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

Mapping all the neurons in the brain requires automatic reconstruction ofentire cells from volume electron microscopy data. The flood-filling network(FFN) architecture has demonstrated leading performance for segmentingstructures from this data. However, the training of the network iscomputationally expensive. In order to reduce the training time, we implementedsynchronous and data-parallel distributed training using the Horovod library,which is different from the asynchronous training scheme used in the publishedFFN code. We demonstrated that our distributed training scaled well up to 2048Intel Knights Landing (KNL) nodes on the Theta supercomputer. Our trainedmodels achieved similar level of inference performance, but took less trainingtime compared to previous methods. Our study on the effects of different batchsizes on FFN training suggests ways to further improve training efficiency. Ourfindings on optimal learning rate and batch sizes agree with previous works.

Scaling Distributed Training of Flood-Filling Networks on HPC Infrastructure for Brain Mapping