Abstract
A machine learning system is described that enables an embedded and/or low-power device to locally train machine learning models using data collected by sensors of the device. When the device is being used by a user and operating on battery power (e.g., during the day), one or more sensors of the device may collect data. When the device is not being used by the user and is charging (e.g., at night), the device may use the collected data to train one or more machine learning models used by the device. In this way, the device may locally train machine learning models without degrading a user experience.
Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 License.
Recommended Citation
Freeman, Tyler, "EFFICIENT TRAINING FOR MACHINE LEARNING MODELS ON EMBEDDED AND/OR LOW-POWER DEVICES", Technical Disclosure Commons, (June 05, 2017)
https://www.tdcommons.org/dpubs_series/542