Macroscopic Rock Texture Image Classification Using a Hierarchical Neuro-Fuzzy Class Method

Table 7

Configurations of neural networks used in the macro classification of gneiss and basalt; diabase, and rhyolite; basalt, diabase, and rhyolite; gneiss, basalt, diabase, and rhyolite

Rock	Database test	Number of layers	Number of neurons in input layer	Number of neurons in first hidden layer	Number of neurons in second hidden layer	Number of neurons in output layer
Gneiss and basalt	Gneiss and basalt1		3	6
	Gneiss and basalt2	3	9	10	—	2
	Gneiss and basalt3		12	10
Diabase and rhyolite	Diabase and rhyolite1		3	20	25
	Diabase and rhyolite2	4	9	25	20	2
	Diabase and rhyolite3		12	20	25
Basalt, diabase and rhyolite	Basalt, diabase, and rhyolite1		3
	Basalt, diabase, and rhyolite2	4	9	40	30	3
	Basalt, diabase, and rhyolite3		12
Gneiss, basalt, diabase, and rhyolite	Gneiss, basalt, diabase, and rhyolite1		3
	Gneiss, basalt, diabase, and rhyolite2	4	9	40	40	4
	Gneiss, basalt, diabase, and rhyolite3		12