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

Recurrent neural networks are a powerful means in diverse applications. Weshow that, together with so-called conceptors, they also allow fast learning,in contrast to other deep learning methods. In addition, a relatively smallnumber of examples suffices to train neural networks with high accuracy. Wedemonstrate this with two applications, namely speech recognition and detectingcar driving maneuvers. We improve the state of the art by application-specificpreparation techniques: For speech recognition, we use mel frequency cepstralcoefficients leading to a compact representation of the frequency spectra, anddetecting car driving maneuvers can be done without the commonly usedpolynomial interpolation, as our evaluation suggests.

Fast Classification Learning with Neural Networks and Conceptors for Speech Recognition and Car Driving Maneuvers