Question: ANN- multi-layer perceptron question. A classifier that uses backpropagation to learn a multi-layer perceptron to classify instances. The network can be built by hand or
ANN- multi-layer perceptron question.
"A classifier that uses backpropagation to learn a multi-layer perceptron to classify instances. The network can be built by hand or set up using a simple heuristic. The network parameters can also be monitored and modified during training time. The nodes in this network are all sigmoid (except for when the class is numeric, in which case the output nodes become unthresholded linear units)."
The previous statement is from Weka, i'm using regression at the moment, so my questions are:
1- Are they saying that in regression (activation function of the hidden layers are sigmoid and the outputs are unthresholded linear units)?
2- I need more explanation about unthresholded linear units? because I do not know what it does mean
3- is it realistic to use sigmoid in hidden layer and unthresholded linear units in output layers in regression?
Step by Step Solution
There are 3 Steps involved in it
Get step-by-step solutions from verified subject matter experts
