Table 1 Neural network architecture and... | Emerald Publishing

Table 1

Neural network architecture and training parameters

Parameter	Value
Framework	PyTorch
Network type	Fully connected neural network
Hidden layers	2
Neurons per hidden layer	32
Activation function	Tanh
Output activation	Sigmoid
Optimizer	Adam
Learning rate	0.001
Training epochs	2,500
Loss weight (λ)	0.1
Hardware	CPU

Parameter	Value
Framework	PyTorch
Network type	Fully connected neural network
Hidden layers	2
Neurons per hidden layer	32
Activation function	Tanh
Output activation	Sigmoid
Optimizer	Adam
Learning rate	0.001
Training epochs	2,500
Loss weight (λ)	0.1
Hardware	CPU