Perceptron is an artificial neural network invented by Frank Rosenblatt in 1957, which can be regarded as the simplest form of feedforward artificial neural network and a binary linear classifier.

BP neural network was developed by David Runelhart in the mid-1980s. Geoffrey Hinton, Ronald W-llians, DavidParker and others independently discovered the back propagation of errors (BP for short), systematically solved the learning problem of hidden layer connection weights of multilayer neural networks, and gave a complete mathematical derivation.

2. Different structures:

BP network adds several layers (one or more layers) of neurons between the input layer and the output layer. These neurons are called hidden units. They have no direct contact with the outside world, but the change of their state can affect the relationship between input and output, and each layer can have several nodes.

Perceptron is also called single-layer artificial neural network to distinguish it from more complex multi-layer perceptron. As a linear classifier, (single-layer) perceptron can be said to be the simplest form of forward artificial neural network.

3. Different algorithms:

The calculation process of BP neural network consists of forward calculation process and reverse calculation process. In the process of forward propagation, the input mode is processed layer by layer from the input layer through the hidden unit layer and turned to the output layer, and the state of neurons in each layer only affects the state of neurons in the next layer. Perceptron is a feedforward artificial neural network represented by feature vectors, and it is a binary classifier. The input is directly converted into the output through the weight relationship.

Baidu encyclopedia-perceptron

Baidu encyclopedia -BP neural network