Skip to main content

Table 1 Parameters for the MLP classifier included in scikit-learn0.18.1. These are the same as commonly used values. See Kingma and Ba (2015) for the meanings of the parameters for the Adam optimizer

From: Segmentation of dust storm areas on Mars images using principal component analysis and neural network

Parameter

Value

Penalty for regularization

0.0001

Batch size

200

Tolerance of optimization

10−4

Whether to shuffle samples in each iteration

True

Whether to use early stopping to terminate training when the validation score is not improving

False

β1 for adam

0.9

β2 for adam

0.999

ϵ for adam

10−8