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

Major complications arise from the recent increase in the amount ofhigh-dimensional data, including high computational costs and memoryrequirements. Feature selection, which identifies the most relevant andinformative attributes of a dataset, has been introduced as a solution to thisproblem. Most of the existing feature selection methods are computationallyinefficient; inefficient algorithms lead to high energy consumption, which isnot desirable for devices with limited computational and energy resources. Inthis paper, a novel and flexible method for unsupervised feature selection isproposed. This method, named QuickSelection, introduces the strength of theneuron in sparse neural networks as a criterion to measure the featureimportance. This criterion, blended with sparsely connected denoisingautoencoders trained with the sparse evolutionary training procedure, derivesthe importance of all input features simultaneously. We implementQuickSelection in a purely sparse manner as opposed to the typical approach ofusing a binary mask over connections to simulate sparsity. It results in aconsiderable speed increase and memory reduction. When tested on severalbenchmark datasets, including five low-dimensional and three high-dimensionaldatasets, the proposed method is able to achieve the best trade-off ofclassification and clustering accuracy, running time, and maximum memory usage,among widely used approaches for feature selection. Besides, our proposedmethod requires the least amount of energy among the state-of-the-artautoencoder-based feature selection methods.

Quick and Robust Feature Selection: the Strength of Energy-efficient Sparse Training for Autoencoders