Výsledky vyhledávání - "Shriver, David"

Report

The SaTML '24 CNN Interpretability Competition: New Innovations for Concept-Level Interpretability

Autor: Casper, Stephen, Yun, Jieun, Baek, Joonhyuk, Jung, Yeseong, Kim, Minhwan, Kwon, Kiwan, Park, Saerom, Moore, Hayden, Shriver, David, Connor, Marissa, Grimes, Keltin, Nicolson, Angus, Tagade, Arush, Rumbelow, Jessica, Nguyen, Hieu Minh, Hadfield-Menell, Dylan

Interpretability techniques are valuable for helping humans understand and oversee AI systems. The SaTML 2024 CNN Interpretability Competition solicited novel methods for studying convolutional neural networks (CNNs) at the ImageNet scale. The object

Externí odkaz: http://arxiv.org/abs/2404.02949

Zobrazit plný text záznamu

Report

DNNV: A Framework for Deep Neural Network Verification

Autor: Shriver, David, Elbaum, Sebastian, Dwyer, Matthew B.

Despite the large number of sophisticated deep neural network (DNN) verification algorithms, DNN verifier developers, users, and researchers still face several challenges. First, verifier developers must contend with the rapidly changing DNN field to

Externí odkaz: http://arxiv.org/abs/2105.12841

Zobrazit plný text záznamu

Report

Refactoring Neural Networks for Verification

Autor: Shriver, David, Xu, Dong, Elbaum, Sebastian, Dwyer, Matthew B.

Deep neural networks (DNN) are growing in capability and applicability. Their effectiveness has led to their use in safety critical and autonomous systems, yet there is a dearth of cost-effective methods available for reasoning about the behavior of

Externí odkaz: http://arxiv.org/abs/1908.08026

Zobrazit plný text záznamu

Akademický článek

Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.

Systematic Generation of Diverse Benchmarks for DNN Verification

Autor: Xu, Dong, Shriver, David, Dwyer, Matthew B., Elbaum, Sebastian

Publikováno v: Computer Aided Verification

The field of verification has advanced due to the interplay of theoretical development and empirical evaluation. Benchmarks play an important role in this by supporting the assessment of the state-of-the-art and comparison of alternative verification

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=pmc_________::35876aa8e924a309a55d80fe2c5d02e8
http://europepmc.org/articles/PMC7363219