Interpolation Mechanism of Functional Networks

In this paper, the interpolation mechanism of functional networks is discussed. A kind of fourlayer (with 1 input and 1 output unit) and a five-layer (with double input and single output unit) functional network are designed. Meanwhile, a learning algorithm based on Minimizing a least squares error function with a unique minimum has been proposed for the purpose of approximating function. Experimental results indicate that the interpolation method is completely correct.

• Type: Conference
• Year: 2005
• Where: ICANN
• Authors: Yong-Quan Zhou, Licheng Jiao
• Keywords: Functional Network, ICANN 2005, Output Unit, Single Output Unit