A neuro-inspired general framework for the evolution of stochastic dynamical systems: Cellular automata, random Boolean
- PDF / 3,736,171 Bytes
- 18 Pages / 595.276 x 790.866 pts Page_size
- 29 Downloads / 257 Views
(0123456789().,-volV)(0123456789().,-volV)
RESEARCH ARTICLE
A neuro-inspired general framework for the evolution of stochastic dynamical systems: Cellular automata, random Boolean networks and echo state networks towards criticality Sidney Pontes-Filho1,2 • Pedro Lind1 • Anis Yazidi1 • Jianhua Zhang1 • Hugo Hammer1 Gustavo B. M. Mello1 • Ioanna Sandvig3 • Gunnar Tufte2 • Stefano Nichele1,4
•
Received: 30 December 2019 / Revised: 8 May 2020 / Accepted: 14 May 2020 Ó The Author(s) 2020
Abstract Although deep learning has recently increased in popularity, it suffers from various problems including high computational complexity, energy greedy computation, and lack of scalability, to mention a few. In this paper, we investigate an alternative brain-inspired method for data analysis that circumvents the deep learning drawbacks by taking the actual dynamical behavior of biological neural networks into account. For this purpose, we develop a general framework for dynamical systems that can evolve and model a variety of substrates that possess computational capacity. Therefore, dynamical systems can be exploited in the reservoir computing paradigm, i.e., an untrained recurrent nonlinear network with a trained linear readout layer. Moreover, our general framework, called EvoDynamic, is based on an optimized deep neural network library. Hence, generalization and performance can be balanced. The EvoDynamic framework contains three kinds of dynamical systems already implemented, namely cellular automata, random Boolean networks, and echo state networks. The evolution of such systems towards a dynamical behavior, called criticality, is investigated because systems with such behavior may be better suited to do useful computation. The implemented dynamical systems are stochastic and their evolution with genetic algorithm mutates their update rules or network initialization. The obtained results are promising and demonstrate that criticality is achieved. In addition to the presented results, our framework can also be utilized to evolve the dynamical systems connectivity, update and learning rules to improve the quality of the reservoir used for solving computational tasks and physical substrate modeling. Keywords Dynamical systems Implementation Reservoir computing Evolution Criticality
Introduction
& Sidney Pontes-Filho [email protected] 1
Department of Computer Science, Oslo Metropolitan University, Oslo, Norway
2
Department of Computer Science, Norwegian University of Science and Technology, Trondheim, Norway
3
Department of Neuromedicine and Movement Science, Norwegian University of Science and Technology, Trondheim, Norway
4
Department of Holistic Systems, Simula Metropolitan, Oslo, Norway
Every day, humans produce exabytes of data and this trend is growing due to emerging technologies, such as 5G and the Internet of Things (McAfee et al. 2012). Given that the main computing technology is based on von Neumann architecture, the analysis of enormous amounts of data is challenging even for the popular deep
Data Loading...
