SCIENCE@home

TreeView: Peeking into Deep Neural Networks Via Feature-Space Partitioning

Jayaraman J. Thiagarajan,B. Kailkhura,P. Sattigeri,K. Ramamurthy

Published 2016 in arXiv.org

ABSTRACT

With the advent of highly predictive but opaque deep learning models, it has become more important than ever to understand and explain the predictions of such models. Existing approaches define interpretability as the inverse of complexity and achieve interpretability at the cost of accuracy. This introduces a risk of producing interpretable but misleading explanations. As humans, we are prone to engage in this kind of behavior \cite{mythos}. In this paper, we take a step in the direction of tackling the problem of interpretability without compromising the model accuracy. We propose to build a Treeview representation of the complex model via hierarchical partitioning of the feature space, which reveals the iterative rejection of unlikely class labels until the correct association is predicted.

PUBLICATION RECORD

  • Publication year

    2016

  • Venue

    arXiv.org

  • Publication date

    2016-11-03

  • Fields of study

    Mathematics, Computer Science

  • Identifiers
    arXiv 1611.07429
  • External record

    Open on Semantic Scholar

  • Source metadata

    Semantic Scholar

CITATION MAP

EXTRACTION MAP

CLAIMS

  • No claims are published for this paper.

CONCEPTS

  • No concepts are published for this paper.

REFERENCES

CITED BY

Showing 1-43 of 43 citing papers · Page 1 of 1