摘要: This paper reports on recent progress in the study of autonomous concept learning systems. In such systems, initial space hypotheses is considered as a first-order sentence, declarative bias, and can thus be derived from background knowledge concerning goal concept. It easy to show that simple derivation process generates language corresponding an unbiased version defined restricted instance description language. However, structure typical corresponds stronger restriction still. shown this semantically-motivated, tree-structured bias fact reduce size doubly-exponential singly-exponential number features. allows effective small examples.
参考文章(13)
Richard M. Keller, Defining operationality for explanation-based learning national conference on artificial intelligence. pp. 482- 487 ,(1987)
Haym Hirsh, Explanation-based generalization in a logic-programming environment international joint conference on artificial intelligence. pp. 221- 227 ,(1987)
Stuart J. Russell, Benjamin N. Grosof, A declarative approach to bias in concept learning national conference on artificial intelligence. pp. 505- 510 ,(1987)
SRIDHAR MAHADEVAN, PRASAD TADEPALLI, On the tractability of learning from incomplete theories international conference on machine learning. pp. 235- 241 ,(1988) , 10.1016/B978-0-934613-64-4.50030-X
S. J. Russell, Analogical and inductive reasoning Stanford University. ,(1987)
Eugene Charniak, None, Introduction to Artificial Intelligence ,(1985)
David Haussler, Quantifying inductive bias: AI learning algorithms and Valiant's learning framework Artificial Intelligence. ,vol. 36, pp. 177- 221 ,(1988) , 10.1016/0004-3702(88)90002-1
Tom M Mitchell, None, Generalization as search Artificial Intelligence. ,vol. 18, pp. 203- 226 ,(1982) , 10.1016/0004-3702(82)90040-6
L. G. Valiant, A theory of the learnable symposium on the theory of computing. ,vol. 27, pp. 1134- 1142 ,(1984) , 10.1145/800057.808710
Stuart J. Russell, Todd Davies, A Logical Approach to Reasoning by Analogy Social Science Research Network. ,(1987)