Sciweavers

567 search results - page 2 / 114
» Learning All Subfunctions of a Function
Sort
View
ESANN
2003
13 years 6 months ago
Neural networks organizations to learn complex robotic functions
Abstract. This paper considers the general problem of function estimation with a modular approach of neural computing. We propose to use functionally independent subnetworks to lea...
Gilles Hermann, Patrice Wira, Jean-Philippe Urban
ESANN
2007
13 years 6 months ago
Informational cost in correlation-based neuronal networks
The cost of maintaining a given level of activity in a neuronal network depends on its size and degree of connectivity. Should a neural function require large-size fully-connected ...
Gaetano Liborio Aiello, Carlo Casarino
DM
2008
110views more  DM 2008»
13 years 5 months ago
A novel algorithm enumerating bent functions
By the relationship between the Walsh spectra at partial points and the Walsh spectra of its sub-functions, by the action of general linear group on the set of Boolean functions, ...
Qingshu Meng, Min Yang, Huanguo Zhang, Jingsong Cu...
FOCI
2007
IEEE
13 years 11 months ago
Almost All Learning Machines are Singular
— A learning machine is called singular if its Fisher information matrix is singular. Almost all learning machines used in information processing are singular, for example, layer...
Sumio Watanabe
COLT
2008
Springer
13 years 7 months ago
Almost Tight Upper Bound for Finding Fourier Coefficients of Bounded Pseudo- Boolean Functions
A pseudo-Boolean function is a real-valued function defined on {0, 1}n . A k-bounded function is a pseudo-Boolean function that can be expressed as a sum of subfunctions each of w...
Sung-Soon Choi, Kyomin Jung, Jeong Han Kim