Title:

Improving the Quality of Computational Science Software by Using Metamorphic Relations to Test Machine Learning Applications

Author(s):

Xie, Xiaoyuan
Ho, Joshua
Murphy, Christian
Kaiser, Gail E.
Xu, Baowen
Chen, T. Y.

Date:

2009

Type:

Technical reports

Department:

Computer Science

Permanent URL:

http://hdl.handle.net/10022/AC:P:29618

Series:

Columbia University Computer Science Technical Reports

Part Number:

CUCS-004-09

Publisher:

Department of Computer Science, Columbia University

Publisher Location:

New York

Abstract:

Many applications in the field of scientific computing - such as computational biology, computational linguistics, and others - depend on Machine Learning algorithms to provide important core functionality to support solutions in the particular problem domains. However, it is difficult to test such applications because often there is no 'test oracle' to indicate what the correct output should be for arbitrary input. To help address the quality of scientific computing software, in this paper we present a technique for testing the implementations of machine learning classification algorithms on which such scientific computing software depends. Our technique is based on an approach called 'metamorphic testing', which has been shown to be effective in such cases. In addition to presenting our technique, we describe a case study we performed on a real-world machine learning application framework, and discuss how programmers implementing machine learning algorithms can avoid the common pitfalls discovered in our study. We also discuss how our findings can be of use to other areas of computational science and engineering.

Subject(s):

Computer science

Item views:

117

Metadata:

description

View | Download