2nd International Workshop
13th February 2016 | Phoenix, Arizona USA

What is the future of AI? And what should we be doing about it now?

The focus of this workshop is on the ethical and societal implications of building AI systems. It follows a successful full-day workshop held at AAAI-15. There is an increasing appetite within and outside AI for such discussions. The workshop will consist of invited talks and tutorials, submitted papers, and one or more panel discussions. Topics include, but are not limited to:

• The future of AI
• AI as a threat to or saviour for humanity
• Mechanisms to ensure moral behaviours in AI systems
• Safeguards necessary within AI research
• Autonomous agents in the military
• Autonomous agents in commerce and other domains
• The impact of AI on work and other aspects of our lives

Tentative Schedule

09.00-10.15: AI and Ethics 1

Benjamin Kuipers | Human-like Morality and Ethics for Robots.

Joanna Bryson | Patiency Is Not a Virtue: AI and the Design of Ethical Systems.

Jessica Taylor | Quantilizers: A Safer Alternative to Maximizers for Limited Optimization.

10.15-10.45: Coffee.

10.15-11.20: Posters.

Tsvi Benson-Tilsen and Nate Soares | Formalizing Convergent Instrumental Goals.

Kaj Sotala | Defining Human Values for Value Learners

Aaron Isaksen, Julian Togelius, Frank Lantz and Andy Nealen | Playing Games Across the Superintelligence Divide.

Jason Wilson | Group Optimization: A Framework for Evaluation and Designing Human-Robot Relationships.

Mark Riedl and Brent Harrison | Using Stories to Teach Human Values to Artificial Agents.

Emanuelle Burton, Judy Goldsmith and Nicholas Mattei | Using “The Machine Stops” for Teaching Ethics in Artificial Intelligence and Computer Science.

11.20-13.00: AI and Ethics 2

Toby Walsh|Why the Technological Singularity May Never Happen.

Miles Brundage | Modeling Progress in AI.

Roman Yampolskiy | Taxonomy of Pathways to Dangerous Artificial Intelligence

David Abel, James Macglashan and Michael Littman | Reinforcement Learning as a Framework for Ethical Decision Making.

13.00-14.00: Lunch.

14.00-15.00: AI & Safety 1

Max Tegmark & Richard Mallah | Introductory remarks on the history and importance of the AI safety and beneficence grants program, and the landscape of current funded AI projects and how they tie together conceptually.

Kaj Sotala | Teaching AI Systems Human Values Through Human-Like Concept Learning.

Vincent Conitzer | How to Build Ethics into Robust Artificial Intelligence.

Fuxin Li | Understanding When a Deep Network Is Going to Be Wrong

Francesca Rossi | Safety Constraints and Ethical Principles in Collective Decision Making Systems.

Bas Steunebrink | Experience-based AI (EXPAI)

15.00-16.00: AI & Safety 2

Manuela Veloso | Explanations for Complex AI Systems

Brian Ziebart | Towards Safer Inductive Learning

Percy Liang | Predictable AI via Failure Detection and Robustness

Benja Fallenstein | Aligning Superintelligence With Human Interests

Paul Christiano | Counterfactual Human Oversight

16.00-16.30: Coffee Break.

16.30-18.00: AI & Safety 3

Stuart Russell | Value Alignment and Moral Metareasoning

Stefano Ermon | Robust Probabilistic Inference Engines for Autonomous Agents

Benjamin Rubinstein | Security Evaluation of Machine Learning Systems

Panel discussion: What are the most promising research directions for keeping AI beneficial? (Russell, Conitzer, Parkes, Liang, Ermon, Rubinstein)

Location and Date

February 13th, 2016 at the Phoenix Convention Center: 100 N 3rd St, Phoenix, AZ 85004

For more information about the event and the participants, please visit the official AI, Ethics and Safety Workshop page.