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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

For convolutional neural networks (CNNs) that have a large volume of inputdata, memory management becomes a major concern. Memory cost reduction can bean effective way to deal with these problems that can be realized throughdifferent techniques such as feature map pruning, input data splitting, etc.Among various methods existing in this area of research, splitting the networkstructure is an interesting research field, and there are a few works done inthis area. In this study, the problem of reducing memory utilization usingnetwork structure splitting is addressed. A new technique is proposed to splitthe network structure into small parts that consume lower memory than theoriginal network. The split parts can be processed almost separately, whichprovides an essential role for better memory management. The split approach hasbeen tested on two well-known network structures of VGG16 and ResNet18 for theclassification of CIFAR10 images. Simulation results show that the splittingmethod reduces both the number of computational operations as well as theamount of memory consumption.

Splitting Convolutional Neural Network Structures for Efficient Inference