Article

Sensitivity based model agnostic scalable explanations of deep learning

2025-02-24

Abstract excerpt

Deep neural networks (DNNs) are powerful tools for data-driven predictive machine learning, but their complex architecture obscures mechanistic relations that they have learned from data. This information is critical to the scientific method of hypotheses development, experiment design, and model validation, especially when DNNs are used for biological and clinical predictions that affect human health. We design S...

Topics

Open a Topic to create a Post that cites this publication.

Identifiers and source

Literature Corpus work: b7a8be42-22ab-51b6-b5d7-a74c808663aa
DOI: 10.1101/2025.02.21.639516

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

Sensitivity based model agnostic scalable explanations of deep learningDOI 10.1101/2025.02.21.639516Read

Explainable Artificial Intelligence for Cross-Dataset Generalizable Biomarker Discovery in Cardiovascular diseases (CVDs)Semantic proximity Read

Explainable autoencoder-based representation learning for gene expression dataSemantic proximity Read

Reliable interpretability of biology-inspired deep neural networksSemantic proximity Read

Reliable interpretability of biology-inspired deep neural networks.Semantic proximity Read

Knowledge-primed neural networks enable biologically interpretable deep learning on single-cell sequencing dataSemantic proximity Read

Verifying explainability of a deep learning tissue classifier trained on RNA-seq data.Semantic proximity Read

An interpretable omnigenic neural network architecture for the human genomeSemantic proximity Read

Transformer-based artificial intelligence on single-cell clinical data for homeostatic mechanism inference and rational biomarker discoverySemantic proximity Read

The Promise of Explainable Deep Learning for Omics Data Analysis: Adding New Discovery Tools to AISemantic proximity Read

RNAGAN: Train One and Get Four, Multipurpose Human RNA-Seq Analysis Tool with Enhanced Interpretability and Small Data Size CapabilitySemantic proximity Read

HD Spot: Interpretable Deep Learning Classification of Single Cell Transcript DataSemantic proximity Read

From Black Box to Biological Insight: AttentioFuse Unlocks Multi-Omics Dynamics in Lung CancerSemantic proximity Read