COOKIES: By using this website you agree that we can place Google Analytics Cookies on your device for performance monitoring. |
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 ApplicationsAdd 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. This talk is included in these lists:
Note that ex-directory lists are not shown. |
Other lists6th Annual Cambridge Technology Ventures Conference - June 11th Cambridge Science Festival DNA, Cells and Cancer- A Symposium to Honour Professor Ron LaskeyOther talksEmotional Health - Evening Talk as part of the 'Quality of Life' Series Signatures of planet formation and orbital evolution in the cold dust emission of protoplanetary discs Imaging & Mathematics Network Meeting - Michaelmas Stochastic Approach to Quantum Spin Dynamics TBC Empires of Acclimatisation (Domestication Practices across History) |