Dr. Daniel Shapiro

Executive Director, ISLE

dgs at csli.stanford.edu

 

 


Research

Publications

Professional Service

Teaching

CV

For Fun


Research

My research surrounds advanced autonomy and general theories of cognition. I work on cognitive architectures for intelligent agents, the technologies underlying those architectures, and on applications of intelligent artifacts. I am one of the principle authors of the Icarus architecture, which supplies a framework for constructing agents that pursue complex tasks in dynamic environments.   I am interested in research on agent motivation, and in establishing trust between artificial agents and their human users.   I work with a variety of tools and technologies that enable intelligent agents, e.g., explanation based learning, reinforcement learning, logical inference, reactive programming, decision theory, and operations research, as well as on a variety of tasks that employ intelligent artifacts, such as transfer learning, problem solving, and human-machine spoken dialogue.

 

I am the past president of Applied Reactivity, Inc., a company I formed to take my work on value driven agents out of academia and into application.  I have been a Senior Researcher at the Stanford University Center for the Study of Language and Information (CSLI), and am currently an affiliate of its Computational Learning Laboratory (CLL). 

 

Publications

Complete list

 

Dissertation

·       Shapiro, D., Value-driven agents, Ph.D. thesis, Stanford University, Department of Management Science and Engineering. (2001). [Abstract | Full Text]

 

Books and Journals, edited

·       Shapiro, D., and Göker, M. (eds.), AI Magazine Special Issue on Advancing AI Research and Applications by Learning from What Went Wrong and Why.  AAAI Press, Summer 2008.

·       Remagnino, P., and Shapiro, D. (eds.), Computational Intelligence: Special Issue on Artificial Intelligence Methods for Ambient Intelligence, Volume 23 Issue 4,  November 2007.

·       Ramos, C., Augusto, J., and Shapiro, D. (eds.). IEEE Intelligent Systems Special Issue on Ambient Intelligence, Vol. 23, No. 2.  Mar./Apr. 2008.

·       Augusto, J., and Shapiro, D. (eds.), Advances in Ambient Intelligence. (2007).  IOS press.  ISBN 978-1-58603-800-7

 

Some recent papers:

·       Könik, K., Ali, K., Shapiro, D., Li, N., and Stracuzzi, D. Improving Structural Knowledge Transfer with Parametric Adaptation (2010). The 23rd Florida Artificial Intelligence Research Society Conference (FLAIRS-23), Daytona Beach, Florida.  (In press.)

·       Könik, T., O’Rorke, P., and Shapiro, D.  Skill Transfer through Goal-Driven Representation Mapping. Cognitive Systems Research, Special Issue on Analogies - Integrating Cognitive Abilities, Vol. 10, No. 3, September 2009. PDF

·       Li, N., Stracuzzi, D., Cleveland, G., Könik, T., Nejati, N., Shapiro, D., Molineaux, M., and Aha, D. (2009). Constructing Game Agents from Video of Human Behavior, Proceedings of the Fifth AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment (AIIDE), Stanford, CA. PDF

·       Ali, K., Leung, K., Könik, K., Choi, D., and Shapiro, D. (2009).  Knowledge-Directed Theory Revision, Nineteenth International Conference on Inductive Logic Programming, Leuven, Belgium.

·       Shapiro, D., Könik, K., and O’Rorke, P. (2008). Achieving Far Transfer in an Integrated Cognitive Architecture, Proceedings of the Twenty-third Conference of the Association for the Advancement of Artificial Intelligence, Chicago, IL. PDF

·       Billman,D.,  Shapiro, D., & Cummings, K. (2005) Processes in Diagnostic Reasoning: Information Use in Causal Explanations. In Program of the Twenty-Seventh Annual Conference of the Cognitive Science Society.  pp. 262-267, Erlbaum:  Hillsdale, NJ.  PDF

·       Shapiro, D., & Collopy, P. (2004). Communicating values to autonomous agents. Stanford Spring Symposium on Interaction between Humans and Autonomous Systems over Extended Operation. PDF

·       Ichise, R., Shapiro, D., Langley, P. (2004). Structured program induction from behavioral traces, IEICE Transactions on Information and Systems, Vol. J87-D-1, No. 6, pp. 730-740 (in Japanese). The Institute of Electronics, Information and Communication Engineers.

·       Langley, P., Cummings, K., & Shapiro, D. (2004). Hierarchical skills and cognitive architectures. Proceedings of the Twenty-Sixth Annual Conference of the Cognitive Science Society. Chicago, IL.  PDF

·       Choi, D., Kaufman, M., Langley, P., Nejati, N., & Shapiro, D. (2004). An architecture for persistent reactive behavior. Proceedings of the Third International Joint Conference on Autonomous Agents and Multi Agent Systems. New York: ACM Press. PDF

·       Langley, P., Shapiro, D., Aycinena, M., & Siliski, M. (2003). A value-driven architecture for intelligent behavior. Proceedings of the IJCAI-2003 Workshop on Cognitive Modeling of Agents and Multi-Agent Interactions. Acapulco, Mexico. PDF

·       Shapiro, D., & Gervasio, M. (2003). Adaptive interfaces for value driven agents. Stanford Spring Symposium on Human Interaction with Autonomous Systems in Complex Environments. PDF

·       Shapiro, D., & Langley, P. (2002). Separating skills from preference: using learning to program by reward. Nineteenth International Conference on Machine Learning. PDF

·       Bay, S., Shapiro, D., & Langley, P. (2002). Revising engineering models: combining computational discovery with knowledge. European Conference on Machine Learning. PDF

·       Ichise, R., Shapiro, D., & Langley, P. (2002). Learning hierarchical skills from observation. Proceedings of the Fifth International Conference on Discovery Science. PDF

·       Shapiro, D., & Shachter, R. (2002). User-agent value alignment. Stanford Spring Symposium, Workshop on Safe Learning Agents. Stanford University, Stanford, CA. PDF

·       Shapiro, D., Langley, P., & Shachter, R. (2001).  Using background knowledge to speed reinforcement learning, Fifth International Conference on Autonomous Agents. PDF

 

Manuscripts:

·       Langley, P., Choi, D., & Shapiro, D. (2004). A cognitive architecture for physical agents. PDF

·       Shapiro, D., & Shachter, R. User-agent value alignment. (Long version) PDF

·       Shapiro, D., Billman, D., Marker, M., and Langley, P. A Human-Centered Approach to Monitoring Complex Dynamic Systems. PDF

·       Shapiro, D., & Shachter, R. Convergent reinforcement learning for hierarchical reactive plans. PDF

 

Professional Service

·       Co-Chair, Innovative Applications of Artificial Intelligence 2010, Chair IAAI-11

·       Editorial board, Journal of Ambient Intelligence and Smart Environments (JAISE)

·       Editorial board, Journal of Interesting Negative Results in Natural Language Processing and Machine Learning (JINR)

·       Program Committee, Goal Directed Autonomy Workshop, AAAI 2010

·       Program Committee, 5th Workshop on Artificial Intelligence Techniques for Ambient Intelligence (AITAmI’10), Kuala Lumpur, Malaysia

·       Program Committee, IAAI-08, IAAI-09

·       Program Committee, 4th Workshop on Artificial Intelligence Techniques for Ambient Intelligence, Barcelona, Spain, 2009

·       Chair, What Went Wrong and Why:Lessons from AI Research and Applications workshop, AAAI Stanford Spring Symposium, 2006

·       Co-chair, Artificial Intelligence Techniques for Ambient Intelligence workshop, European Conference on Artificial Intelligence, 2006.

·       Chair, Persistent Assistants: Living and Working with AI, AAAI Stanford Spring Symposium, 2005

·       Symposium on Learning and Motivation in Cognitive Architectures, CSLI, Stanford University, 3/22-3/23, 2003. Co-organizer with Pat Langley and John Laird.

·       Co-chair, Safe Learning Agents workshop, AAAI Stanford Spring Symposium, 2002.

·       Program Committee, International Conference on Machine Learning, 2002.

 

Teaching

I occasionally teach a class on Cognitive Architectures through the Stanford Symbolics Systems Program, which surveys the field of cognitive architectures and provides students with a hands-on experience using such systems.  I developed a three quarter series on Artificial Intelligence through the Management Science and Engineering department at Stanford, and a course on decision theory in public policy through the Public Administration Department at California State College in Hayward.  I have taught Lisp programming, computer architecture, and software engineering.  Many years ago, I organized an interdisciplinary study group that supplied the technical background for a science fiction book; Flight of the Dragonfly, by Bob Forward (Timescape, 1984).

 

For Fun

·       My pet pumpkins I grow giant vegetables for competitions and for fun.

·       Our wedding cake and the MacShapiro Tartan It is a long story.  You will have to ask.

·       Glass Blowing

·       Scottish country dance

·       Knee falls and toe dancing

·       With my Tuvan throat-singing instructor in Mongolia