Some simple points for those people who know the answer.
I am amending the exams for the moment and one of the previous questions is this:
What < << em> Perceptron
I can not find any information about this in my lecture notes, and even at a loss.
My guess is that the order is the number of layers in a neural network, but it does not seem quite right.
If you want to evaluate order or cardinality < Strong> multilayered NN You should consider the number of internal layers Input and output layer is not considered related to cardinality of NN topology. For example, there is an NN order = 2 with 2 inner layers.
The most interesting thing is that more than one layer, most of the time, neither for performance, nor for training is neither for training.
Comments
Post a Comment