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

Leveraging the symmetries inherent to specific data domains for theconstruction of equivariant neural networks has lead to remarkable improvementsin terms of data efficiency and generalization. However, most existing researchfocuses on symmetries arising from planar and volumetric data, leaving acrucial data source largely underexplored: time-series. In this work, we fillthis gap by leveraging the symmetries inherent to time-series for theconstruction of equivariant neural network. We identify two core symmetries:*scale and translation*, and construct scale-translation equivariant neuralnetworks for time-series learning. Intriguingly, we find that scale-translationequivariant mappings share strong resemblance with the wavelet transform.Inspired by this resemblance, we term our networks Wavelet Networks, and showthat they perform nested non-linear wavelet-like time-frequency transforms.Empirical results show that Wavelet Networks outperform conventional CNNs onraw waveforms, and match strongly engineered spectrogram techniques acrossseveral tasks and time-series types, including audio, environmental sounds, andelectrical signals. Our code is publicly available athttps://github.com/dwromero/wavelet_networks.

Wavelet Networks: Scale-Translation Equivariant Learning From Raw Time-Series