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

Task specific hyperparameter tuning in reservoir computing is an open issue,and is of particular relevance for hardware implemented reservoirs. Weinvestigate the influence of directly including externally controllable taskspecific timescales on the performance and hyperparameter sensitivity ofreservoir computing approaches. We show that the need for hyperparameteroptimisation can be reduced if timescales of the reservoir are tailored to thespecific task. Our results are mainly relevant for temporal tasks requiringmemory of past inputs, for example chaotic timeseries prediciton. We considervarious methods of including task specific timescales in the reservoircomputing approach and demonstrate the universality of our message by lookingat both time-multiplexed and spatially multiplexed reservoir computing.

Reducing hyperparameter dependence by external timescale tailoring