Examining Redundancy in the Context of Safe Machine Learning

Hans Dermot Doran; Monika Reif

Examining Redundancy in the Context of Safe Machine Learning

Machine Learning 2020-07-07 v1 Machine Learning

Authors: Hans Dermot Doran , Monika Reif

Abstract

This paper describes a set of experiments with neural network classifiers on the MNIST database of digits. The purpose is to investigate na\"ive implementations of redundant architectures as a first step towards safe and dependable machine learning. We report on a set of measurements using the MNIST database which ultimately serve to underline the expected difficulties in using NN classifiers in safe and dependable systems.

Keywords

adversarial robustness verification classification

Cite

@article{arxiv.2007.01900,
  title  = {Examining Redundancy in the Context of Safe Machine Learning},
  author = {Hans Dermot Doran and Monika Reif},
  journal= {arXiv preprint arXiv:2007.01900},
  year   = {2020}
}

Comments

5 pages, 7 tables, 5 figures

Related papers

View all related →