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 study the effect of various transfer functions on the properties of a timeseries generated by a continuous-valued feed-forward network in which the nextinput vector is determined from past output values. The parameter space formonotonic and non-monotonic transfer functions is analyzed in the unstableregions with the following main finding; non-monotonic functions can producerobust chaos whereas monotonic functions generate fragile chaos only. In thecase of non-monotonic functions, the number of positive Lyapunov exponentsincreases as a function of one of the free parameters in the model, hence, highdimensional chaotic attractors can be generated. We extend the analysis to acombination of monotonic and non-monotonic functions.

Long-term properties of time series generated by a perceptron with various transfer functions