Towards Verified Artificial Intelligence

06/27/2016

∙

Verified artificial intelligence (AI) is the goal of designing AI-based systems that are provably correct 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.

READ FULL TEXT

Towards Verified Artificial Intelligence

Positive AI: Key Challenges for Designing Wellbeing-aligned Artificial Intelligence

Connecting the Dots in Trustworthy Artificial Intelligence: From AI Principles, Ethics, and Key Requirements to Responsible AI Systems and Regulation

If consciousness is dynamically relevant, artificial intelligence isn't conscious

VERIFAI: A Toolkit for the Design and Analysis of Artificial Intelligence-Based Systems

Superintelligence Safety: A Requirements Engineering Perspective

Symmetry as an Organizing Principle for Geometric Intelligence

The intersection of video capsule endoscopy and artificial intelligence: addressing unique challenges using machine learning

Towards Verified Artificial Intelligence

Related Research

Positive AI: Key Challenges for Designing Wellbeing-aligned Artificial Intelligence

Connecting the Dots in Trustworthy Artificial Intelligence: From AI Principles, Ethics, and Key Requirements to Responsible AI Systems and Regulation

If consciousness is dynamically relevant, artificial intelligence isn't conscious

VERIFAI: A Toolkit for the Design and Analysis of Artificial Intelligence-Based Systems

Superintelligence Safety: A Requirements Engineering Perspective

Symmetry as an Organizing Principle for Geometric Intelligence

The intersection of video capsule endoscopy and artificial intelligence: addressing unique challenges using machine learning