Table 1 The specifications of the suggested MLP.

From: Thermal neutron beam optimization for PGNAA applications using Q-learning algorithm and neural network

Network parameters

MLP

Number of inputs (xi)

5

Number of neurons in the first hidden layer

300

Number of neurons in the second hidden layer

200

Number of neurons in the third hidden layer

200

Number of neurons in the fourth hidden layer

200

Number of neurons in the fifth hidden layer

200

Number of neurons in the sixth hidden layer

200

Number of neurons in the seventh hidden layer

100

Number of outputs

1

Activation function of hidden and output layers

Relu function

Optimizer

Rmsprop = 0.001

Epoch

2500

Loss

0.001