Target
Principle
of BP neural network
Definition of BP
neural network Basic structure of BP neural network Activation function of
neurons in BP neural network , transfer function of BP neural network Wavelet neural network (BP neural network with wavelet basis as transfer function ) Code link: particle swarm optimization wavelet neural network time series forecasting, particle swarm optimization wavelet neural network regression analysis, PSO-ANN time series forecasting resources - CSDN library https://download.csdn.net/download/abc991835105/88140045 neural network Parameters Passenger flow forecast based on wavelet neural network Effect diagram Result analysis Outlook
back view
The development of artificial intelligence is getting faster and faster. This article uses particle swarm algorithm to improve the time series prediction of wavelet neural network.
The principle of BP neural network
Definition of BP neural network
The artificial neural network does not need to determine the mathematical equation of the mapping relationship between input and output in advance, but only learns certain rules through its own training, and obtains the result closest to the expected output value when the input value is given. As an intelligent information processing system, the core of artificial neural network to realize its function is algorithm. BP neural network is a multi-layer feed-forward network trained by error backpropagation (referred to as error backpropagation). Its algorithm is called BP algorithm. Its basic idea is the gradient descent method. The mean square error of the actual output value and the expected output value is the smallest.
The basic structure of BP neural network
The basic BP algorithm includes two processes: forward propagation of signals and back propagation of errors. That is, the error output is calculated in the direction from input to output, while the weights and thresholds are adjusted in the direction from output to input. During forward propagation, the input signal acts on the output node through the hidden layer and undergoes nonlinear transformation to produce an output signal.