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 Tools annual

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 monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

With the ever-increasing number of pretrained models, machine learningpractitioners are continuously faced with which pretrained model to use, andhow to finetune it for a new dataset. In this paper, we propose a methodologythat jointly searches for the optimal pretrained model and the hyperparametersfor finetuning it. Our method transfers knowledge about the performance of manypretrained models with multiple hyperparameter configurations on a series ofdatasets. To this aim, we evaluated over 20k hyperparameter configurations forfinetuning 24 pretrained image classification models on 87 datasets to generatea large-scale meta-dataset. We meta-learn a multi-fidelity performancepredictor on the learning curves of this meta-dataset and use it for fasthyperparameter optimization on new datasets. We empirically demonstrate thatour resulting approach can quickly select an accurate pretrained model for anew dataset together with its optimal hyperparameters.

Quick-Tune: Quickly Learning Which Pretrained Model to Finetune and How