The most basic component of an artificial neural network is the activation unit.
It is made of an input, or set of n inputs (which may include a constant bias term) an 'activation' function and an output.
When we stack this units together into layers, we get a multilayer artificial neural network
Classification example:
XOR function
Let us suppose that we want to create a two layer neural network able to classify these observations.
Classification example:
XOR function
Or equivalently, we want a neural network able to create a classification region such as the yellow one.
Classification example:
XOR function
Proposed solution
More complex activation functions
Now our objective is to train our network with a gradient based method, and to somehow propagate the errors to the previous layers
Of course, with more complex architectures, the problem of computing gradients becomes an issue