Neural networks: algorithms, applications, and programming techniques
Neural networks: algorithms, applications, and programming techniques
Artificial Neural Networks: A Tutorial
Computer - Special issue: neural computing: companion issue to Spring 1996 IEEE Computational Science & Engineering
Reformulated radial basis neural networks trained by gradient descent
IEEE Transactions on Neural Networks
| Hi-index | 0.00 |
A multidimensional approximation problem and the method to solve it is the theme of this work. The problem solving is done by a RBF neural network and, for that, a RBF Sequential Learning Algorithm is described, based on [4]. Section 1 gives the mathematical background and the notations used in the algorithm description. The initialization of this algorithm is done by another algorithm, called the c-means algorithm, from section 2. The sections 3 and 4 contain the RBF sequential learning algorithm itself, in comparison with the RBF batch learning algorithm [4], [7]. A change in the initialization of weight vectors is done, versus [4]. The section 5 contains a numerical example, with all steps of c-means algorithm and several steps of RBF sequential learning algorithm.