Improving performance of deep learning models with axiomatic attribution priors and expected gradients
Year: 2021
Type: article
Source: Nature Machine Intelligence
Institutions: University of Washington, Microsoft (United States)
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
Awards: CAREER: Learning the Chromatin Network from ChIP-Seq Data, G272727986, Collaborative Research: ABI Innovation: Interpretable Machine Learning to Identify Molecular Markers for Complex Phenotypes, Interpretable Machine Learning to Identify Alzheimer's Disease Therapeutic Targets, University of Washington Medical Scientist Training Program, G7932826167, Opening the Black Box of Machine Learning Models, G9000100002
OpenAlex ID: W3105856249