当前位置: X-MOL 学术J. Comput. Sci. Tech. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Verifying ReLU Neural Networks from a Model Checking Perspective
Journal of Computer Science and Technology ( IF 1.2 ) Pub Date : 2020-11-01 , DOI: 10.1007/s11390-020-0546-7
Wan-Wei Liu , Fu Song , Tang-Hao-Ran Zhang , Ji Wang

Neural networks, as an important computing model, have a wide application in artificial intelligence (AI) domain. From the perspective of computer science, such a computing model requires a formal description of its behaviors, particularly the relation between input and output. In addition, such specifications ought to be verified automatically. ReLU (rectified linear unit) neural networks are intensively used in practice. In this paper, we present ReLU Temporal Logic (ReTL), whose semantics is defined with respect to ReLU neural networks, which could specify value-related properties about the network. We show that the model checking algorithm for the Σ2 ∪ Π2 fragment of ReTL, which can express properties such as output reachability, is decidable in EXPSPACE. We have also implemented our algorithm with a prototype tool, and experimental results demonstrate the feasibility of the presented model checking approach.

中文翻译:

从模型检查的角度验证 ReLU 神经网络

神经网络作为一种重要的计算模型,在人工智能(AI)领域有着广泛的应用。从计算机科学的角度来看,这样的计算模型需要对其行为进行正式描述,尤其是输入和输出之间的关系。此外,应该自动验证此类规范。ReLU(整流线性单元)神经网络在实践中被大量使用。在本文中,我们提出了 ReLU 时间逻辑 (ReTL),其语义是相对于 ReLU 神经网络定义的,它可以指定有关网络的值相关属性。我们展示了 ReTL 的 Σ2 ∪ Π2 片段的模型检查算法,可以表达输出可达性等属性,在 EXPSPACE 中是可判定的。我们还使用原型工具实现了我们的算法,
更新日期:2020-11-01
down
wechat
bug