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

The heavy burdens of computation and off-chip traffic impede deploying thelarge scale convolution neural network on embedded platforms. As CNN isattributed to the strong endurance to computation errors, employing blockfloating point (BFP) arithmetics in CNN accelerators could save the hardwarecost and data traffics efficiently, while maintaining the classificationaccuracy. In this paper, we verify the effects of word width definitions in BFPto the CNN performance without retraining. Several typical CNN models,including VGG16, ResNet-18, ResNet-50 and GoogLeNet, were tested in this paper.Experiments revealed that 8-bit mantissa, including sign bit, in BFPrepresentation merely induced less than 0.3% accuracy loss. In addition, weinvestigate the computational errors in theory and develop the noise-to-signalratio (NSR) upper bound, which provides the promising guidance for BFP basedCNN engine design.

Computation Error Analysis of Block Floating Point Arithmetic Oriented Convolution Neural Network Accelerator Design