In PROC HPNEURAL, which activation function is specified for hidden layer neurons using the HIDDEN statement?
Select an answer to reveal the explanation.
Short Explanation and Infographic
Here's the deal — b is correct because PROC HPNEURAL supports the ACTFUNC= option within the HIDDEN statement to specify the activation function for that hidden layer, with options including TANH, LOGISTIC, and others. A is wrong because activation functions can be specified and are not locked to sigmoid.
Full explanation below image
Full Explanation
B is correct because PROC HPNEURAL supports the ACTFUNC= option within the HIDDEN statement to specify the activation function for that hidden layer, with options including TANH, LOGISTIC, and others. A is wrong because activation functions can be specified and are not locked to sigmoid. C is wrong because the specification is per layer via the HIDDEN statement. D is wrong because the INPUT statement's TYPE= option describes input normalization, not hidden layer activation.