Decorrelative Network Architecture for Robust Electrocardiogram Classification

arXiv:2207.09031v4 Announce Type: replace
Abstract: Artificial intelligence has made great progress in medical data analysis, but the lack of robustness and trustworthiness has kept these methods from being widely deployed. As it is not possible to train networks that are accurate in all scenarios, models must recognize situations where they cannot operate confidently. Bayesian deep learning methods sample the model parameter space to estimate uncertainty, but these parameters are often subject to the same vulnerabilities, which can be exploited by …

abstract analysis architecture artificial artificial intelligence arxiv classification cs.ai cs.lg data data analysis intelligence medical medical data network network architecture networks progress robust robustness train type