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

Although the pre-training followed by fine-tuning paradigm is usedextensively in many fields, there is still some controversy surrounding theimpact of pre-training on the fine-tuning process. Currently, experimentalfindings based on text and image data lack consensus. To delve deeper into theunsupervised pre-training followed by fine-tuning paradigm, we have extendedprevious research to a new modality: time series. In this study, we conducted athorough examination of 150 classification datasets derived from the UnivariateTime Series (UTS) and Multivariate Time Series (MTS) benchmarks. Our analysisreveals several key conclusions. (i) Pre-training can only help improve theoptimization process for models that fit the data poorly, rather than thosethat fit the data well. (ii) Pre-training does not exhibit the effect ofregularization when given sufficient training time. (iii) Pre-training can onlyspeed up convergence if the model has sufficient ability to fit the data. (iv)Adding more pre-training data does not improve generalization, but it canstrengthen the advantage of pre-training on the original data volume, such asfaster convergence. (v) While both the pre-training task and the modelstructure determine the effectiveness of the paradigm on a given dataset, themodel structure plays a more significant role.

Examining the Effect of Pre-training on Time Series Classification