Looking on the internet deeply has found these results:

were used as the activation functions is the most popular phrase on the web.

For clustering of the other 10 results on the web	were used as the activation functions 1158 results on the web More popular!
Some examples and use cases from the internet:	Some examples and use cases from the internet:
It doesn't look like this phrase is very popular! The search could not find any examples on the internet.	function (PURELIN) were used as the activation functions for the data processing from inputs to the hidden layer and from the constructed neurons to the output�... limit were used as the activation functions of the output layer. The output of hard limit is either 1 or 0 while that of symmetric hard limit is 1 or by trying various networks. The hyperbolic tangent in the hidden layer and the linear transfer function in the output layer were used as the activation functions. Hyperbolic tangents were used as the activation functions. The training algorithm used was backpropagation with Bayesian regularisation [11], as explained�... 1 representing idle�...

For clustering of the other

10 results on the web

were used as the activation functions

1158 results on the web

More popular!

It doesn't look like this phrase is very popular! The search could not find any examples on the internet.

function (PURELIN) were used as the activation functions for the data processing from inputs to the hidden layer and from the constructed neurons to the output�...
limit were used as the activation functions of the output layer. The output of hard limit is either 1 or 0 while that of symmetric hard limit is 1 or
by trying various networks. The hyperbolic tangent in the hidden layer and the linear transfer function in the output layer were used as the activation functions.
Hyperbolic tangents were used as the activation functions. The training algorithm used was backpropagation with Bayesian regularisation [11], as explained�...
1 representing idle�...