Properties of the Hermite Activation Functions in a Neural Approximation Scheme
- Cite this paper as:
- Beliczynski B. (2007) Properties of the Hermite Activation Functions in a Neural Approximation Scheme. In: Beliczynski B., Dzielinski A., Iwanowski M., Ribeiro B. (eds) Adaptive and Natural Computing Algorithms. ICANNGA 2007. Lecture Notes in Computer Science, vol 4432. Springer, Berlin, Heidelberg
The main advantage to use Hermite functions as activation functions is that they offer a chance to control high frequency components in the approximation scheme. We prove that each subsequent Hermite function extends frequency bandwidth of the approximator within limited range of well concentrated energy. By introducing a scalling parameter we may control that bandwidth.
Unable to display preview. Download preview PDF.