Using a generic classifier to train a personalized classifier for wearable devices

Abstract

Systems and methods may provide for using one or more generic classifiers to generate self-training data based on a first plurality of events associated with a device, and training a personal classifier based on the self-training data. Additionally, the one or more generic classifiers and the personal classifier to may be used to generate validation data based on a second plurality of events associated with the device. In one example, the personal classifier is substituted for the one or more generic classifiers if the validation data indicates that the personal classifier satisfies a confidence condition relative to the one or more generic classifiers.

We claim: 
     
         1 . A wearable device comprising:
 a battery to power the wearable device;   a user interface to detect a first plurality of events during a self-training stage of the wearable device and a second plurality of events during a validation stage of the wearable device;   one or more generic classifiers to generate self-training data based on the first plurality of events;   a personal classifier, wherein the one or more generic classifiers and the personal classifier are to generate validation data based on the second plurality of events; and   a validator coupled to the one or more generic classifiers and the personal classifier, the validator to substitute the personal classifier for the one or more generic classifiers if the validation data indicates that the personal classifier satisfies a confidence condition relative to the one or more generic classifiers.