Road-Type Classification with Deep AutoEncoder

Algorithm 4

Road segment classification using DNN.

	Require: : size of input layer; : size of output layer
	Training set:
	Test set:
	Output: DNN structure: : Optimal weight, : number of layers
	List of labels such that is the class label of the Test set element :
(1)	Training phase:
(2)	Initialise weight parameters structure
(3)	Define number of hidden layers, , and corresponding sizes .
(4)	while optimal parameters are not obtained do
(5)	for each training sample do
(6)	Calculate neurons value using equations (1) and (2).
(7)	Obtain the predicted output using equation (3).
(8)	end for
(9)	Calculate loss using equation (4).
(10)	Obtain the updated weight parameters using equation (5).
(11)	end while
(12)	Store optimal weight parameters .
(13)	Classification phase:
(14)	for each road segment vector do
(15)	Predict class of
(16)	end for
(17)	Return