Towards Verified Artificial Intelligence
It addresses the need for reliable AI systems for developers and users, but is incremental as it builds on existing formal methods concepts.
The paper tackles the problem of designing AI systems with provable correctness by identifying five challenges and proposing five principles from a formal methods perspective, but does not present specific results or numbers.
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.