公开(公告)号：US12135837B2

公开(公告)日：2024-11-05

申请号：US18355659

申请日：2023-07-20

Applicant: Apple Inc.

Inventor： Erdrin Azemi ,  Joseph Yitan Cheng ,  Hanlin Goh

IPC: G06F3/01 ,  G06N3/04 ,  G06N20/00

Abstract: Techniques are disclosed for defining a training data set to include biosignals and categorical labels representative of a context. For example, a categorical label may indicate whether a user was performing a difficult or easy mental task while the biosignal was being recorded. A set of first layers in a neural network can be trained using a portion of the training data set associated with a first set of users and at least one second layer can be trained using a portion of the training data set associated with a particular other user. The neural network can then be used to process other biosignals from the particular other user to generate predicted categorical context labels.

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

IPC: G06N3/08 ,  G06N5/04 ,  G06T1/00 ,  G06K9/00

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：US11747902B2

公开(公告)日：2023-09-05

申请号：US17174875

申请日：2021-02-12

Applicant: Apple Inc.

Inventor： Erdrin Azemi ,  Joseph Yitan Cheng ,  Hanlin Goh

IPC: G06F3/01 ,  G06N3/04 ,  G06N20/00

CPC classification number: G06F3/015 ,  G06N3/04 ,  G06N20/00

Abstract: Techniques are disclosed for defining a training data set to include biosignals and categorical labels representative of a context. For example, a categorical label may indicate whether a user was performing a difficult or easy mental task while the biosignal was being recorded. A set of first layers in a neural network can be trained using a portion of the training data set associated with a first set of users and at least one second layer can be trained using a portion of the training data set associated with a particular other user. The neural network can then be used to process other biosignals from the particular other user to generate predicted categorical context labels.

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：US20210374570A1

公开(公告)日：2021-12-02

申请号：US17326098

申请日：2021-05-20

Applicant: Apple Inc.

Inventor： Joseph Y. Cheng ,  Erdrin Azemi ,  Hanlin Goh ,  Kaan E. Dogrusoz ,  Cuneyt O. Tuzel

IPC: G06N5/04 ,  G06N20/00

Abstract: The present application relates to apparatus, systems, and methods to perform subject-aware self-supervised learning of a machine-learning model for classification of data, such as classification of biosignals.

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：US12271791B2

公开(公告)日：2025-04-08

申请号：US17308033

申请日：2021-05-04

Applicant: Apple Inc.

Inventor： Shuangfei Zhai ,  Walter A. Talbott ,  Nitish Srivastava ,  Chen Huang ,  Hanlin Goh ,  Joshua M. Susskind

IPC: G06N20/00 ,  G06F17/16 ,  G06F40/58 ,  G06N5/04 ,  G06T3/4053

Abstract: Attention-free transformers are disclosed. Various implementations of attention-free transformers include a gating and pooling operation that allows the attention-free transformers to provide comparable or better results to those of a standard attention-based transformer, with improved efficiency and reduced computational complexity with respect to space and time.

公开(公告)号：US20240331207A1

公开(公告)日：2024-10-03

申请号：US18738488

申请日：2024-06-10

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 receiving three-dimensional geometric elements as an input. The method also includes initializing geometric capsules by assigning one of the three-dimensional geometric elements to each of the geometric capsules and setting initial values for a pose component and a feature component of each of the geometric capsules. The method also includes one or more iterations of a routing procedure that includes assigning an additional one of the three-dimensional geometric elements to a respective one of the geometric capsules, based on correspondence of the additional one of the three-dimensional geometric elements to a surface defined based on the feature component of the respective one of the geometric capsules, and updating the feature component of each of the geometric capsules based on the three-dimensional geometric elements assigned to each of the geometric capsules. The method also includes outputting the geometric capsules including encoded three-dimensional data.

公开(公告)号：US20240012480A1

公开(公告)日：2024-01-11

申请号：US18355659

申请日：2023-07-20

Applicant: Apple Inc.

Inventor： Erdrin Azemi ,  Joseph Yitan Cheng ,  Hanlin Goh

IPC: G06F3/01 ,  G06N3/04 ,  G06N20/00

CPC classification number: G06F3/015 ,  G06N3/04 ,  G06N20/00

Abstract: Techniques are disclosed for defining a training data set to include biosignals and categorical labels representative of a context. For example, a categorical label may indicate whether a user was performing a difficult or easy mental task while the biosignal was being recorded. A set of first layers in a neural network can be trained using a portion of the training data set associated with a first set of users and at least one second layer can be trained using a portion of the training data set associated with a particular other user. The neural network can then be used to process other biosignals from the particular other user to generate predicted categorical context labels.

公开(公告)号：US20210286429A1

公开(公告)日：2021-09-16

申请号：US17174875

申请日：2021-02-12

Applicant: Apple Inc.

Inventor： Erdrin Azemi ,  Joseph Yitan Cheng ,  Hanlin Goh

IPC: G06F3/01 ,  G06N20/00 ,  G06N3/04

Abstract: Techniques are disclosed for defining a training data set to include biosignals and categorical labels representative of a context. For example, a categorical label may indicate whether a user was performing a difficult or easy mental task while the biosignal was being recorded. A set of first layers in a neural network can be trained using a portion of the training data set associated with a first set of users and at least one second layer can be trained using a portion of the training data set associated with a particular other user. The neural network can then be used to process other biosignals from the particular other user to generate predicted categorical context labels.