General Science and Philosophy

    

DERaNGe: Dice-Enhanced Random Number Generator

Authors: Ravi Hassanaly, Nemo Fournier, Ghislain Vaillant

Upon review of the literature, it appears clear that Pseudo Random Number Generation (PRNG) used extensively in the Machine Learning is intrinsically problematic. We propose here to reintroduce True Random Number Generation in the ML field, and we publish a library which allows users to replace the default PRNG provided in Python by the results of dice rolls that have been performed by the authors in very controlled conditions. This will ensure more sound theoretical foundations of any downstream ML algorithm using our source of randomness.

Comments: 11 Pages.

Download: PDF

Submission history

[v1] 2024-04-01 21:54:32

Unique-IP document downloads: 380 times

Vixra.org is a pre-print repository rather than a journal. Articles hosted may not yet have been verified by peer-review and should be treated as preliminary. In particular, anything that appears to include financial or legal advice or proposed medical treatments should be treated with due caution. Vixra.org will not be responsible for any consequences of actions that result from any form of use of any documents on this website.

Add your own feedback and questions here:
You are equally welcome to be positive or negative about any paper but please be polite. If you are being critical you must mention at least one specific error, otherwise your comment will be deleted as unhelpful.

comments powered by Disqus