No coin nor oath required. For personal study only.
Contents: Preface. Introduction. I. Foundations. 1. Logic and learning. Daniel N. Osherson, Michael Stob, and Scott Weinstein. 2. Learning theoretical terms. Ranan B. Banerji. 3. How loading complexity is affected by node function sets. Stephen Judd. 4. Defining the limits of analogical planning. Diane J. Cook. II. Representation and bias. 5. Learning hard concepts through constructive induction: Framework and rationale. Larry RendeU and Raj Seshu. 6. Learning disjunctive concepts using domain knowledge. Harish Ragavan and Larry Rendell. 7. Learning in an abstraction space. George Drastal. 8. Binary decision trees and an "average-case" model for concept learning: Implications for feature construction and the study of bias. Rej Seshu. 9. Refining algorithms with knowledgebased neural networks: Improving the Chou-Fasman algorithm for protein folding. Richard Maclin and Jude W. Shavlik. III. Sampling problems. 10. Efficient distribution-free learning of probabilistic concepts. Michael J. Kearns and Robert E. Shapire. 11. VC dimension and sampling complexity of learning sparse polynomials and rational functions. Marek Karpinski and Thorsten Werther. 12. Learning from data with bounded inconsistency: Theoretical and experimental results. Haym Hirsh and William W. Cohen. 13. How fast can a threshold gate learn? Wolfgang Maass and GySrgy Turgm. 14. When are k-nearest neighbor and backpropagation accurate for feasible-sized sets of examples? Eric B. Baum. IV. Experimental. 15. Comparing connectionist and symbolic learning methods. J.R. Quinlan. 16. Weight elimination and effective network size. Andreas S. Weigend and David E. Rumelhart. 17. Simulation results for a new two-armed bandit heuristic. Ronald L. 1%ivest and Yiqun Yin. 18. Hard questions about easy tasks: Issues from learning to play games. Susan L. Epstein. 19. Experiments on the transfer of knowledge between neural networks. Lorien Y. Pratt. Contributors. Index.
📜 SIMILAR VOLUMES