Article
A multi-objective evolutionary approach to neural architecture search for clinical tabular classification: balancing predictive performance and model compactness
2026-07-14
Abstract excerpt
<title>Abstract</title> <p>Designing compact neural network classifiers for clinical tabular data is difficult: manual tuning is labour-intensive, and single-objective optimization tends to favour unnecessarily large models that generalize poorly and are awkward to deploy on constrained hardware. This paper presents a multi-objective genetic algorithm for neural architecture search (MOGA-NAS) that simultaneously...
Topics
Open a Topic to create a Post that cites this publication.
Identifiers and source
- Literature Corpus work
- 6a2c1a7e-e4f0-59dd-9600-dee5476373c5
- DOI
- 10.21203/rs.3.rs-10092066/v1
