
-
Patent number: 11487288Abstract: An autonomous control system generates synthetic data that reflect simulated environments. Specifically, the synthetic data is a representation of sensor data of the simulated environment from the perspective of one or more sensors. The system generates synthetic data by introducing one or more simulated modifications to sensor data captured by the sensors or by simulating the sensor data for a virtual environment. The autonomous control system uses the synthetic data to train computer models for various detection and control algorithms. In general, this allows autonomous control systems to augment training data to improve performance of computer models, simulate scenarios that are not included in existing training data, and/or train computer models that remove unwanted effects or occlusions from sensor data of the environment.Type: GrantFiled: June 8, 2020Date of Patent: November 1, 2022Assignee: Tesla, Inc.Inventors: Forrest Nelson Iandola, Donald Benton MacMillen, Anting Shen, Harsimran Singh Sidhu, Paras Jagdish Jain
-
Publication number: 20220108130Abstract: Systems and methods for training machine models with augmented data. An example method includes identifying a set of images captured by a set of cameras while affixed to one or more image collection systems. For each image in the set of images, a training output for the image is identified. For one or more images in the set of images, an augmented image for a set of augmented images is generated. Generating an augmented image includes modifying the image with an image manipulation function that maintains camera properties of the image. The augmented training image is associated with the training output of the image. A set of parameters of the predictive computer model are trained to predict the training output based on an image training set including the images and the set of augmented images.Type: ApplicationFiled: December 14, 2021Publication date: April 7, 2022Inventors: Matthew John Cooper, Paras Jagdish Jain, Harsimran Singh Sidhu
-
Publication number: 20220043449Abstract: An autonomous control system combines sensor data from multiple sensors to simulate sensor data from high-capacity sensors. The sensor data contains information related to physical environments surrounding vehicles for autonomous guidance. For example, the sensor data may be in the form of images that visually capture scenes of the surrounding environment, geo-location of the vehicles, and the like. The autonomous control system simulates high-capacity sensor data of the physical environment from replacement sensors that may each have lower capacity than high-capacity sensors. The high-capacity sensor data may be simulated via one or more neural network models. The autonomous control system performs various detection and control algorithms on the simulated sensor data to guide the vehicle autonomously.Type: ApplicationFiled: October 22, 2021Publication date: February 10, 2022Inventors: Forrest Nelson Iandola, Donald Benton MacMillen, Anting Shen, Harsimran Singh Sidhu, Daniel Paden Tomasello, Rohan Nandkumar Phadte, Paras Jagdish Jian
-
Patent number: 11205093Abstract: Systems and methods for training machine models with augmented data. An example method includes identifying a set of images captured by a set of cameras while affixed to one or more image collection systems. For each image in the set of images, a training output for the image is identified. For one or more images in the set of images, an augmented image for a set of augmented images is generated. Generating an augmented image includes modifying the image with an image manipulation function that maintains camera properties of the image. The augmented training image is associated with the training output of the image. A set of parameters of the predictive computer model are trained to predict the training output based on an image training set including the images and the set of augmented images.Type: GrantFiled: October 10, 2019Date of Patent: December 21, 2021Assignee: Tesla, Inc.Inventors: Matthew John Cooper, Paras Jagdish Jain, Harsimran Singh Sidhu
-
Patent number: 11157014Abstract: An autonomous control system combines sensor data from multiple sensors to simulate sensor data from high-capacity sensors. The sensor data contains information related to physical environments surrounding vehicles for autonomous guidance. For example, the sensor data may be in the form of images that visually capture scenes of the surrounding environment, geo-location of the vehicles, and the like. The autonomous control system simulates high-capacity sensor data of the physical environment from replacement sensors that may each have lower capacity than high-capacity sensors. The high-capacity sensor data may be simulated via one or more neural network models. The autonomous control system performs various detection and control algorithms on the simulated sensor data to guide the vehicle autonomously.Type: GrantFiled: December 27, 2017Date of Patent: October 26, 2021Assignee: Tesla, Inc.Inventors: Forrest Nelson Iandola, Donald Benton MacMillen, Anting Shen, Harsimran Singh Sidhu, Daniel Paden Tomasello, Rohan Nandkumar Phadte, Paras Jagdish Jain
-
Publication number: 20200401136Abstract: An autonomous control system generates synthetic data that reflect simulated environments. Specifically, the synthetic data is a representation of sensor data of the simulated environment from the perspective of one or more sensors. The system generates synthetic data by introducing one or more simulated modifications to sensor data captured by the sensors or by simulating the sensor data for a virtual environment. The autonomous control system uses the synthetic data to train computer models for various detection and control algorithms. In general, this allows autonomous control systems to augment training data to improve performance of computer models, simulate scenarios that are not included in existing training data, and/or train computer models that remove unwanted effects or occlusions from sensor data of the environment.Type: ApplicationFiled: June 8, 2020Publication date: December 24, 2020Inventors: Forrest Nelson Iandola, Donald Benton MacMillen, Anting Shen, Harsimran Singh Sidhu, Paras Jagdish Jain
-
Patent number: 10678244Abstract: An autonomous control system generates synthetic data that reflect simulated environments. Specifically, the synthetic data is a representation of sensor data of the simulated environment from the perspective of one or more sensors. The system generates synthetic data by introducing one or more simulated modifications to sensor data captured by the sensors or by simulating the sensor data for a virtual environment. The autonomous control system uses the synthetic data to train computer models for various detection and control algorithms. In general, this allows autonomous control systems to augment training data to improve performance of computer models, simulate scenarios that are not included in existing training data, and/or train computer models that remove unwanted effects or occlusions from sensor data of the environment.Type: GrantFiled: March 23, 2018Date of Patent: June 9, 2020Assignee: Tesla, Inc.Inventors: Forrest Nelson Iandola, Donald Benton MacMillen, Anting Shen, Harsimran Singh Sidhu, Paras Jagdish Jain
-
Publication number: 20200117953Abstract: Systems and methods for training machine models with augmented data. An example method includes identifying a set of images captured by a set of cameras while affixed to one or more image collection systems. For each image in the set of images, a training output for the image is identified. For one or more images in the set of images, an augmented image for a set of augmented images is generated. Generating an augmented image includes modifying the image with an image manipulation function that maintains camera properties of the image. The augmented training image is associated with the training output of the image. A set of parameters of the predictive computer model are trained to predict the training output based on an image training set including the images and the set of augmented images.Type: ApplicationFiled: October 10, 2019Publication date: April 16, 2020Inventors: Matthew John Cooper, Paras Jain, Harsimran Singh Sidhu
-
Publication number: 20200074304Abstract: A neural network architecture is used that reduces the processing load of implementing the neural network. This network architecture may thus be used for reduced-bit processing devices. The architecture may limit the number of bits used for processing and reduce processing to prevent data overflow at individual calculations of the neural network. To implement this architecture, the number of bits used to represent inputs at levels of the network and the related filter masks may also be modified to ensure the number of bits of the output does not overflow the resulting capacity of the reduced-bit processor. To additionally reduce the load for such a network, the network may implement a “starconv” structure that permits the incorporation of nearby nodes in a layer to balance processing requirements and permit the network to learn from context of other nodes.Type: ApplicationFiled: September 3, 2019Publication date: March 5, 2020Inventors: Forrest Nelson Iandola, Harsimran Singh Sidhu, Yiqi Hou
-
Publication number: 20200034710Abstract: A model training and implementation pipeline trains models for individual embedded systems. The pipeline iterates through multiple models and estimates the performance of the models. During a model generation stage, the pipeline translates the description of the model together with the model parameters into an intermediate representation in a language that is compatible with a virtual machine. The intermediate representation is agnostic or independent to the configuration of the target platform. During a model performance estimation stage, the pipeline evaluates the performance of the models without training the models. Based on the analysis of the performance of the untrained models, a subset of models is selected. The selected models are then trained and the performance of the trained models are analyzed. Based on the analysis of the performance of the trained models, a single model is selected for deployment to the target platform.Type: ApplicationFiled: July 25, 2019Publication date: January 30, 2020Inventors: Harsimran Singh Sidhu, Paras Jagdish Jain, Daniel Paden Tomasello, Forrest Nelson Iandola
-
Publication number: 20180275658Abstract: An autonomous control system generates synthetic data that reflect simulated environments. Specifically, the synthetic data is a representation of sensor data of the simulated environment from the perspective of one or more sensors. The system generates synthetic data by introducing one or more simulated modifications to sensor data captured by the sensors or by simulating the sensor data for a virtual environment. The autonomous control system uses the synthetic data to train computer models for various detection and control algorithms. In general, this allows autonomous control systems to augment training data to improve performance of computer models, simulate scenarios that are not included in existing training data, and/or train computer models that remove unwanted effects or occlusions from sensor data of the environment.Type: ApplicationFiled: March 23, 2018Publication date: September 27, 2018Inventors: Forrest Nelson Iandola, Donald Benton MacMillen, Anting Shen, Harsimran Singh Sidhu, Paras Jagdish Jain
-
Publication number: 20180188733Abstract: An autonomous control system combines sensor data from multiple sensors to simulate sensor data from high-capacity sensors. The sensor data contains information related to physical environments surrounding vehicles for autonomous guidance. For example, the sensor data may be in the form of images that visually capture scenes of the surrounding environment, geo-location of the vehicles, and the like. The autonomous control system simulates high-capacity sensor data of the physical environment from replacement sensors that may each have lower capacity than high-capacity sensors. The high-capacity sensor data may be simulated via one or more neural network models. The autonomous control system performs various detection and control algorithms on the simulated sensor data to guide the vehicle autonomously.Type: ApplicationFiled: December 27, 2017Publication date: July 5, 2018Inventors: Forrest Nelson Iandola, Donald Benton MacMillen, Anting Shen, Harsimran Singh Sidhu, Daniel Paden Tomasello, Rohan Nandkumar Phadte, Paras Jagdish Jain