Important refinements of concept learning in the limit from positive data considerably restricting the accessibility of input data are studied. Let c be any concept; every infinite sequence of elements exhausting c is called positive presentation of c. In all learning models considered the learning machine computes a sequence of hypotheses about the target concept from a positive presentation of it. With iterative learning, the learning machine, in making a conjecture, has access to its previous conjecture and the latest data item coming in. In k-bounded example-memory inference (k is a priori fixed) the learner is allowed to access, in making a conjecture, its previous hypothesis, its memory of up to k data items it has already seen, and the next element coming in. In the case of k-feedback identification, the learning machine, in making a conjecture, has access to its previous conjecture, the latest data item coming in, and, on the basis of this information, it can compute k items and query the database of previous data to find out, for each of the k items, whether or not it is in the database (k is again a priori fixed). In all cases, the sequence of conjectures has to converge to a hypothesis
|
673
|
Language identification in the limit
– Gold
- 1967
|
|
582
|
Theory of Recursive Functions and Effective Computability
– Rogers
- 1967
|
|
474
|
From Data Mining to Knowledge Discovery: An Overview
– Fayyad, Piatetsky-Shapiro, et al.
- 1996
|
|
249
|
Inductive inference of formal languages from positive data
– Angluin
- 1980
|
|
233
|
Toward a mathematical theory of inductive inference
– Blum, Blum
- 1975
|
|
218
|
Formal Languages and their Relation to Automata
– Hopcroft, Ullman
- 1969
|
|
182
|
Finding patterns common to a set of strings
– Angluin
- 1980
|
|
173
|
Systems that learn: An introduction to learning theory for cognitive and computer scientists
– Osherson, Stob, et al.
- 1986
|
|
162
|
Comparison of identification criteria for machine inductive inference
– Case, Smith
- 1983
|
|
128
|
The process of knowledge discovery in databases: A human-centered Approach
– Brachman, Anand
- 1996
|
|
69
|
A machine independent theory of the complexity of recursive functions
– Blum
- 1967
|
|
58
|
Theory of Formal Systems
– Smullyan
- 1961
|
|
51
|
Editing by example
– Nix
- 1985
|
|
49
|
Automating the analysis and cataloging of sky surveys
– Fayyad, Djorgovski, et al.
- 1996
|
|
49
|
A guided tour across the boundaries of learning recursive languages
– Zeugmann, Lange
- 1995
|
|
48
|
Periodicity in Generations of Automata
– Case
- 1974
|
|
43
|
The power of vacillation in language learning
– Case
- 1999
|
|
39
|
Polynomial-time inference of arbitrary pattern languages
– Lange, Wiehagen
- 1991
|
|
34
|
The power of vacillation
– Case
- 1988
|
|
34
|
Knowledge acquisition from amino acid sequences by machine learning system BONSAI
– Shimozono, Shinohara, et al.
- 1994
|
|
31
|
Limes-Erkennung rekursiver Funktionen durch spezielle Strategien
– Wiehagen
- 1976
|
|
31
|
Learning elementary formal systems
– Arikawa, Shinohara, et al.
- 1992
|
|
29
|
On the role of procrastination in machine learning
– Freivalds, Smith
- 1993
|
|
29
|
Inductive inference of monotonic formal systems from positive data
– Shinohara
- 1991
|
|
25
|
Identification of unions of languages drawn from an identifiable class
– Wright
- 1989
|
|
22
|
Incremental Learning from Positive Data
– Lange, Zeugmann
- 1996
|
|
22
|
Characterizations of monotonic and dual monotonic language learning
– Lange, Zeugmann, et al.
- 1995
|
|
20
|
Set-driven and rearrangement-independent learning of recursive languages
– Lange, Zeugmann
- 1996
|
|
20
|
Pattern inference
– Shinohara, Arikawa
- 1995
|
|
19
|
Ignoring Data may be the only Way to Learn Efficiently
– Wiehagen, Zeugmann
- 1994
|
|
18
|
Inclusion is undecidable for pattern languages
– Jiang, Salomaa, et al.
- 1993
|
|
18
|
Efficient discovery of interesting statements in databases
– Kloesgen
- 1995
|
|
16
|
Selecting and reporting what is interesting
– Matheus, Piatetsky-Shapiro, et al.
- 1996
|
|
14
|
Infinitary self-reference in learning theory
– Case
- 1994
|
|
13
|
Learning recursive languages with bounded mind changes
– Lange, Zeugmann
- 1993
|
|
13
|
Inductive inference of unbounded unions of pattern languages from positive data
– Shinohara, Arimura
- 1996
|
|
12
|
Return to patterns (The Formal Language Theory
– Salomaa
- 1994
|
|
11
|
Inductive inference of Prolog programs with linear data dependency from positive data
– Arimura, Shinohara
- 1994
|
|
9
|
Open problems in systems that learn
– Fulk, Jain, et al.
- 1994
|
|
9
|
and Wiehagen's pattern language learning algorithm: An average-case analysis with respect to its total learning time
– Lange
- 1997
|
|
8
|
Inferring unions of two pattern languages
– Shinohara
- 1983
|
|
7
|
The relation of two patterns with comparable languages
– Fil'e
- 1988
|
|
7
|
and Wiehagen's Pattern Language Learning Algorithm: An Averagecase Analysis with respect to its Total Learning Time
– Zeugmann, Lange
- 1995
|
|
7
|
On monotonic strategies for learning r.e. languages
– Jain, Sharma
- 1994
|
|
6
|
A class of Prolog programs inferable from positive data
– Rao
- 1996
|
|
6
|
The power of vacillation, in "Proceedings 1st Workshop on Computational Learning Theory
– Case
- 1988
|
|
5
|
Probabilistic language learning under monotonicity constraints
– Meyer
- 1995
|
|
4
|
Learning elementary formal systems, Theoretical Computer Science 95
– Arikawa, Shinohara, et al.
- 1992
|
|
4
|
On identification by teams and probabilistic machines
– Jain, Sharma
- 1995
|
|
2
|
Monotonic and dual monotonic probabilistic language learning of indexed families with high probability
– Meyer
- 1997
|
|
