English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Deploying sophisticated deep learning models on embedded devices with thepurpose of solving real-world problems is a struggle using today's technology.Privacy and data limitations, network connection issues, and the need for fastmodel adaptation are some of the challenges that constitute today's approachesunfit for many applications on the edge and make real-time on-device training anecessity. Google is currently working on tackling these challenges byembedding an experimental transfer learning API to their TensorFlow Lite,machine learning library. In this paper, we show that although transferlearning is a good first step for on-device model training, it suffers fromcatastrophic forgetting when faced with more realistic scenarios. We presentthis issue by testing a simple transfer learning model on the CORe50 benchmarkas well as by demonstrating its limitations directly on an Android applicationwe developed. In addition, we expand the TensorFlow Lite library to includecontinual learning capabilities, by integrating a simple replay approach intothe head of the current transfer learning model. We test our continual learningmodel on the CORe50 benchmark to show that it tackles catastrophic forgetting,and we demonstrate its ability to continually learn, even under non-idealconditions, using the application we developed. Finally, we open-source thecode of our Android application to enable developers to integrate continuallearning to their own smartphone applications, as well as to facilitate furtherdevelopment of continual learning functionality into the TensorFlow Liteenvironment.

Continual Learning on the Edge with TensorFlow Lite