公开(公告)号：US20240211805A1

公开(公告)日：2024-06-27

申请号：US18378068

申请日：2023-10-09

Applicant: APPLE INC.

Inventor： Michael R. Siracusa ,  Alexander B. Brown ,  Dheeraj Goswami ,  Nathan C. Wertman ,  Jacob T. Sawyer ,  Donald M. Firlik

IPC: G06N20/00 ,  G06F3/048 ,  G06F3/0486 ,  G06F8/34 ,  G06F18/21 ,  G06F18/214 ,  G06F18/2431 ,  G06V10/776

CPC classification number: G06N20/00 ,  G06F3/048 ,  G06F3/0486 ,  G06F8/34 ,  G06F18/2148 ,  G06F18/2193 ,  G06F18/2431 ,  G06V10/776

Abstract: Embodiments of the present disclosure present devices, methods, and computer readable medium for techniques for creating machine learning models. Application developers can select a machine learning template from a plurality of templates appropriate for the type of data used in their application. Templates can include multiple templates for classification of images, text, sound, motion, and tabular data. A graphical user interface allows for intuitive selection of training data, validation data, and integration of the trained model into the application. The techniques further display a numerical score for both the training accuracy and validation accuracy using the test data. The application provides a live mode that allows for execution of the machine learning model on a mobile device to allow for testing the model from data from one or more of the sensors (i.e., camera or microphone) on the mobile device.

公开(公告)号：US11783223B2

公开(公告)日：2023-10-10

申请号：US16670914

申请日：2019-10-31

Applicant: Apple Inc.

Inventor： Michael R. Siracusa ,  Alexander B. Brown ,  Dheeraj Goswami ,  Nathan C. Wertman ,  Jacob T. Sawyer ,  Donald M. Firlik

IPC: G06F3/048 ,  G06N20/00 ,  G06F3/0486 ,  G06F8/34 ,  G06F18/214 ,  G06F18/21 ,  G06F18/2431 ,  G06V10/776

CPC classification number: G06N20/00 ,  G06F3/048 ,  G06F3/0486 ,  G06F8/34 ,  G06F18/2148 ,  G06F18/2193 ,  G06F18/2431 ,  G06V10/776

Abstract: Embodiments of the present disclosure present devices, methods, and computer readable medium for techniques for creating machine learning models. Application developers can select a machine learning template from a plurality of templates appropriate for the type of data used in their application. Templates can include multiple templates for classification of images, text, sound, motion, and tabular data. A graphical user interface allows for intuitive selection of training data, validation data, and integration of the trained model into the application. The techniques further display a numerical score for both the training accuracy and validation accuracy using the test data. The application provides a live mode that allows for execution of the machine learning model on a mobile device to allow for testing the model from data from one or more of the sensors (i.e., camera or microphone) on the mobile device.

公开(公告)号：US20200380301A1

公开(公告)日：2020-12-03

申请号：US16670914

申请日：2019-10-31

Applicant: Apple Inc.

Inventor： Michael R. Siracusa ,  Alexander B. Brown ,  Dheeraj Goswami ,  Nathan C. Wertman ,  Jacob T. Sawyer ,  Donald M. Firlik

IPC: G06K9/62 ,  G06N20/00 ,  G06F8/34 ,  G06F3/0486

Abstract: Embodiments of the present disclosure present devices, methods, and computer readable medium for techniques for creating machine learning models. Application developers can select a machine learning template from a plurality of templates appropriate for the type of data used in their application. Templates can include multiple templates for classification of images, text, sound, motion, and tabular data. A graphical user interface allows for intuitive selection of training data, validation data, and integration of the trained model into the application. The techniques further display a numerical score for both the training accuracy and validation accuracy using the test data. The application provides a live mode that allows for execution of the machine learning model on a mobile device to allow for testing the model from data from one or more of the sensors (i.e., camera or microphone) on the mobile device.