How can Activation function do its task?

Question

I have a simple question. I know that the main purpose of activation function is to convert an input signal of a node to an output signal. And that output signal is gonna used as an input in the next layer. But I dont have any idea about the way that activation function such as sigmoid do this in classification problem. All I know is about converting. Could any one pleas clarify this to me? Thanks!

Sure. I want to know that how do activation functions do their tasks. How can their define the output of a neuron given an input or set of input. Or simply explain that what is the role of activatom function. Thanks — Z Bokaee, Jan 16 '19 at 09:32
I think you have a confusion, because activations don't do tasks, they are just functions (like max(0, x)) used to introduce non-linear behavior in the network. How the output is defined is just the mathematical expression of the activation function. — Dr. Snoopy, Jan 16 '19 at 09:34
Thank you for your answer. I edited my quesion with a picture of an slide in Andrew Ng machine learning class. As you see there are 3 layers input hidden and output. As you see in the hidden layer we have activation of each unit. I want to know tabout the definition of it and discover why he wrote activation into each neuron — Z Bokaee, Jan 16 '19 at 10:07
Sorry but that is not really on-topic here, its not a programming question. Your question belongs to http://stats.stackexchange.com/ — Dr. Snoopy, Jan 16 '19 at 10:10

score 2 · Answer 1 · answered Jan 16 '19 at 09:11

In simple terms the function gets inputs and assigns some weights to the inputs. Then the activation function calculates the value (eg :- Sigmoid). Then it compares the value with the threshold value assigned . If its more than the threshold value then it backtracks (back propagation Algorithm). and adjusts the weights. You can find more details at https://en.wikipedia.org/wiki/Backpropagation

How can Activation function do its task?

1 Answers1