A multilayer perceptron is a feedforward neural network with an input layer, one or more hidden layers, and an output layer. It learns nonlinear relationships by applying weighted connections and activation functions across layers.
In deep learning, a multilayer perceptron (MLP) is a name for a modern feedforward neural network consisting of fully connected neurons with nonlinear activation functions, organized in layers, notable for being able to distinguish data that is not linearly separable.