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

Continual Learning (CL) is a process in which there is still huge gap betweenhuman and deep learning model efficiency. Recently, many CL algorithms weredesigned. Most of them have many problems with learning in dynamic and complexenvironments. In this work new architecture based approach Ada-QPacknet isdescribed. It incorporates the pruning for extracting the sub-network for eachtask. The crucial aspect in architecture based CL methods is theirs capacity.In presented method the size of the model is reduced by efficient linear andnonlinear quantisation approach. The method reduces the bit-width of theweights format. The presented results shows that low bit quantisation achievessimilar accuracy as floating-point sub-network on a well-know CL scenarios. Toour knowledge it is the first CL strategy which incorporates both compressiontechniques pruning and quantisation for generating task sub-networks. Thepresented algorithm was tested on well-known episode combinations and comparedwith most popular algorithms. Results show that proposed approach outperformsmost of the CL strategies in task and class incremental scenarios.

Ada-QPacknet -- adaptive pruning with bit width reduction as an efficient continual learning method without forgetting