Brief Introduction of Back Propagation (BP) Neural Network Algorithm and Its Improvement

A Machine-Learning-Driven Sky Model

“…When training, the following values were used: learning rate β = 0.01 and momentum µ = 0.9, which is a commonly used momentum value for the backpropagation algorithm, see Li et al [35]. The learning rate is chosen according to the initial experiments which showed that using a smaller learning rate increases the training time and a larger value decreases the training performance.…”

Location predicting methods for UAVs

“…The back propagation (BP) [12,13] neural network algorithm is a kind of feed forward network with multiple layers, which is trained according to error back propagation algorithm BP leaning has two processes, 1) forward propagation of operating signal and 2) back propagation of error signal [10,11]. During the forward propagation process, the weight value and offset value of the network keep constant and the status of each layer of neuron affects only the next layer of neuron.…”

Using Sensors Data and Emissions Information to Diagnose Engine’s Faults

“…In this network, there is no need to disclose in advance the mathematical equation that describes these mapping relations. Its learning rule is to adopt the steepest descent method in which the back propagation is used to regulate the weight value and threshold value of the network to achieve the minimum error sum of square 13 . The BP neural network toolbox in Matlab is chosen to get the ideal fault diagnosis results in this study.…”