窝转脊椎动物
发表于 2025-3-25 06:10:55
http://reply.papertrans.cn/88/8711/871067/871067_21.png
词汇表
发表于 2025-3-25 10:20:09
A Cascade of Checkers for Run-time Certification of Local Robustness ranging from adversarial training with robustness guarantees to post-training and run-time certification of local robustness using either inexpensive but incomplete verification or sound, complete, but expensive constraint solving. We advocate for the use of a run-time cascade of over-approximate,
Blazon
发表于 2025-3-25 15:01:09
http://reply.papertrans.cn/88/8711/871067/871067_23.png
Magisterial
发表于 2025-3-25 17:17:26
http://reply.papertrans.cn/88/8711/871067/871067_24.png
瘙痒
发表于 2025-3-25 20:15:36
http://reply.papertrans.cn/88/8711/871067/871067_25.png
coagulation
发表于 2025-3-26 02:51:11
Neural Networks in Imandra: Matrix Representation as a Verification Choicel applications. Matrices are a data structure essential to formalising neural networks. Functional programming languages encourage diverse approaches to matrix definitions. This feature has already been successfully exploited in different applications. The question we ask is whether, and how, these
违反
发表于 2025-3-26 08:12:05
Self-correcting Neural Networks for Safe Classificationl notion of safety for classifiers via constraints called .. These constraints relate requirements on the order of the classes output by a classifier to conditions on its input, and are expressive enough to encode various interesting examples of classifier safety specifications from the literature.
芳香一点
发表于 2025-3-26 09:25:28
http://reply.papertrans.cn/88/8711/871067/871067_28.png
BRIDE
发表于 2025-3-26 13:01:32
Verified Numerical Methods for Ordinary Differential Equationss and are often used in computational models with safety-critical applications. For critical computations, numerical solvers for ODEs that provide useful guarantees of their accuracy and correctness are required, but do not always exist in practice. In this work, we demonstrate how to use the Coq pr
闯入
发表于 2025-3-26 20:12:06
Neural Network Precision Tuning Using Stochastic Arithmeticedded system with limited resources. A possible solution consists in reducing the precision of their neurons parameters. In this article, we present how to use auto-tuning on neural networks to lower their precision while keeping an accurate output. To do so, we use a floating-point auto-tuning tool