ServiceNow Research

Interpretability

RandomSCM: interpretable ensembles of sparse classifiers tailored for omics data
RandomSCM: interpretable ensembles of sparse classifiers tailored for omics data

Recent metabolomics measurement devices, such as mass spectrometers, produce extremely high-dimensional data. Together with small …

Intelligent Systems for Molecular Biology and European Conference on Computational Biology,  2021.
PDF Cite Code Video
Enforcing Interpretability and its Statistical Impacts: Trade-offs between Accuracy and Interpretability
Enforcing Interpretability and its Statistical Impacts: Trade-offs between Accuracy and Interpretability
To date, there has been no formal study of the statistical cost of interpretability in machine learning. As such, the discourse around …
ArXiv,  2020.
PDF Cite
Interpretable genotype-to-phenotype classifiers with performance guarantees
Interpretable genotype-to-phenotype classifiers with performance guarantees
Understanding the relationship between the genome of a cell and its phenotype is a central problem in precision medicine. Nonetheless, …
Nature Scientific Reports,  2018.
PDF Cite Code