1 / 12

RAIR Lab

RAIR Lab. John Licato licatj@rpi.edu Selmer Bringsjord Department of Cognitive Science Department of Computer Science Lally School of Management Rensselaer AI & Reasoning (RAIR) Lab Rensselaer Polytechnic Institute (RPI) Troy NY 12180 USA Selmer.Bringsjord@gmail.com RPI 2.1.12-1200NY.

ewaa
Download Presentation

RAIR Lab

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript

  1. RAIR Lab • John Licato • licatj@rpi.edu • Selmer Bringsjord • Department of Cognitive Science • Department of Computer Science • Lally School of Management • Rensselaer AI & Reasoning (RAIR) Lab • Rensselaer Polytechnic Institute (RPI) • Troy NY 12180 USA • Selmer.Bringsjord@gmail.com • RPI 2.1.12-1200NY

  2. RAIR Lab Approach: Logic-based: AI & Computational CogSci Reasoning

  3. Our Future Autonomous lethal robots on the battlefield. Autonomous “lethal” robots in our hospitals. Autonomous lethal robots in law enforcement. ...

  4. Problem, More Specifically • How can we ensure that the robots in question always behave in an ethically correct manner? • How can we know ahead of time, via rationales expressed in clear English (and/or other natural languages), that they will so behave? • How can we know in advance that their behavior will be constrained specifically by the ethics affirmed by ethically correct human overseers?

  5. Another not-too-technical introductory paper, addressing this problem:

  6. Analogico-Deductive Reasoning • Moral reasoning has a lot to do with analogical reasoning • ADR: The combination of analogical and hypothetico-deductive reasoning

  7. What is relevant –Do Fish Feel Pain? Feels Pain Feels Pain ? Me Fish Fish are like humans; therefore they feel pain like humans

  8. R&D Thrusts • Engineer radically new system able to prove Gödel’s incompleteness theorems from scratch. For Air Force. • Engineer the world’s first artificial conductor/educator: Handle; CAIRA. For National Science Foundation. • Answer the biggest questions about AI and the human mind. • E.g., “Can a computing machine grasp the infinite?” • For John Templeton Foundation. • Mini-robotics demonstration of X for military. • Save the world by championing & engineering ethically correct warfighting robots. • Introduce a new way of teaching programming that (unlike eg LOGO) produces cognitive transfer, and addresses the “STEM-dearth” problem. • Engineering cognitively robust synthetic characters. IBM, Disney, … • AI & Economics: A new form of LAI-based economics ... • NLP: Logico-mathematically intense; very technical. • Formalizing physics => formalizing cancer-relevant biological processes. Embryonic.

  9. RAIR Lab • John Licato • licatj@rpi.edu • Selmer Bringsjord • Department of Cognitive Science • Department of Computer Science • Lally School of Management • Rensselaer AI & Reasoning (RAIR) Lab • Rensselaer Polytechnic Institute (RPI) • Troy NY 12180 USA • Selmer.Bringsjord@gmail.com • RPI 2.1.12-1200NY

More Related