SIAMCOMP
2011
13 years 7 months ago
2011
Abstract. In the 2nd Annual FOCS (1961), Chao-Kong Chow proved that every Boolean threshold function is uniquely determined by its degree-0 and degree-1 Fourier coefficients. These...
COMBINATORICA
2010
13 years 10 months ago
2010
Consider the following one-player game. The vertices of a random graph on n vertices are revealed to the player one by one. In each step, also all edges connecting the newly reveal...
NCA
2006
IEEE
14 years 20 days ago
2006
IEEE
The use of multilayer perceptrons (MLP) with threshold functions (binary step function activations) greatly reduces the complexity of the hardware implementation of neural networks...
IPL
2006
14 years 21 days ago
2006
Weighted threshold functions with positive weights are a natural generalization of unweighted threshold functions. These functions are clearly monotone. However, the naive way of ...
COLT
2008
Springer
14 years 2 months ago
2008
Springer
In recent work, Kalai, Klivans, Mansour, and Servedio [KKMS05] studied a variant of the "Low-Degree (Fourier) Algorithm" for learning under the uniform probability distr...
ASPDAC
2008
ACM
14 years 2 months ago
2008
ACM
Scaling is currently the most popular technique used to improve performance metrics of CMOS circuits. This cannot go on forever because the properties that are responsible for the ...
COLT
1999
Springer
14 years 5 months ago
1999
Springer
We study the learnability of Threshold functions with bounded weights using membership queries only. We show that the class Ct of Threshold functions with positive integer weights...
FUZZY
2001
Springer
14 years 5 months ago
2001
Springer
In the paper a new approach to building a MOS threshold element and an arti cial neuron on its base is discussed. The implementability of the known MOS threshold elements is restri...
COCO
2009
Springer
14 years 7 months ago
2009
Springer
We prove two main results on how arbitrary linear threshold functions f(x) = sign(w · x − θ) over the n-dimensional Boolean hypercube can be approximated by simple threshold f...