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

Various incremental learning (IL) approaches have been proposed to help deeplearning models learn new tasks/classes continuously without forgetting whatwas learned previously (i.e., avoid catastrophic forgetting). With the growingnumber of deployed audio sensing applications that need to dynamicallyincorporate new tasks and changing input distribution from users, the abilityof IL on-device becomes essential for both efficiency and user privacy.  However, prior works suffer from high computational costs and storage demandswhich hinders the deployment of IL on-device. In this work, to overcome theselimitations, we develop an end-to-end and on-device IL framework, FastICARL,that incorporates an exemplar-based IL and quantization in the context ofaudio-based applications. We first employ k-nearest-neighbor to reduce thelatency of IL. Then, we jointly utilize a quantization technique to decreasethe storage requirements of IL. We implement FastICARL on two types of mobiledevices and demonstrate that FastICARL remarkably decreases the IL time up to78-92% and the storage requirements by 2-4 times without sacrificing itsperformance. FastICARL enables complete on-device IL, ensuring user privacy asthe user data does not need to leave the device.

FastICARL: Fast Incremental Classifier and Representation Learning with Efficient Budget Allocation in Audio Sensing Applications