University of Cambridge > Talks.cam > Computer Laboratory NetOS Group Talklets > An Empirical Study of Lifelong Learning on Mobile Applications

An Empirical Study of Lifelong Learning on Mobile Applications

Add to your list(s) Download to your calendar using vCal

If you have a question about this talk, please contact Seyyed Ahmad Javadi.

Deep neural networks achieve state-of-the-art performances on sensor data generated by a wide variety of mobile applications. However, the capability of deep learning models to perform lifelong learning (continual learning), that is, to learn new inputs (new tasks or classes) continuously, is often impaired by catastrophic forgetting, i.e., a model forgets previously learned knowledge when learning new tasks. This can be very detrimental in ubiquitous computing, where a deployed model needs to accommodate new sensor inputs and changing environments continuously. Several techniques have been proposed to solve catastrophic forgetting, but their performance has not been fully examined in mobile sensing applications. In this talk, for the first time, we systematically study the performance of three predominant lifelong learning schemes (i.e., regularization, replay and replay with examples) on mobile sensing applications of human activity recognition and gesture recognition. With scenarios consisting of different learning complexity, as encountered in practice, we investigate the generalizability, trade-offs between the performance, storage, and latency of different lifelong learning methods on mobile sensing applications. Finally, we summarize our results into a series of lessons that can guide practitioners in their use of lifelong deep learning for mobile applications.

This talk is part of the Computer Laboratory NetOS Group Talklets series.

Tell a friend about this talk:

This talk is included in these lists:

Note that ex-directory lists are not shown.

 

© 2006-2019 Talks.cam, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity