Abstract:
In this paper, separable functional network architecture and a learning algorithm of separable functional network are proposed, the learning of functional parameters use ...Show MoreMetadata
Abstract:
In this paper, separable functional network architecture and a learning algorithm of separable functional network are proposed, the learning of functional parameters use Lagrange multipliers by means of auxiliary function and solving a system of linear equations obtain parameters. An experiment in approximating typical continuous functions is given. The results show that the learning algorithm presented in the paper has excellent performance in approximation error.
Published in: 2008 IEEE International Conference on Granular Computing
Date of Conference: 26-28 August 2008
Date Added to IEEE Xplore: 31 October 2008
ISBN Information: