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

In the quest for efficient neural network models for neural datainterpretation and user intent classification in brain-computer interfaces(BCIs), learning meaningful sparse representations of the underlying neuralsubspaces is crucial. The present study introduces a sparse multitask learningframework for motor imagery (MI) and motor execution (ME) tasks, inspired bythe natural partitioning of associated neural subspaces observed in the humanbrain. Given a dual-task CNN model for MI-ME classification, we apply asaliency-based sparsification approach to prune superfluous connections andreinforce those that show high importance in both tasks. Through our approach,we seek to elucidate the distinct and common neural ensembles associated witheach task, employing principled sparsification techniques to eliminateredundant connections and boost the fidelity of neural signal decoding. Ourresults indicate that this tailored sparsity can mitigate the overfittingproblem and improve the test performance with small amount of data, suggestinga viable path forward for computationally efficient and robust BCI systems.

Sparse Multitask Learning for Efficient Neural Representation of Motor Imagery and Execution