Login | Register

Neural Networks as Pseudorandom Number Generators

Title:

Neural Networks as Pseudorandom Number Generators

Goldsmith, Mark (2015) Neural Networks as Pseudorandom Number Generators. PhD thesis, Concordia University.

[img]
Preview
Text (application/pdf)
Goldsmith_PhD_S2015.pdf - Accepted Version
Available under License Spectrum Terms of Access.
1MB

Abstract

This thesis brings two disparate fields of research together; the fields of artificial neural networks and pseudorandom number generation. In it, we answer variations on the following question: can recurrent neural networks generate pseudorandom numbers? In doing so, we provide a new construction of an $n$-dimensional neural network that has period $2^n$, for all $n$. We also provide a technique for constructing neural networks based on the theory of shift register sequences. The randomness capabilities of these networks is then measured via the theoretical notion of computational indistinguishability and a battery of statistical tests. In particular, we show that neural networks cannot be pseudorandom number generators according to the theoretical definition of computational indistinguishability. We contrast this result by providing some neural networks that pass all of the tests in the SmallCrush battery of tests in the TestU01 testing suite.

Divisions:Concordia University > Gina Cody School of Engineering and Computer Science > Computer Science and Software Engineering
Item Type:Thesis (PhD)
Authors:Goldsmith, Mark
Institution:Concordia University
Degree Name:Ph. D.
Program:Computer Science
Date:1 April 2015
Thesis Supervisor(s):Chvatal, Vasek
ID Code:979881
Deposited By: MARK GOLDSMITH
Deposited On:16 Jul 2015 12:48
Last Modified:18 Jul 2019 15:08
All items in Spectrum are protected by copyright, with all rights reserved. The use of items is governed by Spectrum's terms of access.

Repository Staff Only: item control page

Downloads per month over past year

Research related to the current document (at the CORE website)
- Research related to the current document (at the CORE website)
Back to top Back to top