arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2302.11049cs.LGcs.CVcs.SE
收藏

基于AI的系统认证框架

Framework for Certification of AI-Based Systems

Xwing, Inc.(Xwing公司)

Maxime Gariel, Brian Shimanuki, Rob Timpe, Evan Wilson

摘要:

目前航空航天软件的认证流程并不适应深度神经网络等“基于AI”的算法。与传统的航空航天软件不同,在神经网络训练期间优化的精确参数与处理网络的代码一样重要(或更重要),并且它们不能直接在数学上理解。尽管它们缺乏可解释性,但这些算法很有吸引力,因为对于某些应用程序,它们可以表现出任何传统的显式逐行软件方法都无法达到的高性能。本文提出了一个框架和原则,可用于建立神经网络模型的认证方法,目前的认证过程,如DO-178不能应用。虽然它不是一个神奇的配方,但它是一组常识步骤,通过展示汇集,跟踪和跟踪需求,数据,软件,培训过程和测试结果的能力,可以让申请人和监管机构增加对开发软件的信心。

英文摘要:

The current certification process for aerospace software is not adapted to "AI-based" algorithms such as deep neural networks. Unlike traditional aerospace software, the precise parameters optimized during neural network training are as important as (or more than) the code processing the network and they are not directly mathematically understandable. Despite their lack of explainability such algorithms are appealing because for some applications they can exhibit high performance unattainable with any traditional explicit line-by-line software methods. This paper proposes a framework and principles that could be used to establish certification methods for neural network models for which the current certification processes such as DO-178 cannot be applied. While it is not a magic recipe, it is a set of common sense steps that will allow the applicant and the regulator increase their confidence in the developed software, by demonstrating the capabilities to bring together, trace, and track the requirements, data, software, training process, and test results.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑