Identification of dynamical structures in artificial brains: An analysis of Boolean network controlled robots
Andrea Roli, Marco Villani, Roberto Serra, Lorenzo Garattoni, Carlo Pinciroli, Mauro Birattari · 2013
Abstract. Automatic techniques for the design of artificial computa-tional systems, such as control programs for robots, are currently achiev-ing increasing attention within the AI community. A prominent case is the design of artificial neural network systems by means of search tech-niques, such as genetic algorithms. Frequently, the search calibrates not only the system parameters, but also its structure. This procedure has the advantage of reducing the bias introduced by the designer and makes it possible to explore new, innovative solutions. The drawback, though, is that the analysis of the resulting system might be extremely difficult and limited to few coarse-grained characteristics. In this paper, we consider the case of robots controlled by Boolean networks that are automati-cally designed by means of a training process based on local search. We propose to analyse these systems by a method that detects mesolevel dynamical structures. These structures are emerging patterns composed of elements that behave in a coherent way and loosely interact with the rest of the system. In general, this method can be used to detect func-tional clusters and emerging structures in nonlinear discrete dynamical systems. It is based on an extension of the notion of cluster index, which has been previously proposed by Edelman and Tononi to analyse biologi-cal neural systems. Our results show that our approach makes it possible to identify the computational core of a Boolean network which controls a robot. 1