English

NeuroView: Explainable Deep Network Decision Making

Computer Vision and Pattern Recognition 2021-10-18 v1 Machine Learning

Abstract

Deep neural networks (DNs) provide superhuman performance in numerous computer vision tasks, yet it remains unclear exactly which of a DN's units contribute to a particular decision. NeuroView is a new family of DN architectures that are interpretable/explainable by design. Each member of the family is derived from a standard DN architecture by vector quantizing the unit output values and feeding them into a global linear classifier. The resulting architecture establishes a direct, causal link between the state of each unit and the classification decision. We validate NeuroView on standard datasets and classification tasks to show that how its unit/class mapping aids in understanding the decision-making process.

Keywords

Cite

@article{arxiv.2110.07778,
  title  = {NeuroView: Explainable Deep Network Decision Making},
  author = {CJ Barberan and Randall Balestriero and Richard G. Baraniuk},
  journal= {arXiv preprint arXiv:2110.07778},
  year   = {2021}
}

Comments

12 pages, 7 figures

R2 v1 2026-06-24T06:54:21.992Z