The HPNEURAL Procedure
HIDDEN Statement
HIDDEN number </ ACT=activation-function>;
The HIDDEN statement specifies the number of hidden layers in the network and the number of neurons in each hidden layer. The number of HIDDEN statements specifies the number of layers in the network. The first HIDDEN statement specifies the number of hidden neurons in the first hidden layer. The second HIDDEN statement specifies the number of hidden neurons in the second hidden layer, and so on. A maximum of 100 HIDDEN statements are allowed.
You must specify number, and it must be an integer greater than or equal to 1.
You can also specify the following option:
- ACT=COS | IDENTITY | TANH
-
specifies the activation function for each hidden layer. You can specify the following values:
- COS
specifies the cosine function.
- IDENTITY
specifies the identity function.
- TANH
specifies the hyperbolic tangent function.
By default, ACT=TANH.
When training, you must include one or more HIDDEN statements, unless you specify ARCHITECTURE LOGISTIC (in which case the HIDDEN statement is not allowed). The HIDDEN statement is not allowed when you do stand-alone scoring.