A Novel Framework Design of Network Intrusion Detection Based on Machine Learning Techniques

Algorithm 1

The training procedures of SAE.

	Input: training dataset
	Output: trained SAE model
	Initialization:
	Step 1: perform forward propagation on all input samples
	Step 2: calculate the output of each node a in the hidden layer (equation (1))
	Step 3: calculate the output error of the cost function (equation (3))
	Step 4: updating the weights and biases of each layer using the backpropagation algorithm to reduce errors
	Step 5: repeat Step 2, 3, and 4 until the reconstruction error is minimum
	End