This paper presents a comparison of two Evolutionary Artificial Neural Network (EANN) variants acting as the autonomous control system for instances of the-Consensus Avoidance Problem ( θ-CAP). A novel variant of EANN is proposed by adopting characteristics of a well-performing heuristic into the structural bias of the neurocontroller. Information theoretic landscape measures are used to analyze the problem space as well as variants of the EANN. The results obtained indicate that the two neurocontroller variants learn distinctly different approaches to the θ-CAP, however, the newly proposed variant demonstrates improvements in both solution quality and execution time. A rampeddifficulty evolution scheme is demonstrated to be effective at creating higher quality results as compared to the standard scheme for EANNs. A correlation between the proposed instance difficulty and identifiable landscape characteristics is discovered as well.

Additional Metadata
Keywords Control, Evolutionary algorithms, Inuence, Neural networks, Optimization
Persistent URL
Conference 17th Genetic and Evolutionary Computation Conference, GECCO 2015
Runka, A. (Andrew), & White, A. (2015). Evolving neurocontrollers for the control of information diffusion in social networks. In GECCO 2015 - Companion Publication of the 2015 Genetic and Evolutionary Computation Conference (pp. 1471–1472). doi:10.1145/2739482.2764630