Autonomous Learning from the Environment


I believe that intelligent behavior of any creature is ultimately rooted in its physical abilities to perceive and act in its environment. ``Our idea of anything is our idea of its sensible effects.'' We say ice is cold, because we touch it and sense the effect. The secret of autonomous learning, I think, lies inside the process of how such sensible effects are learned by each individual system from its environment. Driven by this basic belief, I have identified three essential tasks for autonomous learning: Model Abstraction, Model Application, and Integration, and developed a unified computational framework called Predict-Surprise-Revise. This framework, when applied to concept learning tasks, yields When applied to environment learning tasks, the framework produces A good summary of this line of research is included in my recent book Autonomous Learning from the Enivronment, published by Computer Science Press.

The research also reveals several important open problems. It is not clear at all how humans construct necessary mental features when learning in a novel environment. Previous cognitive research assumes it is done by the subconscious. The LIVE system bypasses this problem by limiting the possible mental constructors to the minimal. Clearly, plenty of research needs to be done here. As a related problem, it is also not clear how high level cognitive models deal with uncertainties and errors of physical systems. I have been investigating the use of Bayesian probability theory as well as parallel computational models such as neural networks. I plan to conduct experiments on applying the above framework and its extensions to physical robots.

REFERENCES

Books

Shen, W-M.,  Autonomous Learning from the Environment (355 pages), W. H. Freeman, Computer Science Press, 1994. (Foreword by Herbert A. Simon)
Shen, W.M., Edited, Learning Actions Models, AAAI Press, 1999.

Journal Publications

  1. Shen, WM.  The Process of Discovery. Foundations of Science, 1(2), 1995.
  2. Shen, WM.  Discovery as autonomous learning from the environmentMachine Learning , 12, 143-156, 1993.
  3. Shen, WM. and H.A. Simon.  Fitness requirements for scientific theories containing recursive theoretical terms. British Journal of Philosopy of Science, 44, 641-652, 1993.
  4. Shen, WM. Discovering regularities from knowledge bases. International Journal of Intelligent Systems, 7(7), 623--636, 1992.
  5. Shen, WM. LIVE: An architecture for autonomous learning from the environment, ACM SIGART Bulletin, Special issue on Integrated Cognitive Architectures, 2(4), 151-155, 1992.
  6. Shen, WM.  Functional Transformation in AI Discovery Systems. Artificial Intelligence , 41(3), 257-272, 1989.

Book Chapters

  1. Shen, WM. 1994. Learning deterministic finite automata using local distinguishing experiments. In Computational Learning Theory and Natural Learning Systems, edited by T. Petsche and S. Judd and S. Hanson. MIT Press.
Conference Papers
  1. Shen, W.-M., Learning Finite Automata Using Local Distinguishing Experiments, IJCAI 1993.
  2. Shen, W.-M., Complementary Discrimination Learning with Decision Lists, AAAI 1992.