Next Article in Journal
Asymptotic Properties for Methods Combining the Minimum Hellinger Distance Estimate and the Bayesian Nonparametric Density Estimate
Next Article in Special Issue
Extinction Analysis of Stochastic Predator–Prey System with Stage Structure and Crowley–Martin Functional Response
Previous Article in Journal
Optimization and Entropy Production: Application to Carnot-Like Refrigeration Machines
Previous Article in Special Issue
Spatial Organization of Five-Fold Morphology as a Source of Geometrical Constraint in Biology
Open AccessArticle

Flexibility of Boolean Network Reservoir Computers in Approximating Arbitrary Recursive and Non-Recursive Binary Filters

1
Institute for Systems Biology, 401 Terry Ave N, Seattle, WA 98109, USA
2
Molecular & Cellular Biology Program, University of Washington, Seattle, WA 98195, USA
*
Author to whom correspondence should be addressed.
Entropy 2018, 20(12), 954; https://doi.org/10.3390/e20120954
Received: 7 November 2018 / Revised: 6 December 2018 / Accepted: 7 December 2018 / Published: 11 December 2018
(This article belongs to the Special Issue Biological Statistical Mechanics)
Reservoir computers (RCs) are biology-inspired computational frameworks for signal processing that are typically implemented using recurrent neural networks. Recent work has shown that Boolean networks (BN) can also be used as reservoirs. We analyze the performance of BN RCs, measuring their flexibility and identifying the factors that determine the effective approximation of Boolean functions applied in a sliding-window fashion over a binary signal, both non-recursively and recursively. We train and test BN RCs of different sizes, signal connectivity, and in-degree to approximate three-bit, five-bit, and three-bit recursive binary functions, respectively. We analyze how BN RC parameters and function average sensitivity, which is a measure of function smoothness, affect approximation accuracy as well as the spread of accuracies for a single reservoir. We found that approximation accuracy and reservoir flexibility are highly dependent on RC parameters. Overall, our results indicate that not all reservoirs are equally flexible, and RC instantiation and training can be more efficient if this is taken into account. The optimum range of RC parameters opens up an angle of exploration for understanding how biological systems might be tuned to balance system restraints with processing capacity. View Full-Text
Keywords: complex adaptive systems; systems dynamics; dynamical systems; signal processing; reservoir computing; machine learning; Boolean networks; biological modeling complex adaptive systems; systems dynamics; dynamical systems; signal processing; reservoir computing; machine learning; Boolean networks; biological modeling
Show Figures

Figure 1

MDPI and ACS Style

Echlin, M.; Aguilar, B.; Notarangelo, M.; Gibbs, D.L.; Shmulevich, I. Flexibility of Boolean Network Reservoir Computers in Approximating Arbitrary Recursive and Non-Recursive Binary Filters. Entropy 2018, 20, 954.

Show more citation formats Show less citations formats
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Search more from Scilit
 
Search
Back to TopTop