Can multilayer sensory supervised learning be understood as BP neural networks?

The multilayer perceptron is not a specific neural network, it is a neural network model.

The model of the BP neural network is indeed a multi-layer perceptron, but the BP neural network uses the BP algorithm to optimize the network, which can be understood as.

BP Neural Network = Multilayer Perceptron + BP Algorithm.

Neural network learning mainly refers to the use of learning algorithms to adjust the connection rights between neurons, so that the network output is more realistic. Learning algorithms are divided into two categories: supervised learning and unsupervised learning

1. The supervised learning algorithm feeds a set of training sets into the network, and adjusts the connection rights according to the difference between the actual output of the network and the expected output. The main steps of a supervised learning algorithm include:

a) take a sample (AI, BI) from the sample set;

b) calculate the actual output of the network;

c) Find d = bi o;

d) Adjust the weight matrix according to d;

e) Repeat the above process for each sample until the error does not exceed the specified range for the entire sample set.

The BP algorithm is an excellent supervised learning algorithm.

2. Unsupervised learning extracts the statistical characteristics contained in the sample set and stores them in the network in the form of connection rights between neurons. HEBB learning rate is a typical unsupervised learning algorithm.

The BP algorithm of the multilayer perceptron MLP is supervised learning.

The BP algorithm in MLP learning is composed of two learning processes: the forward propagation of signals and the backpropagation of errors. In the forward propagation, the input sample is transmitted from the input layer, and after being processed layer by layer of each hidden layer, it is transmitted to the output layer. If the output layerThe actual output does not match the expected output (teacher signal)., then it moves to the backpropagation phase of the error.

Error backpropagation is to reverse the output error to the input layer layer by layer through the hidden layer in some form, and distribute the error to all the elements of each layer, so as to obtain the error signal of each layer unit, and this error signal is used as the basis for correcting the weight of each element. The process of adjusting the weights of each layer of the forward propagation of the signal and the reverse propagation of the error is carried out repeatedly. The process of continuous adjustment of the weight, that is, the learning and training process of the network.

This process continues until the error in the network output is reduced to an acceptable level, or until a pre-set number of learnings is reached.

Introduction to the BP algorithm.