Share Email Print

Proceedings Paper

Activation function study for wavelet network
Author(s): Joao Fernando Marar; Edson C. B. Carvalho Filho; Weigang Li; Leonardo Deane Sa
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper 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.

Paper Details

Date Published: 4 April 1997
PDF: 8 pages
Proc. SPIE 3077, Applications and Science of Artificial Neural Networks III, (4 April 1997); doi: 10.1117/12.271531
Show Author Affiliations
Joao Fernando Marar, Univ Estadual Paulista and Univ. Federal de Pernambuco (Brazil)
Edson C. B. Carvalho Filho, Univ. Federal de Pernambuco (Brazil)
Weigang Li, Instituto Nacional de Pesquisas Espaciais (Brazil)
Leonardo Deane Sa, Instituto Nacional de Pesquisas Espaciais (Brazil)

Published in SPIE Proceedings Vol. 3077:
Applications and Science of Artificial Neural Networks III
Steven K. Rogers, Editor(s)

© SPIE. Terms of Use
Back to Top
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?