Parallel distributed processing: explorations in the microstructure of cognition, vol. 1: foundations
Small worlds: the dynamics of networks between order and randomness
Small worlds: the dynamics of networks between order and randomness
Dynamics of complex systems
Complex Systems and Cognitive Processes
Complex Systems and Cognitive Processes
Perturbing the Regular Topology of Cellular Automata: Implications for the Dynamics
ACRI '01 Proceedings of the 5th International Conference on Cellular Automata for Research and Industry
Metaheuristics in combinatorial optimization: Overview and conceptual comparison
ACM Computing Surveys (CSUR)
Stochastic Local Search: Foundations & Applications
Stochastic Local Search: Foundations & Applications
Evolutionary Computation
Evolution of discrete gene regulatory models
Proceedings of the 10th annual conference on Genetic and evolutionary computation
Probabilistic Boolean Networks: The Modeling and Control of Gene Regulatory Networks
Probabilistic Boolean Networks: The Modeling and Control of Gene Regulatory Networks
Hybrid Metaheuristics: An Emerging Approach to Optimization
Hybrid Metaheuristics: An Emerging Approach to Optimization
Analysis of attractor distances in Random Boolean Networks
Proceedings of the 2011 conference on Neural Nets WIRN10: Proceedings of the 20th Italian Workshop on Neural Nets
Proceedings of the 13th annual conference on Genetic and evolutionary computation
Stochastic local search to automatically design Boolean networks with maximally distant attractors
EvoApplications'11 Proceedings of the 2011 international conference on Applications of evolutionary computation - Volume Part I
On the design of Boolean network robots
EvoApplications'11 Proceedings of the 2011 international conference on Applications of evolutionary computation - Volume Part I
Hi-index | 0.01 |
Boolean networks (BNs) have been mainly considered as genetic regulatory network models and are the subject of notable works in complex systems biology literature. Nevertheless, in spite of their similarities with neural networks, their potential as learning systems has not yet been fully investigated and exploited. In this work, we show that by employing metaheuristic methods we can train BNs to deal with two notable tasks, namely, the problem of controlling the BN's trajectory to match a set of requirements and the density classification problem. These tasks represent two important categories of problems in machine learning. The former is an example of the problems in which a dynamical system has to be designed such that its dynamics satisfies given requirements. The latter one is a representative task in classification. We also analyse the performance of the optimisation techniques as a function of the characteristics of the networks and the objective function and we show that the learning process could influence and be influenced by the BNs' dynamical condition.