Multilayer Perceptrons

Multilayer perceptrons are feedforward neural networks having at least three layers of neurons, including an input layer, at least one hidden layer and a single output layer. The activation functions of the input layer is usually the identity function, while the activation functions of the neurons in the hidden and output layers can be, in general, a mathematical function which continuous first and second order derivatives. Example of activation functions are identity, logistic sigmoid, hyperbolic tangent, exponential and sine activation functions.