Development of Predictive Techniques for Estimating Liquid Water-Hydrate Equilibrium of Water-Hydrocarbon System

Table 11

Number of neurons, hidden layers, parameters, data and type of activation function used in the ANN algorithm [4]. (Number of hidden layers = 1, number of parameters = 5, number of data used for training (and testing) = 44, type of activation function: linear, input neurons: temperature and carbon number of single hydrocarbon hydrate former representing the type of hydrocarbon, output neuron: logarithm of solubility of single hydrocarbon hydrate former being in equilibrium with gas hydrates.)

Layer	Number of neurons
1	2
2	1
3	1