-
公开(公告)号：US20230124380A1
公开(公告)日：2023-04-20
申请号：US18082476
申请日：2022-12-15
Applicant: Apple Inc.
Inventor： Moises Goldszmidt , Anatoly D. Adamov , Juan C. Garcia , Julia R. Reisler , Timothy S. Paek , Vishwas Kulkarni , Yu-Chung Hsiao , Pavan Chitta
IPC: G06N20/00 , G06F18/214 , G06F18/21 , G06F18/2415
Abstract: Systems and methods are disclosed for triggering an update to a machine-learning model upon detecting that a distribution of particular (e.g., recently collected) input data set is sufficiently different from a distribution training input data set used to train the model. The distributions may be determined to be sufficiently different when a classifier can identify to which distribution individual data elements belong (e.g., to at least a predetermined degree). An update to the machine-learning model can include morphing weights used by the model and/or retraining the model.
-
公开(公告)号：US11175898B2
公开(公告)日：2021-11-16
申请号：US16583191
申请日：2019-09-25
Applicant: Apple Inc.
Inventor： Timothy S. Paek , Francesco Rossi , Jamil Dhanani , Keith P. Avery , Minwoo Jeong , Xiaojin Shi , Harveen Kaur , Brandt M. Westing
Abstract: The subject technology receives a neural network model in a model format, the model format including information for a set of layers of the neural network model, each layer of the set of layers including a set of respective operations. The subject technology generates neural network (NN) code from the neural network model, the NN code being in a programming language distinct from the model format, and the NN code comprising a respective memory allocation for each respective layer of the set of layers of the neural network model, where the generating comprises determining the respective memory allocation for each respective layer based at least in part on a resource constraint of a target device. The subject technology compiles the NN code into a binary format. The subject technology generates a package for deploying the compiled NN code on the target device.
-
公开(公告)号：US20210224687A1
公开(公告)日：2021-07-22
申请号：US16875825
申请日：2020-05-15
Applicant: Apple Inc.
Inventor： Moises Goldszmidt , Anatoly D. Adamov , Juan C. Garcia , Julia R. Reisler , Timothy S. Paek , Vishwas Kulkarni , Yu-Chung Hsiao , Pavan Chitta
Abstract: Systems and methods are disclosed for triggering an update to a machine-learning model upon detecting that a distribution of particular (e.g., recently collected) input data set is sufficiently different from a distribution training input data set used to train the model. The distributions may be determined to be sufficiently different when a classifier can identify to which distribution individual data elements belong (e.g., to at least a predetermined degree). An update to the machine-learning model can include morphing weights used by the model and/or retraining the model.
-
公开(公告)号：US11704592B2
公开(公告)日：2023-07-18
申请号：US16937479
申请日：2020-07-23
Applicant: Apple Inc.
Inventor： Keith P. Avery , Jamil Dhanani , Harveen Kaur , Varun Maudgalya , Timothy S. Paek , Dmytro Rudchenko , Brandt M. Westing , Minwoo Jeong
IPC: G06F3/0488 , G06F3/01 , G06F3/0481 , G06N20/00 , G06F3/04883 , H04R3/04 , G06N3/08
CPC classification number: G06N20/00 , G06F3/011 , G06F3/017 , G06F3/04883 , H04R3/04 , G06N3/08 , H04R2430/01
Abstract: The subject technology receives, from a first sensor of a device, first sensor output of a first type. The subject technology receives, from a second sensor of the device, second sensor output of a second type, the first and second sensors being non-touch sensors. The subject technology provides the first sensor output and the second sensor output as inputs to a machine learning model, the machine learning model having been trained to output a predicted touch-based gesture based on sensor output of the first type and sensor output of the second type. The subject technology provides a predicted touch-based gesture based on output from the machine learning model. Further, the subject technology adjusts an audio output level of the device based on the predicted gesture, and where the device is an audio output device.
-
公开(公告)号：US20240361975A1
公开(公告)日：2024-10-31
申请号：US18605390
申请日：2024-03-14
Applicant: Apple Inc.
Inventor： Mary-Ann Rau , Reza Azimi , Kevin Durfee , Aaron A. Jaech , Wasifa Jamal , Viet Huy Le , Timothy S. Paek , Pablo D. Brazell , Blanca Isabel C. Villanueva , Lucas O. Winstrom , Chirag Nanavati , Sanket S. Dave , Deepak Iyer , Hilary K. Mogul , Edward T. Davies , Vladan Bajic , Jianjun He
Abstract: A method that includes playing back audio content through a speaker of the headset at a volume setting; receiving a microphone signal that includes noise of an acoustic environment captured by a microphone of the headset; detecting a change to an environmental noise level of the noise based on the microphone signal; retrieving, from memory of the headset, an adapted volume setting to the changed environmental noise level, wherein the adapted volume setting is generated at least in part based on user context or user behavior; and adjusting playback of the audio content by transitioning the volume setting to the adapted volume setting.
-
Patent Agency Ranking
公开(公告)号：US20240338612A1
公开(公告)日：2024-10-10
申请号：US18745654
申请日：2024-06-17
Applicant: Apple Inc.
Inventor： Moises Goldszmidt , Anatoly D. Adamov , Juan C. Garcia , Julia R. Reisler , Timothy S. Paek , Vishwas Kulkarni , Yu-Chung Hsiao , Pavan Chitta
IPC: G06N20/20 , G06F18/21 , G06F18/214 , G06F18/2415 , G06N20/00
CPC classification number: G06N20/20 , G06F18/214 , G06F18/217 , G06F18/2415 , G06N20/00
Abstract: Systems and methods are disclosed for triggering an update to a machine-learning model upon detecting that a distribution of particular (e.g., recently collected) input data set is sufficiently different from a distribution training input data set used to train the model. The distributions may be determined to be sufficiently different when a classifier can identify to which distribution individual data elements belong (e.g., to at least a predetermined degree). An update to the machine-learning model can include morphing weights used by the model and/or retraining the model.
-
公开(公告)号：US11595517B2
公开(公告)日：2023-02-28
申请号：US17395322
申请日：2021-08-05
Applicant: Apple Inc.
Inventor： Madhusudan Chinthakunta , Ping Wen Ong , Timothy S. Paek , Lauren Elise Tappana , Marcel Van Os
IPC: H04M3/42
Abstract: Systems and processes for integrating a digital assistant with telephony are provided. For example, an incoming call may be received, from a caller, at an electronic device. A communication session may be established between the caller and the digital assistant of the electronic device. In accordance with a determination that the identification of the caller is unknown, determination is made whether the caller corresponds to an automated calling system. In accordance with a determination that the identification of the caller is known, a response is provided by the digital assistant to the caller. An output including information corresponding to the communication is provided at the electronic device.
-
公开(公告)号：US11562297B2
公开(公告)日：2023-01-24
申请号：US16875825
申请日：2020-05-15
Applicant: Apple Inc.
Inventor： Moises Goldszmidt , Anatoly D. Adamov , Juan C. Garcia , Julia R. Reisler , Timothy S. Paek , Vishwas Kulkarni , Yu-Chung Hsiao , Pavan Chitta
Abstract: Systems and methods are disclosed for triggering an update to a machine-learning model upon detecting that a distribution of particular (e.g., recently collected) input data set is sufficiently different from a distribution training input data set used to train the model. The distributions may be determined to be sufficiently different when a classifier can identify to which distribution individual data elements belong (e.g., to at least a predetermined degree). An update to the machine-learning model can include morphing weights used by the model and/or retraining the model.
-
公开(公告)号：US12020133B2
公开(公告)日：2024-06-25
申请号：US18082476
申请日：2022-12-15
Applicant: Apple Inc.
Inventor： Moises Goldszmidt , Anatoly D. Adamov , Juan C. Garcia , Julia R. Reisler , Timothy S. Paek , Vishwas Kulkarni , Yu-Chung Hsiao , Pavan Chitta
IPC: G06N20/20 , G06F18/21 , G06F18/214 , G06F18/2415 , G06N20/00
CPC classification number: G06N20/20 , G06F18/214 , G06F18/217 , G06F18/2415 , G06N20/00
Abstract: Systems and methods are disclosed for triggering an update to a machine-learning model upon detecting that a distribution of particular (e.g., recently collected) input data set is sufficiently different from a distribution training input data set used to train the model. The distributions may be determined to be sufficiently different when a classifier can identify to which distribution individual data elements belong (e.g., to at least a predetermined degree). An update to the machine-learning model can include morphing weights used by the model and/or retraining the model.
-
公开(公告)号：US11416136B2
公开(公告)日：2022-08-16
申请号：US17167896
申请日：2021-02-04
Applicant: Apple Inc.
Inventor： John M. Nefulda , Keith P. Avery , Madhu Chinthakunta , Christopher B. Fleizach , Varun Maudgalya , Sommer E. Panage , Xinyi Yan , Garrett L. Weinberg , Michal K. Wegrzynski , William Caruso , Kenneth S. Friedman , Jamil Dhanani , Muhammad Amir Shafiq , Minwoo Jeong , Timothy S. Paek , Viet Huy Le , Heriberto Nieto , Brandt M. Westing , Rishabh Yadav
IPC: G06F3/048 , G06F3/04847 , H04M1/72466 , G06F3/0482 , G06F3/01
Abstract: The present disclosure generally relates to assigning tasks to various user inputs, and detecting and responding to user inputs. In some embodiments, the present disclosure relates to assigning tasks to various user inputs received on a back surface of a device, and detecting and responding to user inputs on the back surface of the device.
-
-
-
-
-
-
-
-
-
Search Results
10
records
(took 0.018 seconds)
