Reaction–diffusion chemistry implementation of associative memory neural network. Issue 1 (2nd January 2017)

• Record Type: Journal Article
• Authors: Stovold, James; O'Keefe, Simon
• Is Part Of: International journal of parallel, emergent and distributed systems. Volume 32:Issue 1(2017)
• Page Start: 74
• Page End: 94
• Publication Date: 2017-01-02
• Subjects: Associative memory -- artificial neural network -- correlation matrix memory -- reaction–diffusion chemistry -- unconventional computing; Parallel computers -- Periodicals; Electronic data processing -- Distributed processing -- Periodicals; Computer algorithms -- Periodicals; 004.35
• DOI: 10.1080/17445760.2016.1155579
• Languages: English
• ISSNs: 1744-5760

Abstract

Abstract : Unconventional computing paradigms are typically very difficult to program. By implementing efficient parallel control architectures such as artificial neural networks, we show that it is possible to program unconventional paradigms with relative ease. The work presented implements correlation matrix memories (a form of artificial neural network based on associative memory) in reaction–diffusion chemistry, and shows that implementations of such artificial neural networks can be trained and act in a similar way to conventional implementations. Graphical abstract: