Consider a linear output unit versus a logistic output unit for a feed-forward network with
no hidden layer shown below. The network has a set of inputs
x
and an output neuron
y
connected to the input by weights
w
and bias
b
.
We're using the squared error cost function even though the task that we care about, in the end, is binary classification. At training time, the target output values are
1
(for one class) and
0
(for the other class). At test time we will use the classifier to make decisions in the standard way: the class of an input
x
according to our model
after training is as follows:
class of x={1 if wTx+b≥00 otherwise
Note that we will be training the network using
y
, but that the decision rule shown above will be the same at
test time, regardless of the type of output neuron we use for training. Which of the following statements is true?