Principal Sensitivity Analysis
Machine Learning
2015-09-22 v2 Machine Learning
Abstract
We present a novel algorithm (Principal Sensitivity Analysis; PSA) to analyze the knowledge of the classifier obtained from supervised machine learning techniques. In particular, we define principal sensitivity map (PSM) as the direction on the input space to which the trained classifier is most sensitive, and use analogously defined k-th PSM to define a basis for the input space. We train neural networks with artificial data and real data, and apply the algorithm to the obtained supervised classifiers. We then visualize the PSMs to demonstrate the PSA's ability to decompose the knowledge acquired by the trained classifiers.
Keywords
Cite
@article{arxiv.1412.6785,
title = {Principal Sensitivity Analysis},
author = {Sotetsu Koyamada and Masanori Koyama and Ken Nakae and Shin Ishii},
journal= {arXiv preprint arXiv:1412.6785},
year = {2015}
}