arXiv Machine Learning
Efficient Architecture Search under Leave-One-Subject-Out Evaluation
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
arXiv AI
Sep 11
Efficient Leakage-Free Neural Architecture Search under Leave-One-Subject-Out Evaluation
The paper introduces a leakage‑free, block‑based method for Neural Architecture Search (NAS) that shares runs across subjects, thereby avoiding the quadratic cost of a fully nested Leave‑One‑Subject‑Out (LOSO) evaluation. Applied to the BioVid Heat Pain dataset, the approach raises mean accuracy from 82.79 % to 83.39 % and can cut model parameters by up to 99.2 %.
Hugging Face Trending Papers
Jul 22
An Exploratory Analysis of Pain Localization via Explainable Computational Modeling
Automatic pain localization, which involves identifying the anatomical origin of pain from peripheral physiological signals without patient self-report, is a clinically critical but largely unaddressed problem, particularly for non-verbal patients. This paper presents a systematic comparison of classical feature engineering and deep sequence learning for subject-independent three-class pain localization using the AI4Pain 2026 Challenge dataset, which comprises four synchronously recorded wearable modalities: electrodermal activity, blood volume pulse, respiration, and peripheral oxygen saturation recorded from 65 participants under controlled TENS-induced pain.
arXiv Machine Learning
Aug 27
ONNX-Net: Towards Universal Representations and Instant Performance Prediction for Neural Architectures
ONNX-Net introduces a universal representation for neural architectures using natural language descriptions, enabling instant performance prediction across diverse search spaces. The authors present ONNX-Bench, a benchmark of over 600k architecture–accuracy pairs compiled from open‑source NAS‑bench networks in ONNX format. Experiments demonstrate strong zero‑shot predictive performance with minimal pretraining, overcoming the limitations of cell‑based, graph‑encoded approaches.
arXiv AI
Jun 9
Seq103: A Unified Neuroevolution Framework for Compact Sequence Architecture Discovery
arXiv:2606. 07664v1 Announce Type: cross Abstract: Neuroevolution is a representative neural architecture search paradigm that evolves both network topology and weights through evolutionary algorithms.
arXiv AI
Jun 8
LuMamba: Latent Unified Mamba for Electrode Topology-Invariant and Efficient EEG Modeling
arXiv:2603. 19100v2 Announce Type: replace Abstract: Electroencephalography (EEG) enables non-invasive monitoring of brain activity across clinical and neurotechnology applications, yet building foundation models for EEG remains challenging due to differing electrode topologies and computational scalability, as Transformer architectures incur quadratic sequence complexity.
arXiv Machine Learning
Jun 24
Zero-Shot Neural Priors for Generalizable Cross-Subject and Cross-Task EEG Decoding
arXiv:2606. 23706v1 Announce Type: cross Abstract: The development of generalizable electroencephalography (EEG) decoding models is essential for robust brain-computer interfaces (BCI) and objective neural biomarkers in mental health.