-
公开(公告)号：US11636348B1
公开(公告)日：2023-04-25
申请号：US17535472
申请日：2021-11-24
Applicant: Apple Inc.
Inventor： Yichuan Tang , Nitish Srivastava , Ruslan Salakhutdinov
Abstract: At a centralized model trainer, one or more neural network based models are trained using an input data set. At least a first set of parameters of a model is transmitted to a model deployment destination. Using a second input data set, one or more adaptive parameters for the model are determined at the model deployment destination. Using the adaptive parameters, one or more inferences are generated at the model deployment destination.
-
公开(公告)号：US20220343138A1
公开(公告)日：2022-10-27
申请号：US17810329
申请日：2022-06-30
Applicant: Apple Inc.
Inventor： Yichuan Tang , Nitish Srivastava , Ruslan Salakhutdinov
IPC: G06N3/04 , G06T7/20 , G06F16/432 , G01S17/89 , H04N5/14
Abstract: Sensor data captured by one or more sensors may be received at an analysis system. A neural network may be used to detect an object in the sensor data. A plurality of polygons surrounding the object may be generated in one or more subsets of the sensor data. A prediction of a future position of the object may be generated based at least in part on the polygons. One or more commands may be provided to a control system based on the prediction of the future position.
-
公开(公告)号：US20180157972A1
公开(公告)日：2018-06-07
申请号：US15828399
申请日：2017-11-30
Applicant: Apple Inc.
Inventor： Rui Hu , Kshitiz Garg , Hanlin Goh , Ruslan Salakhutdinov , Nitish Srivastava , YiChuan Tang
CPC classification number: G06N3/08 , G06K9/00791 , G06N3/0454 , G06N5/04 , G06T1/0007
Abstract: A system includes a neural network organized into layers corresponding to stages of inferences. The neural network includes a common portion, a first portion, and a second portion. The first portion includes a first set of layers dedicated to performing a first inference task on an input data. The second portion includes a second set of layers dedicated to performing a second inference task on the same input data. The common portion includes a third set of layers, which may include an input layer to the neural network, that are used in the performance of both the first and second inference tasks. The system may receive an input data and perform both inference tasks on the input data in a single pass. During training, a training sample with annotations for both inference tasks may be used to train the neural network in a single pass.
-
公开(公告)号：US20180157934A1
公开(公告)日：2018-06-07
申请号：US15828408
申请日：2017-11-30
Applicant: Apple Inc.
Inventor： Rui Hu , Ruslan Salakhutdinov , Nitish Srivastava , YiChuan Tang
CPC classification number: G06K9/6262 , G05D1/0246 , G05D2201/0213 , G06K9/00791 , G06K9/00805 , G06K9/4628 , G06K9/6256 , G06K9/66 , G06N3/0454 , G06N3/08 , G06N3/084
Abstract: A system employs an inspection neural network (INN) to inspect data generated during an inference process of a primary neural network (PNN) to generate an indication of reliability for an output generated by the PNN. The system includes a sensor configured to capture sensor data. Sensor data captured by the sensor is provided to a data analyzer to generate an output using the PNN. An analyzer inspector is configured to capture inspection data associated with the generation of the output by the data analyzer, and use the INN to generate an indication of reliability for the PNN's output based on the inspection data. The INN is trained using a set of training data that is distinct from the training data used to train the PNN.
-
公开(公告)号：US11189052B2
公开(公告)日：2021-11-30
申请号：US16990510
申请日：2020-08-11
Applicant: Apple Inc.
Inventor： Emilio Parisotto , Jian Zhang , Ruslan Salakhutdinov , Devendra Singh Chaplot
Abstract: In accordance with some embodiments, a method is performed at a device with one or more processors and non-transitory memory. The method includes obtaining location vector data characterizing an object. The method includes determining a neural pose graph associated with a respective time-period based on an initial local pose estimation as a function of respective location vector data. The method includes determining a meta pose estimation associated with the respective time-period by aggregating the neural pose graph associated with the respective time-period and one or more other neural pose graphs associated with one or more temporally adjacent time-periods. The method includes synthesizing a corrected pose estimation by correcting the meta pose estimation associated with the respective time-period based on a function of the meta pose estimation associated with the respective time-period and meta pose estimations associated with one or more temporally adjacent time-periods in order to correct accumulated errors in the initial local pose estimation.
-
Patent Agency Ranking
公开(公告)号：US10943148B2
公开(公告)日：2021-03-09
申请号：US15828408
申请日：2017-11-30
Applicant: Apple Inc.
Inventor： Rui Hu , Ruslan Salakhutdinov , Nitish Srivastava , YiChuan Tang
Abstract: A system employs an inspection neural network (INN) to inspect data generated during an inference process of a primary neural network (PNN) to generate an indication of reliability for an output generated by the PNN. The system includes a sensor configured to capture sensor data. Sensor data captured by the sensor is provided to a data analyzer to generate an output using the PNN. An analyzer inspector is configured to capture inspection data associated with the generation of the output by the data analyzer, and use the INN to generate an indication of reliability for the PNN's output based on the inspection data. The INN is trained using a set of training data that is distinct from the training data used to train the PNN.
-
公开(公告)号：US20200372675A1
公开(公告)日：2020-11-26
申请号：US16990510
申请日：2020-08-11
Applicant: Apple Inc.
Inventor： Emilio Parisotto , Jian Zhang , Ruslan Salakhutdinov , Devendra Singh Chaplot
Abstract: In accordance with some embodiments, a method is performed at a device with one or more processors and non-transitory memory. The method includes obtaining location vector data characterizing an object. The method includes determining a neural pose graph associated with a respective time-period based on an initial local pose estimation as a function of respective location vector data. The method includes determining a meta pose estimation associated with the respective time-period by aggregating the neural pose graph associated with the respective time-period and one or more other neural pose graphs associated with one or more temporally adjacent time-periods. The method includes synthesizing a corrected pose estimation by correcting the meta pose estimation associated with the respective time-period based on a function of the meta pose estimation associated with the respective time-period and meta pose estimations associated with one or more temporally adjacent time-periods in order to correct accumulated errors in the initial local pose estimation.
-
公开(公告)号：US12008790B2
公开(公告)日：2024-06-11
申请号：US16836028
申请日：2020-03-31
Applicant: Apple Inc.
Inventor： Nitish Srivastava , Ruslan Salakhutdinov , Hanlin Goh
IPC: G06T9/00 , G06N3/047 , G06N3/08 , H04N13/111 , H04N13/161
CPC classification number: G06T9/002 , G06N3/047 , G06N3/08 , H04N13/111 , H04N13/161
Abstract: A method includes defining a geometric capsule that is interpretable by a capsule neural network, wherein the geometric capsule includes a feature representation and a pose. The method also includes determining multiple viewpoints relative to the geometric capsule and determining a first appearance representation of the geometric capsule for each of the multiple viewpoints. The method also includes determining a transform for each of the multiple viewpoints that moves each of the multiple viewpoints to a respective transformed viewpoint and determining second appearance representations that each correspond to one of the transformed viewpoints. The method also includes combining the second appearance representations to define an agreed appearance representation. The method also includes updating the feature representation for the geometric capsule based on the agreed appearance representation.
-
公开(公告)号：US20210090302A1
公开(公告)日：2021-03-25
申请号：US16836028
申请日：2020-03-31
Applicant: Apple Inc.
Inventor： Nitish Srivastava , Ruslan Salakhutdinov , Hanlin Goh
IPC: G06T9/00 , H04N13/111 , H04N13/161 , G06N3/04 , G06N3/08
Abstract: A method includes defining a geometric capsule that is interpretable by a capsule neural network, wherein the geometric capsule includes a feature representation and a pose. The method also includes determining multiple viewpoints relative to the geometric capsule and determining a first appearance representation of the geometric capsule for each of the multiple viewpoints. The method also includes determining a transform for each of the multiple viewpoints that moves each of the multiple viewpoints to a respective transformed viewpoint and determining second appearance representations that each correspond to one of the transformed viewpoints. The method also includes combining the second appearance representations to define an agreed appearance representation. The method also includes updating the feature representation for the geometric capsule based on the agreed appearance representation.
-
公开(公告)号：US10776948B1
公开(公告)日：2020-09-15
申请号：US16113647
申请日：2018-08-27
Applicant: Apple Inc.
Inventor： Emilio Parisotto , Jian Zhang , Ruslan Salakhutdinov , Devendra Singh Chaplot
Abstract: In accordance with some embodiments, a method is performed at a device with one or more processors and non-transitory memory. The method includes obtaining location vector data characterizing an object. The method includes determining a neural pose graph associated with a respective time-period based on an initial local pose estimation as a function of respective location vector data. The method includes determining a meta pose estimation associated with the respective time-period by aggregating the neural pose graph associated with the respective time-period and one or more other neural pose graphs associated with one or more temporally adjacent time-periods. The method includes synthesizing a corrected pose estimation by correcting the meta pose estimation associated with the respective time-period based on a function of the meta pose estimation associated with the respective time-period and meta pose estimations associated with one or more temporally adjacent time-periods in order to correct accumulated errors in the initial local pose estimation.
-
-
-
-
-
-
-
-
-
Search Results
12
records
(took 0.034 seconds)
