May 2020
Intermediate to advanced
530 pages
17h 8m
English
The linear activation function, y = c x, is a straight line and is proportional to the input (that is, the weighted sum on this neuron). Such a choice of activation function allows us to get a range of values, not just a binary answer. We can connect several neurons and if more than one neuron is activated, the decision is made based on the choice of, for example, the maximum value.
The following diagram shows what the linear activation function looks like:

The derivative of y = c x with respect to x is c. This conclusion means that the gradient has nothing to do with the argument of the function. The gradient ...
Read now
Unlock full access