Sciweavers

107 search results - page 11 / 22
» Polynomially Bounded Matrix Interpretations
Sort
View
DM
2010
77views more  DM 2010»
13 years 6 months ago
Representing (0, 1)-matrices by boolean circuits
A boolean circuit represents an n by n (0,1)-matrix A if it correctly computes the linear transformation y = Ax over GF(2) on all n unit vectors. If we only allow linear boolean f...
Stasys Jukna
CDC
2009
IEEE
221views Control Systems» more  CDC 2009»
13 years 10 months ago
Parametrization invariant covariance quantification in identification of transfer functions for linear systems
This paper adresses the variance quantification problem for system identification based on the prediction error framework. The role of input and model class selection for the auto-...
Tzvetan Ivanov, Michel Gevers
ICFCA
2009
Springer
14 years 1 months ago
Factor Analysis of Incidence Data via Novel Decomposition of Matrices
Matrix decomposition methods provide representations of an object-variable data matrix by a product of two different matrices, one describing relationship between objects and hidd...
Radim Belohlávek, Vilém Vychodil
UAI
2003
13 years 8 months ago
On the Convergence of Bound Optimization Algorithms
Many practitioners who use EM and related algorithms complain that they are sometimes slow. When does this happen, and what can be done about it? In this paper, we study the gener...
Ruslan Salakhutdinov, Sam T. Roweis, Zoubin Ghahra...
STOC
1993
ACM
141views Algorithms» more  STOC 1993»
13 years 10 months ago
Bounds for the computational power and learning complexity of analog neural nets
Abstract. It is shown that high-order feedforward neural nets of constant depth with piecewisepolynomial activation functions and arbitrary real weights can be simulated for Boolea...
Wolfgang Maass