Skip to main content
Springer Nature Link
Log in

Robot Baby 2001

  • Conference paper
  • First Online:
Algorithmic Learning Theory (ALT 2001)

Part of the book series: Lecture Notes in Computer Science ((LNAI,volume 2225))

Included in the following conference series:

  • 516 Accesses

Abstract

In this paper we claim that meaningful representations can be learned by programs, although today they are almost always designed by skilled engineers. We discuss several kinds of meaning that representations might have, and focus on a functional notion of meaning as appropriate for programs to learn. Specifically, a representation is meaningful if it incorporates an indicator of external conditions and if the indicator relation informs action. We survey methods for inducing kinds of representations we call structural abstractions. Prototypes of sensory time series are one kind of structural abstraction, and though they are not denoting or compositional, they do support planning. Deictic representations of objects and prototype representations of words enable a program to learn the denotational meanings of words. Finally, we discuss two algorithms designed to find the macroscopic structure of episodes in a domain-independent way.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution

Institutional subscriptions

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Similar content being viewed by others

References

  1. Philip E. Agre and David Chapman. Pengi: An implementation of a theory of activity. In Proceedings of the Sixth National Conference on Artificial Intelligence, pages 268–272, Seattle, Washington, 1987. American Association for Artificial Intelligence.

    Google Scholar 

  2. James F. Allen. An interval based representation of temporal knowledge. In Proceedings of the Seventh International Joint Conference on Artificial Intelligence, pages 221–226, San Mateo, CA, 1981. Morgan Kaufmann Publishers, Inc.

    Google Scholar 

  3. Dana H. Ballard, Mary M. Hayhoe, and Polly K. Pook. Deictic codes for the embodiment of cognition. Computer Science Department, University of Rochester.

    Google Scholar 

  4. D.H. Ballard. Reference frames for animate vision. In Proceedings of the Eleventh International Joint Conference on Artificial Intelligenc. Morgan Kaufmann Publishers, Inc., 1989.

    Google Scholar 

  5. Paul Bloom. How Children Learn the Meanings of Words. MIT Press, 2000.

    Google Scholar 

  6. Paul Cohen. Fluent learning: Elucidating the structure of episodes. In Proceedings of Fourth Symposium on Intelligent Data Analysis. Springer, 2001.

    Google Scholar 

  7. Paul Cohen and Niall Adams. An algorithm for segmenting categorical time series into meaningful episodes. In Proceedings of Fourth Symposium on Intelligent Data Analysis. Springer, 2001.

    Google Scholar 

  8. Paul R. Cohen and Mary Litch. What are contentful mental states? dretske’s theory of mental content viewed in the light of robot learning and planning algorithms. In Proceedings of the Sixteenth National Conference on Artificial Intelligence, 1999.

    Google Scholar 

  9. Bénédicte de Boysson-Bardies. How Language Comes to Children. MIT Press, 2001.

    Google Scholar 

  10. Daniel Dennett. Do it yourself understanding. In Daniel Dennett, editor, Brainchildren, Essays on Designing Minds. MIT Press and Penguin, 1998.

    Google Scholar 

  11. Fred Dretske. Knowledge and the Flow of Information. Cambridge University Press, 1981. Reprinted by CSLI Publications, Stanford University.

    Google Scholar 

  12. Fred Dretske. Explaining Behavior: Reasons in a World of Causes. MIT Press, 1988.

    Google Scholar 

  13. Joseph B. Kruskall and Mark Liberman. The symmetric time warping problem: From continuous to discrete. In Time Warps, String Edits and Macromolecules: The Theory and Practice of Sequence Comparison. Addison-Wesley, 1983.

    Google Scholar 

  14. B. Kuipers. The spatial semantic hierarchy. Artificial Intelligence, 119:191–233, 2000.

    Article  MathSciNet  Google Scholar 

  15. George Lako.. Women, Fire, and Dangerous Things. University of Chicago Press, 1984.

    Google Scholar 

  16. D. B. Lenat. Cyc: Towards programs with common sense. Communications of the ACM, 33(8), 1990.

    Google Scholar 

  17. D. B. Lenat and R. V. Guha. Building large knowledge-based systems: Representation and inference in the Cyc project. Addison Wesley, 1990.

    Google Scholar 

  18. Paola Sebastiani, Marco Ramoni and Paul Cohen. Bayesian clustering by dynamics. Machine Learning, to appear(to appear):to appear, 2001.

    Google Scholar 

  19. John McCarthy. Situations, actions and causal laws. Stanford Artificial Intelligence Project: Memo 2, also, http://www.formal.stanford.edu/jmc/mcchay69/ mcchay69. htm, 1963.

  20. J. T. Oates. Grounding Knowledge in Sensors: Unsupervised Learning for Language and Planning. PhD thesis, Department of Computer Science, University of Massachusetts, 2001.

    Google Scholar 

  21. Tim Oates, Paul R. Cohen, Marc S. Atkin and Carole R. Beal. NEO: Learning conceptual knowledge by sensorimotor interaction with an environment. In Proceedings of the First International Conference on Autonomous Agents, pages 170–177, 1997.

    Google Scholar 

  22. David Pierce and Benjamin Kuipers. Map learning with uninterpreted sensors and effectors. Artificial Intelligence Journal, 92:169–229, 1997.

    Article  Google Scholar 

  23. Marco Ramoni, Paola Sebastiani, and Paul Cohen. Multivariate clustering by dynamics. In Proceedings of the Seventeenth National Conference on AI, pages 633–638. AAAI Press/The MIT Press, 2000.

    Google Scholar 

  24. E. Rosch and C. B. Mervis. Family resemblances: Studies in the internal structure of categories. Cognitive Psychology, 7:573–605, 1975.

    Article  Google Scholar 

  25. Robert St. Amant and Paul R. Cohen. Intelligent Support for Exploratory Data Analysis. The Journal of Computational and Graphical Statistics, 1998.

    Google Scholar 

  26. Robert St. Amant and Paul R. Cohen. Interaction With a Mixed-Initiative System for Exploratory Data Analysis. Knowledge-Based Systems, 10(5):265–273, 1998.

    Article  Google Scholar 

  27. Luc Steels. The Talking Heads Experiment: Volume I. Words and Meanings. Laboratorium, Antwerpen, 1999. This is a museum catalog but is in preparation as a book.

    Google Scholar 

  28. Paul Cohen, Tim Oates, Matthew Schmill. Identifying qualitatively different outcomes of actions: Gaining autonomy through learning. In Proceedings Fourth International Conference on Autonomous Agents, pp 110–111. ACM, 2000.

    Google Scholar 

  29. Paul Cohen, Tim Oates, Matthew Schmill. A method for clustering the experience of a mobile robot that accords with human judgments. In Proceedings of Seventeenth National Conference, pp. 846–851. AAAI Press/The MIT Press, 2000.

    Google Scholar 

  30. Paul Utgo. and Paul R. Cohen. Applicability of reinforcement learning. In The Methodology of Applying Machine leraning Problem Definition, Task Decompostion and Technique Selection Workshop, ICML-98, pages 37–43, 1998.

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Department of Computer Science, University of Massachusetts, Amherst, USA

    Paul R. Cohen

  2. Department of Computer Science, University of Maryland, Baltimore County, USA

    Tim Oates

  3. Department of Mathematics, Imperial College, London, UK

    Niall Adams

  4. Department of Psychology, University of Massachusetts, Amherst, USA

    Carole R. Beal

Authors
  1. Paul R. Cohen
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Tim Oates
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Niall Adams
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Carole R. Beal
    View author publications

    You can also search for this author in PubMed Google Scholar

Editor information

Editors and Affiliations

  1. IBM, Thomas J.Watson Research Center, Room 33-237, P.O.Box 218, 10598, Yorktown, NY, USA

    Naoki Abe

  2. Dept.of Electrical Engineering and Computer Science, Tufts University, 161 College Ave., 02155, Medford, MA, USA

    Roni Khardon

  3. Medizinische Universität zu Lübeck,Inst.für Theoretische Informatik, Wallstr.40, 23560, Lübeck, Germany

    Thomas Zeugmann

Rights and permissions

Reprints and permissions

Copyright information

© 2001 Springer-Verlag Berlin Heidelberg

About this paper

Cite this paper

Cohen, P.R., Oates, T., Adams, N., Beal, C.R. (2001). Robot Baby 2001. In: Abe, N., Khardon, R., Zeugmann, T. (eds) Algorithmic Learning Theory. ALT 2001. Lecture Notes in Computer Science(), vol 2225. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-45583-3_4

Download citation

  • DOI: https://doi.org/10.1007/3-540-45583-3_4

  • Published:

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-540-42875-6

  • Online ISBN: 978-3-540-45583-7

  • eBook Packages: Springer Book Archive

Publish with us

Policies and ethics