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

Convolutional Neural Networks (CNNs) is one of successful method in manyareas such as image classification tasks. However, the amount of memory andcomputational cost needed for CNNs inference obstructs them to run efficientlyin mobile devices because of memory and computational ability limitation. Oneof the method to compress CNNs is compressing the layers iteratively, i.e. bylayer-by-layer compression and fine-tuning, with CP-decomposition inconvolutional layers. To compress with CP-decomposition, rank selection isimportant. In the previous approach rank selection that is based on sensitivityof each layer, the average rank of the network was still arbitrarily selected.Additionally, the rank of all layers were decided before whole process ofiterative compression, while the rank of a layer can be changed afterfine-tuning. Therefore, this paper proposes selecting rank of each layer usingVariational Bayesian Matrix Factorization (VBMF) which is more systematic thanarbitrary approach. Furthermore, to consider the change of each layer's rankafter fine-tuning of previous iteration, the method is applied just beforecompressing the target layer, i.e. after fine-tuning of the previous iteration.The results show better accuracy while also having more compression rate inAlexNet's convolutional layers compression.

Rank Selection of CP-decomposed Convolutional Layers with Variational Bayesian Matrix Factorization