scholarly journals Computing the moments of k-bounded pseudo-Boolean functions over Hamming spheres of arbitrary radius in polynomial time

2012 ◽  
Vol 425 ◽  
pp. 58-74 ◽  
Author(s):  
Andrew M. Sutton ◽  
L. Darrell Whitley ◽  
Adele E. Howe
1996 ◽  
Vol 8 (2) ◽  
pp. 403-415 ◽  
Author(s):  
Pekka Orponen

We prove that polynomial size discrete Hopfield networks with hidden units compute exactly the class of Boolean functions PSPACE/poly, i.e., the same functions as are computed by polynomial space-bounded nonuniform Turing machines. As a corollary to the construction, we observe also that networks with polynomially bounded interconnection weights compute exactly the class of functions P/poly, i.e., the class computed by polynomial time-bounded nonuniform Turing machines.


1992 ◽  
Vol 03 (01) ◽  
pp. 41-54
Author(s):  
PAOLA CAMPADELLI ◽  
ANNA MORPURGO

This paper deals with learnability from positive examples of subclasses of linearly separable boolean functions in the framework of the probably approximately correct learning model. We prove that classes of functions defined by binary threshold neurons with n inputs and g(n) unknown weights are learnable in polynomial time iff g(n)=O(log n) and give an upper and a lower bound on the sample size.


2020 ◽  
Vol 69 ◽  
Author(s):  
Miloš Chromý ◽  
Ondřej Čepek

In this paper, we focus on a less usual way to represent Boolean functions, namely on representations by switch-lists, which are closely related to interval representations. Given a truth table representation of a Boolean function f the switch-list representation of f is a list of Boolean vectors from the truth table which have a different function value than the preceding Boolean vector in the truth table. The main aim of this paper is to include this type of representation in the Knowledge Compilation Map by Darwiche and Marquis and to argue that switch-lists may in certain situations constitute a reasonable choice for a target language in knowledge compilation. First, we compare switch-list representations with a number of standard representations (such as CNF, DNF, and OBDD) with respect to their relative succinctness. As a by-product of this analysis, we also give a short proof of a longstanding open question proposed by Darwiche and Marquis, namely the incomparability of MODS (models) and PI (prime implicates) representations. Next, using the succinctness result between switch-lists and OBDDs, we develop a polynomial time compilation algorithm from switch-lists to OBDDs. Finally, we analyze which standard transformations and queries (those considered by Darwiche and Marquis) can be performed in polynomial time with respect to the size of the input if the input knowledge is represented by a switch-list. We show that this collection is very broad and the combination of polynomial time transformations and queries is quite unique. Some of the queries can be answered directly using the switch-list input, others require a compilation of the input to OBDD representations which are then used to answer the queries.


1997 ◽  
Vol 26 (1) ◽  
pp. 93-109 ◽  
Author(s):  
Endre Boros ◽  
Peter L. Hammer ◽  
Toshihide Ibaraki ◽  
Kazuhiko Kawakami

2018 ◽  
Vol 60 (2) ◽  
pp. 360-375
Author(s):  
A. V. Vasil'ev ◽  
D. V. Churikov

Sign in / Sign up

Export Citation Format

Share Document