\(\hbox {ACO}_\mathbb {R}\) is a well-established Ant Colony Optimization (ACO) algorithm for continuous-domain optimization. In this paper, we propose an extension (which we call \(\hbox {ACO}_{\mathbb {R}}^{*}\) ) in which several fundamental modifications are made to \(\hbox {ACO}_\mathbb {R}\) ’s solution construction process, including the incorporation of a social influence mechanism borrowed from Particle Swarm Optimization (PSO). Our modifications to the \(\hbox {ACO}_\mathbb {R}\) algorithm are intended to promote search diversity and combat premature convergence. We experimentally evaluate our proposal in the context of training feedforward neural networks for classification using 65 widely-used datasets from the University of California Irvine (UCI) repository, as well as the optimization of several popular synthetic continuous-domain benchmark functions, with number of dimensions varying up to 30,000. Our results empirically confirm that our proposal reduces the frequency of search stagnation, and improves performance on both applications, to a statistically significant extent.
