Tuning layers of a modular neural network

US11352014B1 · kind B1 · utility

Assignee

• Samsara Inc. · US

Inventors

• Sharan Srinivasan · San Francisco, US
• Brian Tuan · Cupertino, US
• John Bicket · San Francisco, US
• Jing Wang · Fremont, US
• Muhammad Ali Akhtar · Oakland, US
• Abner Ayala Acevedo · Orlando, US
• Bruce Kellerman · Atlanta, US
• Vincent Shieh · San Francisco, US

Key dates

• Filing date: Nov 12, 2021
• Grant date: Jun 7, 2022
• Expiry date: Nov 12, 2041

Classification

• Technology area (CPC B): Performing Operations; Transporting
• CPC primary: B60W2400/00
• WIPO field: Computer technology
• WIPO sector: Electrical engineering

Abstract

A vehicle device may execute one or more neural networks (and/or other artificial intelligence), based on input from one or more of the cameras and/or other sensors, to intelligently detect safety events in real-time. The one or more neural networks may be an ensemble neural network that includes neural networks for detecting a head and hand of a user, neural networks for detecting hand actions of the user, neural networks for detecting the head pose of the user, neural networks for predicting an occurrence of an event, and neural networks for predicting a start time and end time of the event. Further, the neural networks can be segmented into a modular neural network based on metadata. The segmentation of the neural network can define a thin layer of the modular neural network to enable independent tuning of the thin layer of the modular neural network.