From Black Boxes to IF-THEN: Explaining Deep Nets with Logic (xDNN(ASP))

Deep neural networks are powerful but often opaque. This paper introduces xDNN(ASP), a method that turns a trained network into human-readable logic rules, so you can see not just what it predicts, but why.

• It extracts a logic program (via Answer Set Programming) that aims to mirror the network's input-output behavior across all classes, giving global explanations.
• You get IF-THEN style rules that show which features matter and how hidden nodes influence decisions.
• These insights can guide pruning hidden layers to simplify and speed up the model, while keeping high accuracy.

On two synthetic datasets, the extracted program stayed accurate and offered clear, audit-ready views into the model's inner workings, from feature importance to the role of hidden nodes.

Paper: https://arxiv.org/abs/2601.03847v1

Paper: https://arxiv.org/abs/2601.03847v1

Register: https://www.AiFeta.com

#ExplainableAI #DeepLearning #MachineLearning #XAI #LogicProgramming #AnswerSetProgramming #ModelTransparency #AI