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

Traditional Recurrent Neural Network (RNN) architectures, such as LSTM andGRU, have historically held prominence in time series tasks. However, they haverecently seen a decline in their dominant position across various time seriestasks. As a result, recent advancements in time series forecasting have seen anotable shift away from RNNs towards alternative architectures such asTransformers, MLPs, and CNNs. To go beyond the limitations of traditional RNNs,we design an efficient RNN-based model for time series tasks, named RWKV-TS,with three distinctive features: (i) A novel RNN architecture characterized by$O(L)$ time complexity and memory usage. (ii) An enhanced ability to capturelong-term sequence information compared to traditional RNNs. (iii) Highcomputational efficiency coupled with the capacity to scale up effectively.Through extensive experimentation, our proposed RWKV-TS model demonstratescompetitive performance when compared to state-of-the-art Transformer-based orCNN-based models. Notably, RWKV-TS exhibits not only comparable performance butalso demonstrates reduced latency and memory utilization. The success ofRWKV-TS encourages further exploration and innovation in leveraging RNN-basedapproaches within the domain of Time Series. The combination of competitiveperformance, low latency, and efficient memory usage positions RWKV-TS as apromising avenue for future research in time series tasks. Code is availableat:\href{https://github.com/howard-hou/RWKV-TS}{https://github.com/howard-hou/RWKV-TS}

RWKV-TS: Beyond Traditional Recurrent Neural Network for Time Series Tasks