Safety Assurance under Uncertainties: From Software to Cyber-Physical/Machine Learning Systems
暫譯: 不確定性下的安全保證：從軟體到網路物理/機器學習系統

Hasuo, Ichiro, Ishikawa, Fuyuki

Safety Assurance under Uncertainties: From Software to Cyber-Physical/Machine Learning Systems
  • 出版商: CRC
  • 出版日期: 2025-05-13
  • 售價: $4,870
  • 貴賓價: 9.5 折 $4,627
  • 語言: 英文
  • 頁數: 348
  • 裝訂: Hardcover - also called cloth, retail trade, or trade
  • ISBN: 0367554011
  • ISBN-13: 9780367554019
  • 相關分類: Machine Learning

    • 尚未上市，無法訂購

商品描述

Safety assurance of software systems has never been as imminent a problem as it is today. Practitioners and researchers who work on the problem face a challenge unique to modern software systems: uncertainties. For one, the cyber-physical nature of modern software systems as exemplified by automated driving systems mandates environmental uncertainties to be addressed and the resulting hazards to be mitigated. Besides, the abundance of statistical machine-learning components massive numerical computing units for statistical reasoning such as deep neural networks make systems hard to explain, understand, analyze, or verify.

The book is the first to provide a comprehensive overview of such united and interdisciplinary efforts. Driven by automated driving systems as a leading example, the book describes diverse techniques to specify, model, test, analyze, and verify modern software systems. Coming out of a collaboration between industry and basic academic research, the book covers both practical analysis techniques (readily applicable to existing systems) and more long-range design techniques (that call for new designs but bring a greater degree of assurance).

The book provides high-level intuitions and use-cases of each technique, rather than technical details, with plenty of pointers for interested readers.

商品描述(中文翻譯)

軟體系統的安全保障從未像今天這樣迫在眉睫。從事此問題的實務工作者和研究人員面臨著現代軟體系統特有的挑戰：不確定性。首先，現代軟體系統的網路物理特性，例如自動駕駛系統，要求必須解決環境不確定性並減輕由此產生的危害。此外，統計機器學習組件的豐富性以及用於統計推理的大規模數值計算單元，如深度神經網路，使得系統難以解釋、理解、分析或驗證。

本書首次提供了這些統一且跨學科努力的全面概述。以自動駕駛系統作為主要範例，本書描述了多種技術來指定、建模、測試、分析和驗證現代軟體系統。這本書源於產業與基礎學術研究的合作，涵蓋了實用的分析技術（可直接應用於現有系統）以及更長期的設計技術（需要新的設計但能帶來更高的保證程度）。

本書提供了每種技術的高層次直覺和使用案例，而非技術細節，並為有興趣的讀者提供了大量的指引。

作者簡介

Ichiro Hasuo, Ph.D. (cum laude, Radboud University Nijmegen, 2008), is a Professor at National Institute of Informatics (NII), Tokyo, Japan. He is at the same time the Research Director of the JST ERATO "Metamathematics for Systems Design'' Project, and the Director of Research Center for Mathematical Trust in Software and Systems at NII. His research field is software science and his interests include formal verification, mathematical and logical structures, category theory, integration of formal methods and testing, and application to cyber-physical systems and systems with statistical machine learning components.

Fuyuki Ishikawa, Ph.D. (The University of Tokyo, 2007), is an Associate Professor in Information Systems Architecture Science Research Division and the Director of GRACE Center, at National Institute of Informatics (NII), Tokyo, Japan. His research focuses on software engineering, especially for dependability of emerging AI and smart cyber-physical systems, including test generation, fault analysis, automated repair, and formal verification for automated driving systems. He is leading relevant initiatives of the Japanese industry such as the QA4AI guidelines for quality assurance of AI systems.

作者簡介(中文翻譯)

長尾一郎，博士（以優異成績畢業，荷蘭奈梅亨大學，2008年），是日本東京國立資訊學研究所（NII）的教授。他同時擔任JST ERATO「系統設計的元數學」專案的研究主任，以及NII數學信任於軟體與系統研究中心的主任。他的研究領域是軟體科學，興趣包括形式驗證、數學與邏輯結構、範疇論、形式方法與測試的整合，以及應用於網路物理系統和具有統計機器學習組件的系統。

石川冬樹，博士（東京大學，2007年），是日本東京國立資訊學研究所（NII）資訊系統架構科學研究部的副教授及GRACE中心的主任。他的研究專注於軟體工程，特別是新興人工智慧和智慧網路物理系統的可靠性，包括測試生成、故障分析、自動修復和自動駕駛系統的形式驗證。他正在領導日本產業相關的倡議，例如針對人工智慧系統的質量保證QA4AI指導方針。

類似商品

最後瀏覽商品 (20)