DocumentCode :
2785046
Title :
Polynomial threshold functions, AC functions and spectrum norms
Author :
Bruck, Jehoshua ; Smolensky, Roman
Author_Institution :
IBM Almaden Res. Center, San Jose, CA, USA
fYear :
1990
fDate :
22-24 Oct 1990
Firstpage :
632
Abstract :
The class of polynomial-threshold functions is studied using harmonic analysis, and the results are used to derive lower bounds related to AC0 functions. A Boolean function is polynomial threshold if it can be represented as a sign function of a sparse polynomial (one that consists of a polynomial number of terms). The main result is that polynomial-threshold functions can be characterized by means of their spectral representation. In particular, it is proved that a Boolean function whose L1 spectral norm is bounded by a polynomial in n is a polynomial-threshold function, and that a Boolean function whose L-1 spectral norm is not bounded by a polynomial in n is not a polynomial-threshold function. Some results for AC0 functions are derived
Keywords :
Boolean functions; polynomials; threshold logic; AC functions; Boolean function; harmonic analysis; polynomial-threshold functions; spectral representation; spectrum norms; Boolean functions; Circuits; Computational modeling; Ear; Neural networks; Polynomials;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Foundations of Computer Science, 1990. Proceedings., 31st Annual Symposium on
Conference_Location :
St. Louis, MO
Print_ISBN :
0-8186-2082-X
Type :
conf
DOI :
10.1109/FSCS.1990.89585
Filename :
89585
Link To Document :
بازگشت