In artificial neural networks, the sigmoid and complementary log log activation functions are similar in shape when plotted on a graph. I would like to know when to use the two functions and their pros and cons. Thanks in advance :)
$\begingroup$
$\endgroup$
1
-
$\begingroup$ "Sigmoid" just means s-shaped curve. I gather you are referring to the logit function here. You may want to read: Difference between logit and probit models. $\endgroup$– gung - Reinstate MonicaApr 21, 2017 at 16:57
Add a comment
|
1 Answer
$\begingroup$
$\endgroup$
1
This paper is behind a pay-wall but is one of the only references that I've found.
Gecynalda S. da S. Gomes & Teresa B. Ludermir. "Complementary Log-Log and Probit: Activation Functions Implemented in Artificial Neural Networks"
The types of activation functions most often used in artificial neural networks are logistic and hyperbolic tangent. Activation functions used in ANN have been said to play an important role in the convergence of the algorithms used. This paper uses sigmoid functions in the processing units of neural networks. Such functions are commonly applied in statistical regression models. The nonlinear functions implemented here are the inverse of complementary log-log and probit link functions. A Monte Carlo framework is presented to evaluate the results of prediction power with these nonlinear functions.
-
$\begingroup$ I highly appreciate your answer. I will look into this reference. Thank You :) $\endgroup$ Jun 3, 2018 at 13:30