Glass Box Neural Networks

[#1]

Neural network models are typically described as “black boxes” because their inner workings are not easy to understand. We propose that, since a neural network model that accurately predicts its target variable is a good representation of the training data, the output of the model may be recast as a target variable and subjected to standard regression algorithms to “explain” it as a response variable. Thus, the “black box” of the internal mechanism is transformed into a “glass box” that facilitates understanding of the underlying model.

[sbxkoenk]

Hello,

I often use that technique as well. Works good !

Since VIYA, I also use :

• Partial Dependence Plots (PD-plots)
• Individual Conditional Expectation Plots (ICE-plots)
• Local Interpretable Model-agnostic Explanations (LIME) visualisations
• Shapley values (shapleyExplainer action)

Much info on the above can be found when Googling ( include SAS key-word when you are searching !! )

Koen