ISCI
2008
13 years 3 months ago
2008
In this paper, two modified constrained learning algorithms are proposed to obtain better generalization performance and faster convergence rate. The additional cost terms of the ...
NC
2002
13 years 4 months ago
2002
In this paper, Parallel Evolutionary Algorithms for integer weight neural network training are presented. To this end, each processor is assigned a subpopulation of potential solut...
IJCAI
1997
13 years 5 months ago
1997
Max and min operations have interesting properties that facilitate the exchange of information between the symbolic and real-valued domains. As such, neural networks that employ m...
ESANN
2003
13 years 5 months ago
2003
In this paper a neural network for approximating function is described. The activation functions of the hidden nodes are the Radial Basis Functions (RBF) whose parameters are learn...
STOC
1993
ACM
13 years 8 months ago
1993
ACM
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...
ISCAS
2005
IEEE
13 years 10 months ago
2005
IEEE
— In the context of Independent Component Analysis (ICA), we propose a simple method for online estimation of activation functions in order to blindly separate instantaneous mixt...
ICANN
2007
Springer
13 years 10 months ago
2007
Springer
Radial basis function networks (RBF) are efficient general function approximators. They show good generalization performance and they are easy to train. Due to theoretical consider...