TABLE 2.

Hyperparameters optimized for seven end-use quality traits using the uni-trait MLP model.

Hyperparameter	GPC	FPROT	FASH	MSCOR	FYELD	CODI	FSDS
Activation function	relu	relu	tanh	relu	relu	tanh	tanh
Epochs	200	200	100	150	150	200	150
Dropout	0.2	0.2	0.2	0.2	0.2	0.2	0.2
Learning rate	adaptive	adaptive	constant	adaptive	constant	adaptive	constant
No. of hidden layers	4	3	4	3	3	4	2
No. of neurons	(30, 30, 30, 30)	(24, 24, 24)	(50, 50, 25, 25)	(30, 30, 10)	(90, 90)	(100, 50, 25, 25)	(50, 50)
Regularization	0.1	0.1	0.05	0.02	0.05	0.1	0.001
Solver	Adam	Adam	SGD	L-BFGS	SGD	L-BFGS	SGD