DocumentCode :
2149206
Title :
Resource bounded measure and learnability
Author :
Lindner, Wolfgang ; Schuler, Rainer ; Watanabe, Osamu
Author_Institution :
Abt. Theor. Inf., Ulm Univ., Germany
fYear :
1998
fDate :
15-18 Jun 1998
Firstpage :
261
Lastpage :
270
Abstract :
We consider the resource bounded measure of polynomial-time learnable subclasses of polynomial-size circuits. We show that if EXP≠MA, then every PAC-learnable subclass of P/poly has EXP-measure zero. We introduce a nonuniformly computable variant of resource bounded measure and show that, for every fixed polynomial q, any polynomial-time learnable subclass of circuits of size q has measure zero with respect to P/poly. We relate our results to the question whether Boolean Circuits are polynomial-time learnable
Keywords :
Boolean algebra; computational complexity; learning (artificial intelligence); Boolean Circuits; PAC-learnable subclass; learnable subclasses; polynomial-size circuits; polynomial-time; resource bounded measure; Circuits; Computer science; Cryptography; Ear; Particle measurements; Polynomials; Q measurement; Security; Size measurement; Time measurement;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Computational Complexity, 1998. Proceedings. Thirteenth Annual IEEE Conference on
Conference_Location :
Buffalo, NY
ISSN :
1093-0159
Print_ISBN :
0-8186-8395-3
Type :
conf
DOI :
10.1109/CCC.1998.694620
Filename :
694620
Link To Document :
بازگشت