Computing Complex Tasks with Dynamical Cellular Systems
Computing with ultra-simple, small, dynamical systems, such as Cellular Automata (CA), Random Boolean Networks (RBNs), or Reservoir Computers (RC) is appealing because such systems are in general ultra-low power and easy to fabricate. In this talk I will first present an overview of such simple cellular systems. In the second part, I will present new results on reservoir computing with complex cellular automata. Several researchers have experimented with using the dynamical behavior of elementary cellular automaton rules as reservoirs. We have expanded this approach to cellular automaton with larger neighborhoods and/or more states, which are termed complex, as opposed to the elementary rules. Results show that some of these non-elementary cellular automaton rules outperform the best elementary rules at the standard benchmark 5-bit memory task, requiring half the reservoir size to produce comparable results. The research is relevant for building simple, small, and ultra-low power systems that perform complex computational tasks.
Neil Babson is a PhD student in Computer Science at Portland State University working Dr. Christof Teuscher. Neil previously received an M.S. in Computer Science from Portland State as well as B.S. degrees in Mathematics and Physics. His research interests include Reservoir Computing using hierarchical and self-organizing networks.
Biology | Computer Sciences
Babson, Neil, "Computing Complex Tasks with Dynamical Cellular Systems" (2019). Systems Science Friday Noon Seminar Series. 6.