← Back to all news
arXiv Machine Learning

Neuron Activation-based Computation of Logical Explanations for Deep Neural Networks

The paper introduces a flexible symbolic framework that efficiently computes logical explanations for deep neural networks by parameterizing explanations with internal neuron activations and leveraging general-purpose logical engines like SMT solvers. Unlike previous methods that rely on specialized verifiers or are limited to individual input features, this approach is not restricted in shape and can scale to deep architectures. Experiments on image recognition and medical benchmarks demonstrate improved computational efficiency and the ability to explain networks that were previously intractable for logic-based methods.

Related stories

arXiv AI
2d ago

Predicate Neuron: Differentiable Quantization of Predicate Relations in Gradient-based Learning

The paper introduces the Native Predicate Neuron, a differentiable logic‑reasoning module that can be inserted into standard neural architectures. It learns to alternate between logical operations using a single trainable parameter and employs a dual‑nature gradient mechanism that performs hard logical operations during training while remaining differentiable for backpropagation. Experiments on Fully‑Connected, Convolutional, Recurrent, and Transformer models show that adding Predicate Neurons speeds convergence, improves accuracy, and reduces loss, especially on tasks involving monotonic reasoning or discontinuities.

By Ioannis Konstantoulas, Iliana Loi, Kyriakos Sgarbas
llmsefficiencybenchmarks
More like this →
arXiv Machine Learning
Jun 2

Normalized Relevance Measure as a Unifying Framework to Explain Neural Network Latent Structures

arXiv:2606. 00557v1 Announce Type: new Abstract: To understand how a neural network (NN) functions and makes predictions, it has become increasingly clear that analyzing only the input domain is insufficient -- one must also examine its internal inference mechanisms to capture the complete picture.

By Ping Xiong, Thomas Schnake, Gr\'egoire Montavon, Klaus-Robert M\"uller, Shinichi Nakajima
computer-vision
More like this →
arXiv AI
Jun 4

Binary Spiking Neural Networks as Causal Models

arXiv:2604. 27007v2 Announce Type: replace Abstract: We provide a causal analysis of Binary Spiking Neural Networks (BSNNs) to explain their behavior.

By Aditya Kar (CNRS, IRIT), Emiliano Lorini (CNRS, IRIT), Timoth\'ee Masquelier (CNRS, CERCO UMR5549)
More like this →
arXiv AI
Aug 19

From Abductive Explanations to Global Logical Rules for Node Classification in SGCs

The paper introduces a logic-based framework that extracts global logical rules for node classification in Simple Graph Convolution (SGC) networks. It uses minimal abductive explanations—small sets of node-feature pairs that preserve a node’s predicted class—as an intermediate step. Decision trees trained on these explanations yield compact global rules that retain high fidelity to the original SGC model, as demonstrated on benchmark datasets.

By Bryan Lima Cavalcante, Thiago Alves Rocha
benchmarks
More like this →
arXiv Machine Learning
Sep 24

NeuroRule: Making Black-Box Neural Networks Explainable through Rule-set Evolution

NeuroRule is a knowledge distillation framework that transforms high‑capacity neural networks into explainable rule‑sets. It adapts the EVOTER rule‑set evolution infrastructure to evolve propositional logic expressions that capture the neural network’s performance. The approach includes a conciseness objective to enhance explainability and demonstrates viability even without access to the original training data.

By Tapaswini Kodavanti, Hormoz Shahrzad, Risto Miikkulainen
efficiencybenchmarks
More like this →
arXiv AI
Oct 2

Auto-Formalizing Neuro-Symbolic Predictors

arXiv:2610.01519v1 Announce Type: cross Abstract: Neuro-Symbolic (NeSy) predictors incorporate prior knowledge into the prediction process of neural networks, ensuring that outputs satisfy specified...

By Samuele Bortolotti, Weixin Chen, Han Zhao, Andrea Passerini, Stefano Teso, Antonio Vergari
llmsbenchmarks
More like this →
arXiv Machine Learning
Sep 7

SMILE: Self-Explainable Multimodal Information Bottleneck for Medical Diagnosis

The paper introduces SMILE, a self‑explainable multimodal information bottleneck framework for medical diagnosis. It jointly optimizes predictive accuracy and modality‑specific explainability by selecting the most informative elements within each data modality. Experiments on diverse medical datasets show strong diagnostic performance, including a 9.1‑percentage‑point accuracy gain on the iCTCF dataset, and provide transparent, modality‑aware explanations that enhance both explainability and generalization.

By Yuqing Yang, Alexander Schmatz, Zhaozhao Ma, Changkyu Choi, Robert Jenssen, Shujian Yu
multimodalsafety
More like this →