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/

Zendy Plus

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

Zendy Tools

Zendy Open

Neural network based approximate computing is a universal architecturepromising to gain tremendous energy-efficiency for many error resilientapplications. To guarantee the approximation quality, existing works deploy twoneural networks (NNs), e.g., an approximator and a predictor. The approximatorprovides the approximate results, while the predictor predicts whether theinput data is safe to approximate with the given quality requirement. However,it is non-trivial and time-consuming to make these two neural networkcoordinate---they have different optimization objectives---by training themseparately. This paper proposes a novel neural network structure---AXNet---tofuse two NNs to a holistic end-to-end trainable NN. Leveraging the philosophyof multi-task learning, AXNet can tremendously improve the invocation(proportion of safe-to-approximate samples) and reduce the approximation error.The training effort also decrease significantly. Experiment results show 50.7%more invocation and substantial cuts of training time when compared to existingneural network based approximate computing framework.

AXNet: ApproXimate computing using an end-to-end trainable neural network