Results 271 to 280 of about 57,258 (313)

A robust backpropagation learning algorithm for function approximation

IEEE Transactions on Neural Networks, 1994
The backpropagation (BP) algorithm allows multilayer feedforward neural networks to learn input-output mappings from training samples. Due to the nonlinear modeling power of such networks, the learned mapping may interpolate all the training points. When erroneous training data are employed, the learned mapping can oscillate badly between data points ...
David S. Chen, Ramesh C. Jain
openaire   +2 more sources

An optimal adaptive algorithm for the approximation of concave functions

Mathematical Programming, 2005
Consider a proper concave function \(f:[ 0,1] \to\mathbb R\), normalized so that \(f( 0) =0\) and \(f( 1) =1.\) \ Denote by \(f^{\prime }( \overline{x}) \) an arbitrary supergradient \(\xi \) of \(f\) at \(\overline{x},\) i.e., a supergradient \(\xi \) satisfying: \[ f( x) \leq f( \overline{x}) +\xi ( x-\overline{x} ) \text{ for all }x\in [ 0,1] \] Let
Jean Guérin, Patrice Marcotte, Gilles Savard   +2 more
openaire   +1 more source

A novel hybrid algorithm for function approximation

Expert Systems with Applications, 2008
This paper introduces a novel hybrid algorithm for function approximation. The proposed algorithm consists of a hybrid approach to develop Takagi and Sugeno's fuzzy model for function approximation. In this paper, a coarse tuning based on Takagi and Sugeno's fuzzy model is applied to identify the fuzzy structure, and also a fuzzy cluster validity index
openaire   +1 more source

A constructive neural network algorithm for function approximation

Proceedings of International Conference on Neural Networks (ICNN'96), 2002
A study of the approximation capabilities of single hidden layer neural networks leads to a strong motivation for investigating constructive learning techniques as a means of realizing established error bounds. Learning characteristics employed by constructive algorithms provide ideas for development of new algorithms applicable to the function ...
Tim Draelos, Don R. Hush
openaire   +1 more source

Function approximator design using genetic algorithms

Proceedings of 1997 IEEE International Conference on Evolutionary Computation (ICEC '97), 2002
The approximation of a mathematical function (using examples in the form of input-output pairs) is a central issue in subjects as diverse as pattern recognition, control theory and statistics. In this paper, we propose an approach for designing a universal function approximator based on a combination of trigonometric and polynomial functions using ...
M. A. Ahmed, K. A. DeJong
openaire   +1 more source

A FUNCTION APPROXIMATION ALGORITHM USING SEQUENTIAL COMPOSITION

International Journal of Neural Systems, 1993
A new method for approximating one dimensional functions is developed based on structural capabilities of multilayer feedforward neural networks. It possesses notable but unproven convergence properties which are examined in a series of examples. It is shown that it outperforms conventional networks for complicated one dimensional problems.
openaire   +2 more sources

Best Algorithms for Approximating the Maximum of a Submodular Set Function

Mathematics of Operations Research, 1978
A real-valued function z whose domain is all of the subsets of N = {1, …, n) is said to be submodular if z(S) + z(T) ≥ z(S ∪ T) + z(S ∩ T), ∀S, T ⊆ N, and nondecreasing if z(S) ≤ z(T), ∀S ⊂ T ⊆ N. We consider the problem maxS⊂N {z(S): |S| ≤ K, z submodular and nondecreasing, z(Ø) = 0}.
George L. Nemhauser, Laurence A. Wolsey
openaire   +2 more sources

An Algorithm for the Automatic Approximate Minimization of Boolean Functions

IEEE Transactions on Computers, 1968
Abstract—There are several algorithms that determine directly an irredundant normal form (INF) of a Boolean function without generating the entire set of prime implicants. These algorithms can generate solutions for the minimization problem much more rapidly than the algorithms determining minimum normal forms (MNF), and the cost of these solutions is,
openaire   +2 more sources

An Algorithm for the Approximation of the Solution of a Functional-Integral Equation

2009 11th International Symposium on Symbolic and Numeric Algorithms for Scientific Computing, 2009
In this paper we consider a functional-integral equation with linear modification of the argument. By applying the successive approximation method and by using the trapezoidal formula we give an algorithm for the approximation of the solution of this equation.
openaire   +1 more source

Tane: An Efficient Algorithm for Discovering Functional and Approximate Dependencies

The Computer Journal, 1999
Summary: The discovery of functional dependencies from relations is an important database analysis technique. We present TANE, an efficient algorithm for finding functional dependencies from large databases. TANE is based on partitioning the set of rows with respect to their attribute values, which makes testing the validity of functional dependencies ...
Ykä Huhtala, Juha Kärkkäinen, Pasi Porkka, Hannu Toivonen   +3 more
openaire   +2 more sources