Joao Fernando Marar,1 Edson C. B. Carvalho Filho,2 Weigang Li,3 Leonardo Deane Sa3
1Univ Estadual Paulista and Univ. Federal de Pernambuco (Brazil) 2Univ. Federal de Pernambuco (Brazil) 3Instituto Nacional de Pesquisas Espaciais (Brazil)
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.
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.
Joao Fernando Marar,Edson C. B. Carvalho Filho,Weigang Li, andLeonardo Deane Sa
"Activation function study for wavelet network", Proc. SPIE 3077, Applications and Science of Artificial Neural Networks III, (4 April 1997); https://doi.org/10.1117/12.271531
ACCESS THE FULL ARTICLE
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.
The alert did not successfully save. Please try again later.
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); https://doi.org/10.1117/12.271531