• Summary
• Related Documents
  • Active Bibliography
  • Co-citation
• Version History

Abstract:

of Philosophy We consider three problems in machine learning: ffl concept learning in the PAC model ffl mobile robot environment learning ffl learning-based approaches to protein structure prediction In the PAC framework, we give an efficient algorithm for learning any function on k terms by general DNF. On the other hand, we show that in a well-studied restriction of the PAC model where the learner is not allowed to use a more expressive hypothesis (such as general DNF), learning most symmetric functions on k terms is NP-hard. In the area of mobile robot environment learning, we introduce the problem of piecemeal learning an unknown environment. The robot must learn a complete map of its environment, while satisfying the constraint that periodically it has to return to its starting position (for refueling, say). For environments that can be modeled as grid graphs with rectangular obstacles, we give two piecemeal learning algorithms in which the robot traverses a linear number of edges.

Citations