Murphy Christian author Columbia University. Computer Science Kaiser Gail E. author Columbia University. Computer Science Hu Lifeng author Columbia University. Computer Science Columbia University. Computer Science originator contributor text Technical reports New York Department of Computer Science, Columbia University 2008 It is challenging to test machine learning (ML) applications, which are intended to learn properties of data sets where the correct answers are not already known. In the absence of a test oracle, one approach to testing these applications is to use metamorphic testing, in which properties of the application are exploited to define transformation functions on the input, such that the new output will be unchanged or can easily be predicted based on the original output; if the output is not as expected, then a defect must exist in the application. Here, we seek to enumerate and classify the metamorphic properties of some machine learning algorithms, and demonstrate how these can be applied to reveal defects in the applications of interest. In addition to the results of our testing, we present a set of properties that can be used to define these metamorphic relationships so that metamorphic testing can be used as a general approach to testing machine learning applications. Computer science CUCS-011-08 http://hdl.handle.net/10022/AC:P:29550 English NNC NNC 2011-04-27 09:37:23 -0400 2012-04-06 10:51:31 -0400 3998 eng