What is the difference between a perceptron and a multi-layer perceptron?

A perceptron is a type of neural network model that is used for binary classification problems. It consists of a single layer of artificial neurons that receives input values, computes a weighted sum, and applies a threshold function to produce an output. The weights are updated during training to improve the accuracy of the model.

A multi-layer perceptron (MLP), on the other hand, is a more complex neural network model that can handle more complex tasks. It consists of multiple layers of artificial neurons, with each layer performing its own computations on the input data. The output of each layer is fed into the next layer until the final output is produced. MLPs are trained using a backpropagation algorithm, which adjusts the weights of the connections between neurons to minimize the error between the predicted output and the actual output. MLPs are commonly used in tasks such as image recognition, speech recognition, and natural language processing.