arXiv Machine Learning June 2, 2026 By Ping Xiong, Thomas Schnake, Gr\'egoire Montavon, Klaus-Robert M\"uller, Shinichi Nakajima

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

Read the original on arXiv Machine Learning →

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.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

computer-vision

arXiv Machine Learning

Sep 15

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.

By Tom\'a\v{s} Kol\'arik, Faezeh Labbaf, Fabrizio Leopardi, Grigory Fedyukovich, Michael Wand, Natasha Sharygina

computer-vision benchmarks

arXiv Machine Learning

Sep 1

Integrating attention into explanation frameworks for language and vision transformers

arXiv:2508.08966v2 Announce Type: replace Abstract: The attention mechanism lies at the core of the transformer architecture, providing an interpretable model-internal signal that has motivated a gro...

By Marte Eggen, Jacob Lysn{\ae}s-Larsen, Inga Str\"umke

llms computer-vision nlp benchmarks

arXiv Machine Learning

Aug 4

LAYA: Layer-wise Attention Aggregation for Interpretable Depth-Aware Neural Networks

arXiv:2511. 12723v2 Announce Type: replace Abstract: Deep neural networks typically rely on the representation produced by their final hidden layer to make predictions, implicitly assuming that this single vector fully captures the semantics encoded across all preceding transformations.

By Gennaro Vessio

rag computer-vision safety

arXiv Machine Learning

Aug 18

Beyond $L_2$: Generalizing Abductive Latent Explanations to Diverse Prototype-Based Architectures

arXiv:2608. 16773v1 Announce Type: new Abstract: Prototype-based neural networks are hailed as interpretable-by-design architectures.

By Jules Soria, Alban Grastien, Romain Xu-Darme, Julien Girard-Satabin, Zakaria Chihani, Daniela Cancila

diffusion benchmarks safety

arXiv Machine Learning

Sep 1

Tracing distinguishability through transformer processing with stochastic LayerNorm

arXiv:2608.30720v1 Announce Type: new Abstract: Representational similarity is foundational to analyses of deep networks, yet distances between point-valued representations are not intrinsically tied...

By Kieran Murphy

llms fine-tuning efficiency safety

arXiv AI

Jun 10

Visual-TCAV: Concept-based Attribution and Saliency Maps for Post-hoc Explainability in Image Classification

arXiv:2411. 05698v3 Announce Type: replace-cross Abstract: Convolutional Neural Networks (CNNs) have shown remarkable performance in image classification.

By Antonio De Santis, Riccardo Campi, Matteo Bianchi, Marco Brambilla

computer-vision benchmarks safety

One email a morning, machine-written

Related stories

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

Integrating attention into explanation frameworks for language and vision transformers

LAYA: Layer-wise Attention Aggregation for Interpretable Depth-Aware Neural Networks

Beyond $L_2$: Generalizing Abductive Latent Explanations to Diverse Prototype-Based Architectures

Tracing distinguishability through transformer processing with stochastic LayerNorm

Visual-TCAV: Concept-based Attribution and Saliency Maps for Post-hoc Explainability in Image Classification