arXiv Machine Learning July 24, 2026 By Arunan J

Detecting Neural Network Failures through Spectral Analysis of Internal Activations

Read the original on arXiv Machine Learning →

arXiv:2607. 20590v1 Announce Type: new Abstract: Neural network misclassifications exhibit characteristic spectral instability in internal activations that is invisible at the output layer.

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.

arXiv Computer Vision

Sep 1

Feature-Spectral Fragility in Segmentation: Dataset Dependence, Architecture-Specific Localization, and Spectral Correlates

arXiv:2608.29167v1 Announce Type: new Abstract: Robustness of segmentation models is commonly assessed through input-domain perturbations, while dependence on frequency content within learned feature...

By Subhash Kashyap

llms computer-vision

arXiv AI

Jul 15

Sparse Autoencoders for Interpretable Out-of-Distribution Detection

arXiv:2607. 12094v1 Announce Type: cross Abstract: Reliable detection of out-of-distribution (OOD) samples is crucial for the safe deployment of machine learning models.

By Ayush Karmacharya (Purdue University), Luke Luschwitz (Purdue University), Lucia Romero (Purdue University), Yanan Niu (EPFL), Joseph Campbell (Purdue University)

benchmarks

arXiv Machine Learning

Jun 25

Training Dynamics of Neural Software Defect Predictors under Coupled Data-Quality Issues

arXiv:2606. 24968v1 Announce Type: new Abstract: Context: Software defect prediction supports maintenance decisions such as testing prioritization, release-risk assessment, and quality monitoring.

By Emmanuel Charleson Dapaah, Philip Makedonski, Jens Grabowski

data-engineering

arXiv Machine Learning

Jul 15

Fisher Rank Inflation: A Spectral Signature of Memorization under Label Noise

arXiv:2607. 12438v1 Announce Type: new Abstract: Deep networks trained with label noise often learn clean structure before memorizing corrupted labels.

By Satwik Bathula, Anand A. Joshi

llms computer-vision

arXiv AI

Jun 26

Evaluation-Strategy Gap in Fault Diagnosis of Deep Learning Programs

arXiv:2606. 26492v1 Announce Type: cross Abstract: Deep Learning (DL) programs can fail during training for many reasons, and diagnosing the cause is a costly and time-consuming maintenance task.

By Sigma Jahan

arXiv Machine Learning

Aug 4

Spectral Reach: Understanding Neural Scaling as Progress into the Spectral Tail

arXiv:2605. 31244v2 Announce Type: replace Abstract: Neural scaling laws describe predictable power-law relationships between model size, dataset size, compute, and performance.

By Konstantin Nikolaou, Jonas Scheunemann, Sven Krippendorf, Samuel Tovey, Christian Holm

One email a morning, machine-written

Related stories

Feature-Spectral Fragility in Segmentation: Dataset Dependence, Architecture-Specific Localization, and Spectral Correlates

Sparse Autoencoders for Interpretable Out-of-Distribution Detection

Training Dynamics of Neural Software Defect Predictors under Coupled Data-Quality Issues

Fisher Rank Inflation: A Spectral Signature of Memorization under Label Noise

Evaluation-Strategy Gap in Fault Diagnosis of Deep Learning Programs

Spectral Reach: Understanding Neural Scaling as Progress into the Spectral Tail