Show simple item record

dc.contributor.advisorTriesch, Jochen
dc.contributor.advisorSprague, Nathan
dc.contributor.authorHughes, James M.
dc.date.accessioned2008-11-05T20:19:27Z
dc.date.available2008-11-05T20:19:27Z
dc.date.issued2007-04-26
dc.identifier.urihttp://hdl.handle.net/10920/6348
dc.description39 p.en
dc.description.abstractPseudo-random number generators are deterministic functions that map, in most cases, a state x to a new state x˙ using some update function in order to generate pseudo-random data. Use of these numbers is an integral part of computer science, stochastic physical & statistical simulation, and cryptography. Because of the deterministic nature of these functions, it is impossible to speak of the resultant numbers as truly random. Therefore, the primary goal of pseudo-random number generation is to create values that are statistically identical to truly random numbers. To this end, a few specific characteristics are desirable. First, there should be a way to extract some value from the function (such as a single bit) at discrete intervals that cannot be guessed with probability greater than 50% if only f, the update function, is known. Additionally, functions with long limit cycles and whose cycle lengths grow exponentially in the size of one or more system variables are among those well-suited for random number generation. Finally, the values generated should be independently and identically distributed over the given output interval. Many different, well-established methods exist for generating pseudo-random numbers. Each of these methods has advantages and disadvantages related to its efficiency and effectiveness. In this project, we present the results of a unique pseudorandom number generator created using binary recurrent neural networks trained with two types of neuronal plasticity, anti-spike-timing dependent plasticity (anti- STDP) and intrinsic plasticity (IP). We subject our results to industry-standard random number generator test suites, in addition to performing empirical analysis on the dynamics of our simulated networks. We show that the interaction of these types of plasticity creates network dynamics well-suited for pseudo-random number generation.en
dc.description.abstractMaterials made available to the public 3/20/2014 with consent of the author.
dc.description.sponsorshipFrankfurt Institute for Advanced Studies
dc.description.sponsorshipJohann-Wolfgang-Goethe Universität, Frankfurt, Germany
dc.description.sponsorshipHoward Hughes Medical Institute
dc.description.sponsorshipUniversität Frankfurt am Main
dc.description.sponsorshipHoward Hughes Medical Institute
dc.language.isoen_USen
dc.relation.ispartofSenior Individualized Projects. Computer Science.
dc.rightsU.S. copyright laws protect this material. Commercial use or distribution of this material is not permitted without prior written consent of the author.
dc.titlePseudo-random Number Generation Using Binary Recurrent Neural Networksen
dc.typeThesisen


Files in this item

Thumbnail

This item appears in the following Collection(s)

  • Computer Science Senior Integrated Projects [236]
    This collection includes Senior Integrated Projects (SIP's) completed in the Computer Science Department. Abstracts are generally available to the public, but PDF files are available only to current Kalamazoo College students, faculty, and staff.

Show simple item record