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

Some Deep Neural Networks (DNN) have what we call lanes, or they can bereorganized as such. Lanes are paths in the network which are data-independentand typically learn different features or add resilience to the network. Giventheir data-independence, lanes are amenable for parallel processing. TheMulti-lane CapsNet (MLCN) is a proposed reorganization of the Capsule Networkwhich is shown to achieve better accuracy while bringing highly-parallel lanes.However, the efficiency and scalability of MLCN had not been systematicallyexamined. In this work, we study the MLCN network with multiple GPUs findingthat it is 2x more efficient than the original CapsNet when usingmodel-parallelism. Further, we present the load balancing problem ofdistributing heterogeneous lanes in homogeneous or heterogeneous acceleratorsand show that a simple greedy heuristic can be almost 50% faster than a naiverandom approach.

Efficiency and Scalability of Multi-Lane Capsule Networks (MLCN)