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

Applications of neural networks on edge systems have proliferated in recentyears but the ever-increasing model size makes neural networks not able todeploy on resource-constrained microcontrollers efficiently. We proposebit-serial weight pools, an end-to-end framework that includes networkcompression and acceleration of arbitrary sub-byte precision. The framework canachieve up to 8x compression compared to 8-bit networks by sharing a pool ofweights across the entire network. We further propose a bit-serial lookup basedsoftware implementation that allows runtime-bitwidth tradeoff and is able toachieve more than 2.8x speedup and 7.5x storage compression compared to 8-bitweight pool networks, with less than 1% accuracy drop.

Bit-serial Weight Pools: Compression and Arbitrary Precision Execution of Neural Networks on Resource Constrained Processors