Journal
NEURAL PROCESSING LETTERS
Volume 28, Issue 2, Pages 63-79Publisher
SPRINGER
DOI: 10.1007/s11063-008-9082-0
Keywords
activation functions; dynamical system identification; Levenberg-Marquardt algorithm
Categories
Funding
- TOBB Economics and Technology University [ETU BAP-2006/04]
- TUBITAK [107E137]
Ask authors/readers for more resources
Feedforward neural network structures have extensively been considered in the literature. In a significant volume of research and development studies hyperbolic tangent type of a neuronal nonlinearity has been utilized. This paper dwells on the widely used neuronal activation functions as well as two new ones composed of sines and cosines, and a sinc function characterizing the firing of a neuron. The viewpoint here is to consider the hidden layer(s) as transforming blocks composed of nonlinear basis functions, which may assume different forms. This paper considers 8 different activation functions which are differentiable and utilizes Levenberg-Marquardt algorithm for parameter tuning purposes. The studies carried out have a guiding quality based on empirical results on several training data sets.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available