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

AI's widespread integration has led to neural networks (NNs) deployment onedge and similar limited-resource platforms for safety-critical scenarios. Yet,NN's fragility raises concerns about reliable inference. Moreover, constrainedplatforms demand compact networks. This study introduces VeriCompress, a toolthat automates the search and training of compressed models with robustnessguarantees. These models are well-suited for safety-critical applications andadhere to predefined architecture and size limitations, making them deployableon resource-restricted platforms. The method trains models 2-3 times fasterthan the state-of-the-art approaches, surpassing relevant baseline approachesby average accuracy and robustness gains of 15.1 and 9.8 percentage points,respectively. When deployed on a resource-restricted generic platform, thesemodels require 5-8 times less memory and 2-4 times less inference time thanmodels used in verified robustness literature. Our comprehensive evaluationacross various model architectures and datasets, including MNIST, CIFAR, SVHN,and a relevant pedestrian detection dataset, showcases VeriCompress's capacityto identify compressed verified robust models with reduced computation overheadcompared to current standards. This underscores its potential as a valuabletool for end users, such as developers of safety-critical applications on edgeor Internet of Things platforms, empowering them to create suitable models forsafety-critical, resource-constrained platforms in their respective domains.

VeriCompress: A Tool to Streamline the Synthesis of Verified Robust Compressed Neural Networks from Scratch