Year: 2016
Type: preprint
Abstract: Verified artificial intelligence (AI) is the goal of designing AI-based systems that that have strong, ideally provable, assurances of correctness with respect to mathematically-specified requirements. This paper considers Verified AI from a formal methods perspective. We describe five challenges for achieving Verified AI, and five corresponding principles for addressing these challenges.
Source: arXiv (Cornell University)
Institutions: University of California, Berkeley, Stanford University
Language: English
Subfield: Computational Theory and Mathematics
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
Awards: CPS: Breakthrough: Control Improvisation for Cyber-Physical Systems, CPS: Frontier: Collaborative Research: VeHICaL: Verified Human Interfaces, Control, and Learning for Semi-Autonomous Systems, SHF: CSR: Small: Integrated Design and Verification of High-Confidence Interactive Systems, Collaborative Research: Expeditions in Computer Augmented Program Engineering (ExCAPE): Harnessing Synthesis for Software Design, FMitF: Collaborative Research: Formal Methods for Machine Learning System Design
OpenAlex ID: W2467659428