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 goal of continual learning (CL) is to learn different tasks over time.The main desiderata associated with CL are to maintain performance on oldertasks, leverage the latter to improve learning of future tasks, and tointroduce minimal overhead in the training process (for instance, to notrequire a growing model or retraining). We propose the Neuro-InspiredStability-Plasticity Adaptation (NISPA) architecture that addresses thesedesiderata through a sparse neural network with fixed density. NISPA formsstable paths to preserve learned knowledge from older tasks. Also, NISPA usesconnection rewiring to create new plastic paths that reuse existing knowledgeon novel tasks. Our extensive evaluation on EMNIST, FashionMNIST, CIFAR10, andCIFAR100 datasets shows that NISPA significantly outperforms representativestate-of-the-art continual learning baselines, and it uses up to ten timesfewer learnable parameters compared to baselines. We also make the case thatsparsity is an essential ingredient for continual learning. The NISPA code isavailable at https://github.com/BurakGurbuz97/NISPA.

NISPA: Neuro-Inspired Stability-Plasticity Adaptation for Continual Learning in Sparse Networks