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

Kari Jaaskelainen

08 Jan 2026 — 1 min read

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

Meet GRACE: a moral governor for safer, more transparent AI

AI agents are getting powerful—so how do we make sure they do the right thing, not just the effective thing? Meet GRACE, a reason-based moral governor that keeps AI behavior aligned with human norms by separating moral reasoning from goal-driven decision-making. * Moral Module: uses deontic logic and explicit reasons

Why some fine-tuned LLMs miss phishing—and how to fix it

Not all fine-tuned LLMs spot phishing equally. A new study tests Llama 3.1 8B, Gemma 2 9B, and Mistral on high-stakes phishing detection—and uses SHAP and mechanistic interpretability to reveal why models do (or don’t) generalize. * Architecture × data diversity matters: Gemma 2 9B hits state-of-the-art performance (F1

AI that explains itself—by following the science

AI that explains itself—by following the science Black-box AI can be powerful, but it often can’t tell us why it made a decision. Concept Bottleneck Models (CBMs) try to fix that by predicting human-understandable concepts first, then the final answer. The catch: standard CBMs ignore domain-specific cause-and-effect and

Meet GenomAgent: A Team of AI Specialists for Smarter Genomics Q&A

TL;DR: Finding reliable answers in genomics is hard. GenomAgent turns one big AI into a coordinating team of specialists—and beats the current leader by 12% on a key benchmark. Genomic facts live across many databases. Standard chatbots struggle because they can’t flexibly query those sources. GeneGPT added

Read more

Meet GRACE: a moral governor for safer, more transparent AI

Why some fine-tuned LLMs miss phishing—and how to fix it

AI that explains itself—by following the science

Meet GenomAgent: A Team of AI Specialists for Smarter Genomics Q&A