Prediction and Evaluation of Coal Mine Coal Bump Based on Improved Deep Neural Network

Table 1

Parameters of coal bump prediction model.

Serial number	Parameter	Value
1	Number of neurons in input layer	6
2	Number of hidden layer neurons	32, 64, 16
3	Number of neurons in output layer	6
4	Hidden layer activation function	ReLU
5	Output layer activation function	Softmax
6	Loss function	Cross-entropy error
7	Suppress overfitting	Dropout method
8	Drop rate in dropout model
9	Training function	Improved Adam algorithm
10	Initial learning rate
11	Momentum coefficient
12	Error target value	0.001
13	Batch size	10
14	Training times	70