Generating Artificial Neural Networks for Value Function Approximation in a Domain Requiring a Shifting Strategy

2013 ◽  
pp. 294-303 ◽  
Author(s):  
Ransom K. Winder
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Function Approximation ◽  
Value Function ◽  
Value Function Approximation ◽  
Shifting Strategy ◽  
Artificial Neural

scholarly journals On Global–Local Artificial Neural Networks for Function Approximation

2006 ◽  
Vol 17 (4) ◽  
pp. 942-952 ◽  
Author(s):  
D. Wedge ◽  
D. Ingram ◽  
D. Mclean ◽  
C. Mingham ◽  
Z. Bandar
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Function Approximation ◽  
Artificial Neural

scholarly journals A Non-Polynomial, Non-Sigmoidal, Bounded and Symmetric Activation Function for Feed – Forward Artificial Neural Networks

2019 ◽  
Vol 8 (12) ◽  
pp. 405-410
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Function Approximation ◽  
Activation Function ◽  
Continuous Functions ◽  
Feed Forward ◽  
Learning Tasks ◽  
Non Linear ◽  
Artificial Neural ◽  
Hidden Layer

Feed-forward artificial neural networks are universal approximators of continuous functions. This property enables the use of these networks to solve learning tasks. Learning tasks in this paradigm are cast as function approximation problems. The universal approximation results for these networks require at least one hidden layer with non-linear nodes, and also require that the non-linearities be non-polynomial in nature. In this paper a non-polynomial and non-sigmoidal non-linear function is proposed as a suitable activation function for these networks. The usefulness of the proposed activation function is shown on 12 function approximation task. The obtained results demonstrate that the proposed activation function outperforms the logistic / log-sigmoid and the hyperbolic tangent activation functions.

Sign in / Sign up

Export Citation Format

Share Document