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

Closing the gap between the hardware requirements of state-of-the-artconvolutional neural networks and the limited resources constraining embeddedapplications is the next big challenge in deep learning research. Thecomputational complexity and memory footprint of such neural networks aretypically daunting for deployment in resource constrained environments. Modelcompression techniques, such as pruning, are emphasized among otheroptimization methods for solving this problem. Most existing techniques requiredomain expertise or result in irregular sparse representations, which increasethe burden of deploying deep learning applications on embedded hardwareaccelerators. In this paper, we propose the autoencoder-based low-rankfilter-sharing technique technique (ALF). When applied to various networks, ALFis compared to state-of-the-art pruning methods, demonstrating its efficientcompression capabilities on theoretical metrics as well as on an accurate,deterministic hardware-model. In our experiments, ALF showed a reduction of70\% in network parameters, 61\% in operations and 41\% in execution time, withminimal loss in accuracy.

ALF: Autoencoder-based Low-rank Filter-sharing for Efficient Convolutional Neural Networks