An activation function adapting training algorithm for sigmoidal feedforward networks

Neurocomputing

Volumn 61, Issue 1-4, 2004, Pages 429-437

  Chandra, Pravin ^a   Singh, Yogesh ^a  

^a GURU GOBIND SINGH INDRAPRASTHA UNIVERSITY   (India)

Author keywords

Feedforward artificial neural networks; Self adaptation; Sigmoidal activation; Squashing function

Indexed keywords

ACTIVATION ENERGY; ALGORITHMS; BACKPROPAGATION; MATHEMATICAL MODELS; PERSONNEL TRAINING;

ACTIVATION FUNCTION; ACTIVATION FUNCTION ADAPTING ALGORITHM; NEURAL NETWORK TRAINING;

NEURAL NETWORKS;

ALGORITHM; ARTICLE; ARTIFICIAL NEURAL NETWORK; CALCULATION; LEARNING; MATHEMATICAL COMPUTING; PRIORITY JOURNAL; TASK PERFORMANCE;

EID: 10244235219     PISSN: 09252312     EISSN: None     Source Type: Journal    
DOI: 10.1016/j.neucom.2004.04.001     Document Type: Article

References (8)

1. Chandra P. Singh Y. A case for the self adaptation of activation functions in FFANN's Neurocomputing 56 2003 447-454
2. Cybenko G. Approximation by superposition of a sigmoidal function Math. Control, Signal Systems 2 4 1989 303-314
3. Funahashi K. On the approximate realization of continuous mappings by neural networks Neural Networks 2 3 1989 183-192
4. Hornik K. Stinchcombe M. White H. Multilayer feedforward networks are universal approximators Neural Networks 2 3 1989 359-366
5. Hornik K. Stinchcombe M. White H. Universal approximation of an unknown mapping and its derivatives using multilayer feedforward networks Neural Networks 3 4 1990 551-560
6. LeCun Y. Battou B. Orr G.B. Muller K.-R. Efficient BackProp Orr G. Muller K. (Eds.) Neural Networks: Tricks of the Trade 1998 5-50 Springer Berlin
7. Singh Y. Chandra P. A class +1 sigmoidal activation functions for FFANNs J. Econ. Dyn. Control 28 1 2003 183-187
8. Trentin T. Networks with trainable amplitude of activation functions Neural Networks 14 1992 471-493