4 April 1997 Activation function study for wavelet network
Author Affiliations +
Abstract
The main purpose of this paper is to investigate theoretically and experimentally the use of family of Polynomial Powers of the Sigmoid (PPS) Function Networks applied in speech signal representation and function approximation. This paper carries out practical investigations in terms of approximation fitness (LSE), time consuming (CPU Time), computational complexity (FLOP) and representation power (Number of Activation Function) for different PPS activation functions. We expected that different activation functions can provide performance variations and further investigations will guide us towards a class of mappings associating the best activation function to solve a class of problems under certain criteria.
© (1997) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Joao Fernando Marar, Edson C. B. Carvalho Filho, Weigang Li, Leonardo Deane Sa, "Activation function study for wavelet network", Proc. SPIE 3077, Applications and Science of Artificial Neural Networks III, (4 April 1997); doi: 10.1117/12.271531; https://doi.org/10.1117/12.271531
PROCEEDINGS
8 PAGES


SHARE
KEYWORDS
Back to Top