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 Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

We describe a new technique which minimizes the amount of neurons in thehidden layer of a random recurrent neural network (rRNN) for time seriesprediction. Merging Takens-based attractor reconstruction methods with machinelearning, we identify a mechanism for feature extraction that can be leveragedto lower the network size. We obtain criteria specific to the particularprediction task and derive the scaling law of the prediction error. Theconsequences of our theory are demonstrated by designing a Takens-inspiredhybrid processor, which extends a rRNN with a priori designed delay externalmemory. Our hybrid architecture is therefore designed including both, real andvirtual nodes. Via this symbiosis, we show performance of the hybrid processorby stabilizing an arrhythmic neural model. Thanks to our obtained design rules,we can reduce the stabilizing neural network's size by a factor of 15 withrespect to a standard system.

Takens-inspired neuromorphic processor: a downsizing tool for random recurrent neural networks via feature extraction