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

The continuous changes in the world have resulted in the performanceregression of neural networks. Therefore, continual learning (CL) areagradually attracts the attention of more researchers. For edge intelligence,the CL model not only needs to overcome catastrophic for-getting, but alsoneeds to face the huge challenge of severely limited resources: the lack oflabeled resources and powerful devices. However, the existing classic CLmethods usually rely on a large number of labeled samples to maintain theplasticity and stability, and the semi-supervised learning methods often needto pay a large computational and memory overhead for higher accuracy. Inresponse to these prob-lems, a low-cost semi-supervised CL method named EdgeHierarchical Memory Learner (EdgeHML) will be proposed. EdgeHML caneffec-tively utilize a large number of unlabeled samples and a small number oflabeled samples. It is based on a hierarchical memory pool, lever-agemulti-level storage structure to store and replay samples. EdgeHML implementsthe interaction between different levels through a combination of online andoffline strategies. In addition, in order to further reduce the computationaloverhead for unlabeled samples, EdgeHML leverages a progressive learningmethod. It reduces the computation cycles of unlabeled samples by controllingthe learning process. The experimental results show that on threesemi-supervised CL tasks, EdgeHML can improve the model accuracy by up to16.35% compared with the classic CL method, and the training iterations timecan be reduced by more than 50% compared with semi-supervised methods. EdgeHMLachieves a semi-supervised CL process with high performance and low overheadfor edge intelligence.

Hierarchical Memory Pool Based Edge Semi-Supervised Continual Learning Method