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

Neural Architecture Search (NAS) algorithms aim at finding efficient DeepNeural Network (DNN) architectures for a given application under given systemconstraints. DNNs are computationally-complex as well as vulnerable toadversarial attacks. In order to address multiple design objectives, we proposeRoHNAS, a novel NAS framework that jointly optimizes for adversarial-robustnessand hardware-efficiency of DNNs executed on specialized hardware accelerators.Besides the traditional convolutional DNNs, RoHNAS additionally accounts forcomplex types of DNNs such as Capsule Networks. For reducing the explorationtime, RoHNAS analyzes and selects appropriate values of adversarialperturbation for each dataset to employ in the NAS flow. Extensive evaluationson multi - Graphics Processing Unit (GPU) - High Performance Computing (HPC)nodes provide a set of Pareto-optimal solutions, leveraging the tradeoffbetween the above-discussed design objectives. For example, a Pareto-optimalDNN for the CIFAR-10 dataset exhibits 86.07% accuracy, while having an energyof 38.63 mJ, a memory footprint of 11.85 MiB, and a latency of 4.47 ms.

RoHNAS: A Neural Architecture Search Framework with Conjoint  Optimization for Adversarial Robustness and Hardware Efficiency of  Convolutional and Capsule Networks