Program

The format of this one-day workshop will include a balanced blend of invited talks, poster presentations, panels, and open discussion. The workshop is open to all AI researchers who are interested in the workshop's topics, though we anticipate a limit of approximately 50 people.  

8:30-9:00 Introduction -- Gary Marcus, Francesca Rossi, Manuela Veloso

9:00-9:30 Topic 1: Language understanding

Chair: Gary Marcus

       WWTS (What Would Turing Say), Doug Lenat (Cycorp)

       The devil's in the details: planning, executing, and evaluating the Winograd              Schema Challenge, Leora Morgensten (Leidos)

9:30-9:45 Discussion - Essence of language in a Turing Test

9:45-10:30 Topic 2: Perception/embodiment/brain

       A picture is worth a thousand words, and a good story: the visual Turing test, Fei-Fei Li (Stanford University)

       Why we need a physically embodied Turing test and what it might look like, Charles Ortiz (Nuance)

       Turing+ Questions, Tomaso Poggio (MIT)

10:30 - 10:45 Discussion - Beyond language

10:45-11:15 Coffee break + posters

11:15-11:45 Topic 3: Cognitive science and Q/A

       Software Social Organisms: Implications for Measuring AI Progress, Ken Forbus (Northwestern University)

       "My computer is an Honor Student" - but is it intelligent? Standardized tests as a measure of AI, Peter Clark (AI2)

11:45-12:00 Discussion - Cognition and knowledge

12:00-13:00 Lunch (provided by AAAI for all registered workshop attendees, room Texas VII)

13:00-13:30 Topic 4: Creativity/teams

       The day AI wins Nobel Prize, Hiroaki Kitano  (OIST -- Okinawa Institute of Science and Technology)

       Is your intelligent computer smart enough to work on my team?, Barbara Grosz (Harvard University)

13:30 - 13:45 Discussion - Collaboration

13:45-14:45 Topic 5: Competitions

Would Turing Have Passed The Turing Test?, Moshe Vardi (Rice University)

RoboCup as a Competition: Beginnings and Beyond, Manuela Veloso (CMU)

      Principles for designing an AI competition, or why the Turing test fails as an inducement prize, Stuart Shieber (Harvard University)  

 I-athlon: Towards a Multidimensional Intelligence Test, Guruduth Banavar (IBM Yorktown)

14:45-15:30 Working groups - Creating a real test

15:30-16:00 Coffee break + posters

16:00-17:30 Report from working groups, concrete plan, and wrap up - Gary Marcus, Francesca Rossi, Manuela Veloso

18:00-19:00 The future of AI (Joint panel with Workshop on AI and Ethics), Panelists: Toby Walsh, Max Tegmark, Gary Marcus, Francesca Rossi, Manuela Veloso

List of posters:

Mateusz Malinowski and Mario Fritz. Hard to Cheat: A Turing Test based on Answering Questions about Images.

Nicole Maslan, Melissa Roemmele, and Andrew S. Gordon. An Integrated Evaluation of Perception, Interpretation, and Narration

Richard Wallace. The Shakespeare Authorship Question: A New Type of AI Challenge

Oliver Brock. The Work Turing Test

Mark Riedl. The Lovelace 2.0 Test of Artificial Creativity and Intelligence

Vinay Chaudhri. Abstraction and Perspective in Question Answering

Yoonsuck Choe, Jaewook Yoo and Qinbo Li. Tool Construction and Use Challenge: Tooling Test Rebooted

Joel Lehman and Risto Miikkulainen. General Video Game Playing as a Benchmark for Human-Competitive AI

Ashok Goel. Geometry, Drawings, Visual Thinking and Imagery: Towards a Visual Turing Test of Machine Intelligence

Guillermo Cecchi and Irina Rish. Turing a la Freud: Test for an Automated Psychiatrist

David Bender. Subcognition and the Winograd Schema Challenge

Lianghao Li and Qiang Yang. Lifelong Machine Learning Test

Christian Lebiere, Dan Bothell, Don Morrison, Oscar Javier Romero López, Robert Thomson and Yury Vinokurov. Strong CogSci: Guidance from Cognitive Science On the Design of a Test of Artificial Intelligence

Praveen Paritosh. Comprehensive Comprehension

Francois Pachet and Pierre Roy. (Manufac) Turing Tests for Music