Sciweavers

COLT
1992
Springer
13 years 9 months ago
On the Computational Power of Neural Nets
This paper deals with finite size networks which consist of interconnections of synchronously evolving processors. Each processor updates its state by applying a "sigmoidal&q...
Hava T. Siegelmann, Eduardo D. Sontag
COLT
1992
Springer
13 years 9 months ago
Query by Committee
We propose an algorithm called query by committee, in which a committee of students is trained on the same data set. The next query is chosen according to the principle of maximal...
H. Sebastian Seung, Manfred Opper, Haim Sompolinsk...
COLT
1992
Springer
13 years 9 months ago
A Theory for Memory-Based Learning
Jyh-Han Lin, Jeffrey Scott Vitter
COLT
1992
Springer
13 years 9 months ago
Toward Efficient Agnostic Learning
In this paper we initiatean investigationof generalizationsof the ProbablyApproximatelyCorrect (PAC) learningmodelthat attemptto significantlyweakenthe target functionassumptions.T...
Michael J. Kearns, Robert E. Schapire, Linda Selli...
COLT
1992
Springer
13 years 9 months ago
Language Learning from Stochastic Input
Language learning from positive data in the Gold model of inductive inference is investigated in a setting where the data can be modeled as a stochastic process. Specifically, the...
Shyam Kapur, Gianfranco Bilardi
COLT
1992
Springer
13 years 9 months ago
On-line Learning of Rectangles
Zhixiang Chen, Wolfgang Maass
COLT
1992
Springer
13 years 9 months ago
PAC-Learnability of Determinate Logic Programs
Saso Dzeroski, Stephen Muggleton, Stuart J. Russel...
COLT
1992
Springer
13 years 9 months ago
On Learning Limiting Programs
Machine learning of limit programs (i.e., programs allowed finitely many mind changes about their legitimate outputs) for computable functions is studied. Learning of iterated lim...
John Case, Sanjay Jain, Arun Sharma
COLT
1992
Springer
13 years 9 months ago
Learning Switching Concepts
We consider learning in situations where the function used to classify examples may switch back and forth between a small number of different concepts during the course of learnin...
Avrim Blum, Prasad Chalasani
COLT
1992
Springer
13 years 9 months ago
Polynomial Time Inference of a Subclass of Context-Free Transformations
This paper deals with a class of Prolog programs, called context-free term transformations (CFT). We present a polynomial time algorithm to identify a subclass of CFT, whose progr...
Hiroki Arimura, Hiroki Ishizaka, Takeshi Shinohara