Open AccessJournal Article
Learning from examples
About:
This article is published in Bulletin of The Polish Academy of Sciences-technical Sciences.The article was published on 1986-01-01 and is currently open access. It has received 32 citations till now. The article focuses on the topics: Algorithmic learning theory & Inference.read more
Citations
More filters
Dissertation
Attribute-Oriented Induction in Relational Databases.
TL;DR: An attributeoriented induction method to extract characteristic rules and classification rules from relational databases that adopts the artificial intelligence "learning from examples" paradigm and applies an attribute-oriented concept tree ascending technique in the learning process which provides a simple, efficient way of learning from large databases.
Journal ArticleDOI
Influence of prior knowledge on concept acquisition: Experimental and computational results.
TL;DR: It is demonstrated that prior knowledge can influence the rate of concept learning and that the influence of prior causal knowledge can dominate the influenceof the logical form.
Journal ArticleDOI
Statistical theory of learning curves under entropic loss criterion
Shun-ichi Amari,Noboru Murata +1 more
TL;DR: A universal property of learning curves is elucidated, which shows how the generalization error, training error, and the complexity of the underlying stochastic machine are related and how the behavior of a stochastics machine is improved as the number of training examples increases.
Proceedings ArticleDOI
Characterizing research in computing education: a preliminary analysis of the literature
Lauri Malmi,Judy Sheard,Simon,Roman Bednarik,Juha Helminen,Ari Korhonen,Niko Myller,Juha Sorva,Ahmad Taherkhani +8 more
TL;DR: It is found that this subset of computing education research has more in common with research in information systems than with that in computer science or software engineering; and that the papers published at ICER generally appear to conform to the specified ICER requirements.
Journal ArticleDOI
How tight are the Vapnik-Chervonenkis bounds?
David Cohn,Gerald Tesauro +1 more
TL;DR: It is found that, in some cases, the average generalization of neural networks trained on a variety of simple functions is significantly better than the VC bound: the approach to perfect performance is exponential in the number of examples m, rather than the 1/m result of the bound.