lcoogan
/
flucoma-sc
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

move the warning about ranges where it made more sense

Browse Source
nix
Pierre Alexandre Tremblay 6 years ago
parent efab1d08b2
commit 14f78dfc21
2 changed files with 4 additions and 4 deletions
Show Stats Download Patch File Download Diff File

4
release-packaging/HelpSource/Classes/FluidMLPClassifier.schelp
Unescape Escape View File

@ -17,7 +17,7 @@ ARGUMENT:: hidden
An link::Classes/Array:: that gives the sizes of any hidden layers in the network (default is two hidden layers of three units each). An link::Classes/Array:: that gives the sizes of any hidden layers in the network (default is two hidden layers of three units each).
ARGUMENT:: activation ARGUMENT:: activation
The activation function to use for the hidden layer units. The activation function to use for the hidden layer units. Beware of the permitted ranges of each: relu (0->inf), sigmoid (0->1), tanh (-1,1).
ARGUMENT:: maxIter ARGUMENT:: maxIter
The maximum number of iterations to use in training. The maximum number of iterations to use in training.
@ -35,7 +35,7 @@ ARGUMENT:: validation
The fraction of the DataSet size to hold back during training to validate the network against. The fraction of the DataSet size to hold back during training to validate the network against.
METHOD:: identity, relu, sigmoid, tanh METHOD:: identity, relu, sigmoid, tanh
A set of convinience constants for the available activation functions. Beware of the permitted ranges of each: relu (0->inf), sigmoid (0->1), tanh (-1,1) A set of convinience constants for the available activation functions.
INSTANCEMETHODS:: INSTANCEMETHODS::

4
release-packaging/HelpSource/Classes/FluidMLPRegressor.schelp
Unescape Escape View File

@ -18,7 +18,7 @@ ARGUMENT:: hidden
An link::Classes/Array:: that gives the sizes of any hidden layers in the network (default is two hidden layers of three units each). An link::Classes/Array:: that gives the sizes of any hidden layers in the network (default is two hidden layers of three units each).
ARGUMENT:: activation ARGUMENT:: activation
The activation function to use for the hidden layer units. The activation function to use for the hidden layer units. Beware of the permitted ranges of each: relu (0->inf), sigmoid (0->1), tanh (-1,1).
ARGUMENT:: outputLayer ARGUMENT:: outputLayer
The layer whose output to return. It is negative 0 counting, where the default of 0 is the output layer, and 1 would be the last hidden layer, and so on. The layer whose output to return. It is negative 0 counting, where the default of 0 is the output layer, and 1 would be the last hidden layer, and so on.
@ -39,7 +39,7 @@ ARGUMENT:: validation
The fraction of the DataSet size to hold back during training to validate the network against. The fraction of the DataSet size to hold back during training to validate the network against.
METHOD:: identity, relu, sigmoid, tanh METHOD:: identity, relu, sigmoid, tanh
A set of convinience constants for the available activation functions. Beware of the permitted ranges of each: relu (0->inf), sigmoid (0->1), tanh (-1,1) A set of convinience constants for the available activation functions.
INSTANCEMETHODS:: INSTANCEMETHODS::

Write Preview
Loading…
Cancel
Save