Combining evolution and self-organization to find natural Boolean representations in unconventional computational media

Show simple item record Egbert, Matthew en Gruenert, G en Ibrahim, B en Dittrich, P en 2020-09-23T04:33:37Z en 2020-09-23T04:33:37Z en 2019-10-01 en
dc.identifier.uri en
dc.description.abstract Designing novel unconventional computing systems often requires the selection of the computational structure as well as choosing the right symbol encoding. Several approaches apply heuristic search and evolutionary algorithms to find both computational structure and symbol encoding, which is time consuming because they depend on each other. Here, we present a novel approach that combines evolution with self-organization, in particular we evolve the computational structure but let the symbol encoding emerge through self-organization. This should not only be more efficient but should also lead to a more “natural“ symbol encoding. We successfully demonstrate the potential of the technique, using an evolutionary algorithm to optimize the parameters of two non-linear media to perform as NAND-gates: a continuous-time recurrent neural network (CTRNN) and a computational model of BZ-droplet-based computing (DropSim). In both cases, the technique identified representations for TRUE and FALSE, and system configurations that performed successfully as NAND-gates. The effectiveness of the evolved NAND gates was further evaluated by their performance in half-adder networks, where again, both evolved systems performed correctly, producing the correct output for all possible inputs and for all possible transitions between inputs. We conclude that beyond the specific applications demonstrated here, combining evolution with self-organization could be a promising strategy widely applicable. en
dc.relation.ispartofseries Biosystems en
dc.rights Items in ResearchSpace are protected by copyright, with all rights reserved, unless otherwise indicated. Previously published items are made available in accordance with the copyright policy of the publisher. en
dc.rights.uri en
dc.title Combining evolution and self-organization to find natural Boolean representations in unconventional computational media en
dc.type Journal Article en
dc.identifier.doi 10.1016/j.biosystems.2019.104011 en
pubs.volume 184 en
dc.rights.holder Copyright: The author en en
dc.rights.accessrights en
pubs.subtype Article en
pubs.elements-id 809867 en Science en School of Computer Science en
pubs.record-created-at-source-date 2020-08-07 en 2019-07-29 en

Files in this item

Find Full text

This item appears in the following Collection(s)

Show simple item record


Search ResearchSpace