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. |
Year | DOI | Venue |
---|---|---|
2017 | 10.1080/17445760.2016.1155579 | International Journal of Parallel, Emergent and Distributed Systems - Special Issue: Signal processing, biosensing, and computing with bio-inspired and biochemical systems Guest Editor: Vladimir Privman |
Keywords | Field | DocType |
Associative memory, artificial neural network, correlation matrix memory, reaction-diffusion chemistry, unconventional computing | Nervous system network models,Autoassociative memory,Content-addressable memory,Unconventional computing,Physical neural network,Computer science,Recurrent neural network,Theoretical computer science,Time delay neural network,Artificial intelligence,Artificial neural network | Journal |
Volume | Issue | ISSN |
32 | 1 | 1744-5760 |
Citations | PageRank | References |
2 | 0.42 | 8 |
Authors | ||
2 |
Name | Order | Citations | PageRank |
---|---|---|---|
James Stovold | 1 | 5 | 1.19 |
Simon O'keefe | 2 | 41 | 11.71 |