LEARNING RANDOM NUMBERS: A MATLAB ANOMALY

• Published in: Applied artificial intelligence 2008-03, Vol.22 (3), p.254-265
• Main Authors: Savicky, Petr, Robnik-Šikonja, Marko
• Format: Article
• Language: English
• ISSN: 0883-9514; 1087-6545
• DOI: 10.1080/08839510701768382

We describe how dependencies between random numbers generated with some popular pseudo-random number generators can be detected using general purpose machine-learning techniques. This is a novel approach, since usually pseudo-random number generators are evaluated using tests specifically designed for this purpose. Such specific tests are more sensitive. Hence, detecting the dependence using machine-learning methods implies that the dependence is indeed very strong. The most important example of a generator, where dependencies may easily be found using our approach, is MATLAB's function rand if the method state is used. This method was the default in MATLAB versions between 5 (1995) and 7.3 (2006b), i.e., for more than 10 years. In order to evaluate the strength of the dependence in it, we used the same machine-learning tools to detect dependencies in some other random number generators, which are known to be bad or insufficient for large simulations: the infamous RANDU, ANSIC, the oldest generator in C library, minimal standard generator, suggested by Park and Miller ( 1988 ), and the rand function in Microsoft C compiler.