Invention Grant
- Patent Title: Extending previously trained deep neural networks
-
Application No.: US15968694Application Date: 2018-05-01
-
Publication No.: US10559088B2Publication Date: 2020-02-11
- Inventor: Erich-Soren Finkelstein
- Applicant: Microsoft Technology Licensing, LLC
- Applicant Address: US WA Redmond
- Assignee: MICROSOFT TECHNOLOGY LICENSING, LLC
- Current Assignee: MICROSOFT TECHNOLOGY LICENSING, LLC
- Current Assignee Address: US WA Redmond
- Agency: Alleman Hall Creasman & Tuttle LLP
- Main IPC: G06T7/70
- IPC: G06T7/70 ; G06N3/04 ; G06K9/66 ; G06N3/08

Abstract:
Sensor data is provided to a deep neural network previously trained to detect a feature within the physical environment. Result signals are received from the neural network, and the computing system determines if the feature is present within the physical environment based on the result signals. Responsive to determining that the feature is present, the computing system implements a function of a rule assigned to the feature. Responsive to determining that the feature is not present, the computing system determines whether one or more activation parameters of the neural network have been met indicative of an alternative feature being present within the physical environment. An indication that the activation parameters have been met is output by the computing system, enabling the rule to be extended to the alternative feature.
Public/Granted literature
- US20190340779A1 EXTENDING PREVIOUSLY TRAINED DEEP NEURAL NETWORKS Public/Granted day:2019-11-07
Information query