English

Identifying the relevant dependencies of the neural network response on characteristics of the input space

Data Analysis, Statistics and Probability 2018-10-16 v2 Computational Physics

Abstract

The relation between the input and output spaces of neural networks (NNs) is investigated to identify those characteristics of the input space that have a large influence on the output for a given task. For this purpose, the NN function is decomposed into a Taylor expansion in each element of the input space. The Taylor coefficients contain information about the sensitivity of the NN response to the inputs. A metric is introduced that allows for the identification of the characteristics that mostly determine the performance of the NN in solving a given task. Finally, the capability of this metric to analyze the performance of the NN is evaluated based on a task common to data analyses in high-energy particle physics experiments.

Keywords

Cite

@article{arxiv.1803.08782,
  title  = {Identifying the relevant dependencies of the neural network response on characteristics of the input space},
  author = {Stefan Wunsch and Raphael Friese and Roger Wolf and Günter Quast},
  journal= {arXiv preprint arXiv:1803.08782},
  year   = {2018}
}