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

Recurrent Neural Networks (RNNs) are among the most successful machinelearning models for sequence modelling, but tend to suffer from an exponentialincrease in the number of parameters when dealing with large multidimensionaldata. To this end, we develop a multi-linear graph filter framework forapproximating the modelling of hidden states in RNNs, which is embedded in atensor network architecture to improve modelling power and reduce parametercomplexity, resulting in a novel Recurrent Graph Tensor Network (RGTN). Theproposed framework is validated through several multi-way sequence modellingtasks and benchmarked against traditional RNNs. By virtue of the domain awareinformation processing of graph filters and the expressive power of tensornetworks, we show that the proposed RGTN is capable of not only out-performingstandard RNNs, but also mitigating the Curse of Dimensionality associated withtraditional RNNs, demonstrating superior properties in terms of performance andcomplexity.

Recurrent Graph Tensor Networks: A Low-Complexity Framework for Modelling High-Dimensional Multi-Way Sequence