Aggregating inductive expertise
Information and Control
Theory of recursive functions and effective computability
Theory of recursive functions and effective computability
Probability and plurality for aggregations of learning machines
Information and Computation
Co-learning of total recursive functions
COLT '94 Proceedings of the seventh annual conference on Computational learning theory
The Power of Pluralism for Automatic Program Synthesis
Journal of the ACM (JACM)
Functions Computable in the Limit by Probabilistic Machines
Proceedings of the 3rd Symposium on Mathematical Foundations of Computer Science
Machine Inductive Inference and Language Identification
Proceedings of the 9th Colloquium on Automata, Languages and Programming
On Identification by Teams and Probabilistic Machines
Algorithmic Learning for Knowledge-Based Systems, GOSLER Final Report
Closedness Properties in Team Learning of Recursive Functions
EuroCOLT '97 Proceedings of the Third European Conference on Computational Learning Theory
Unions of Identifiable Classes of Total Recursive Functions
AII '92 Proceedings of the International Workshop on Analogical and Inductive Inference
ALT '97 Proceedings of the 8th International Conference on Algorithmic Learning Theory
Learning recursive functions: A survey
Theoretical Computer Science
| Hi-index | 0.00 |
In this paper we investigate in which cases unions of identifiable classes are also necessarily identifiable. We consider identification in the limit with bounds on mindchanges and anomalies. Though not closed under the set union, these identification types still have features resembling closedness. For each of them we and n such that (1) if every union of n − 1 classes out of U1, ... , Un is identifiable, so is the union of all n classes; (2) there are classes U1, ... ,Un−1 such that every union of n−2 classes out of them is identifiable, while the union of n − 1 classes is not. We show that by finding these n we can distinguish which requirements put on the identifiability of unions of classes are satisfiable and which are not. We also show how our problem is connected with team learning. Copyright 2001 Elsevier Science B.V. All rights reserved.