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

The automated machine learning (AutoML) field has become increasinglyrelevant in recent years. These algorithms can develop models without the needfor expert knowledge, facilitating the application of machine learningtechniques in the industry. Neural Architecture Search (NAS) exploits deeplearning techniques to autonomously produce neural network architectures whoseresults rival the state-of-the-art models hand-crafted by AI experts. However,this approach requires significant computational resources and hardwareinvestments, making it less appealing for real-usage applications. This articlepresents the third version of Pareto-Optimal Progressive Neural ArchitectureSearch (POPNASv3), a new sequential model-based optimization NAS algorithmtargeting different hardware environments and multiple classification tasks.Our method is able to find competitive architectures within large searchspaces, while keeping a flexible structure and data processing pipeline toadapt to different tasks. The algorithm employs Pareto optimality to reduce thenumber of architectures sampled during the search, drastically improving thetime efficiency without loss in accuracy. The experiments performed on imagesand time series classification datasets provide evidence that POPNASv3 canexplore a large set of assorted operators and converge to optimal architecturessuited for the type of data provided under different scenarios.

POPNASv3: a Pareto-Optimal Neural Architecture Search Solution for Image and Time Series Classification