Classification using information

Authors:
William Gasarch;Mark G. Pleszkoch;Frank Stephan;Mahendran Velauthapillai
Affiliations:
Department of Computer Science and Institute for Advanced Studies, University of Maryland, College Park, MD 20742, USA E-mail: gasarch@cs.umd.edu;IBM Corporation, Gaithersburg, MD 20879, USA E-mail: markp@vnet.ibm.com;Mathematical Institute of the University of Heidelberg, Im Neuenheimer Feld 294, D‐69121 Heidelberg, Germany E-mail: fstephan@math.uni‐Heidelberg.de;Department of Computer Science, Georgetown University, Washington, DC 20057, USA E-mail: mahe@cs.georgetown.edu
Venue:
Annals of Mathematics and Artificial Intelligence
Year:
1998

Citing 8
Cited 10

Aggregating inductive expertise

Information and Control
Learning via queries with teams and anomilies

COLT '90 Proceedings of the third annual workshop on Computational learning theory
Can finite samples detect singularities of real-valued functions?

STOC '92 Proceedings of the twenty-fourth annual ACM symposium on Theory of computing
Generalization versus classification

COLT '92 Proceedings of the fifth annual workshop on Computational learning theory
Learning via queries

Journal of the ACM (JACM)
Learning via queries and oracles

COLT '95 Proceedings of the eighth annual conference on Computational learning theory
The Power of Pluralism for Automatic Program Synthesis

Journal of the ACM (JACM)
Classification Using Information

AII '94 Proceedings of the 4th International Workshop on Analogical and Inductive Inference: Algorithmic Learning Theory

Induction by enumeration

Information and Computation
Learning, Logic, and Topology in a Common Framework

ALT '02 Proceedings of the 13th International Conference on Algorithmic Learning Theory
A General Theory of Deduction, Induction, and Learning

DS '01 Proceedings of the 4th International Conference on Discovery Science
On the classification of recursive languages

Information and Computation
Unifying logic, topology and learning in parametric logic

Theoretical Computer Science - Algorithmic learning theory(ALT 2002)
Inferring answers to queries

Journal of Computer and System Sciences
Absolute versus probabilistic classification in a logical setting

Theoretical Computer Science
The complexity of learning SUBSEQ (A)

ALT'06 Proceedings of the 17th international conference on Algorithmic Learning Theory
Absolute versus probabilistic classification in a logical setting

ALT'05 Proceedings of the 16th international conference on Algorithmic Learning Theory
On a syntactic characterization of classification with a mind change bound

COLT'05 Proceedings of the 18th annual conference on Learning Theory

Quantified Score

Hi-index	0.00

Visualization

Abstract

Let \mathcal{A} be a set of functions. A classifier for \mathcal{A} is a way of telling, given a function f, if f is in \mathcal{A}. We will define this notion formally. We will then modify our definition in three ways: (1) allow the classifier to ask questions to an oracle A (thus increasing the classifiers computational power), (2) allow the classifier to ask questions about f (thus increasing the classifiers information access), and (3) restrict the number of times the classifier can change its mind (thus decreasing the classifiers information access). By varying these parameters we will gain a better understanding of the contrast between computational power and informational access. We have determined exactly (1) which sets are classifiable (theorem 3.6), (2) which sets are classifiable with queries to some oracle (theorem 3.2), (3) which sets are classifiable with queries to some oracle and queries about f (theorem 5.2), and (4) which sets are classifiable with queries to some oracle, queries about f and a bounded number of mindchanges (theorem 5.2). The last two items involve the Borel hierarchy.