Automatic definition of modular neural networks
Adaptive Behavior
Towards designing artificial neural networks by evolution
Applied Mathematics and Computation - Special issue on articficial life and robotics
Proceedings of the European Conference on Genetic Programming
Efficient Reinforcement Learning Through Evolving Neural Network Topologies
GECCO '02 Proceedings of the Genetic and Evolutionary Computation Conference
Symbiotic Evolution of Neural Networks in Sequential Decision Tasks
Symbiotic Evolution of Neural Networks in Sequential Decision Tasks
Accelerated Neural Evolution through Cooperatively Coevolved Synapses
The Journal of Machine Learning Research
Structural and Parametric Evolution of Continuous-Time Recurrent Neural Networks
SBRN '08 Proceedings of the 2008 10th Brazilian Symposium on Neural Networks
A comparison between cellular encoding and direct encoding for genetic neural networks
GECCO '96 Proceedings of the 1st annual conference on Genetic and evolutionary computation
Connectionist theory refinement: genetically searching the space of network topologies
Journal of Artificial Intelligence Research
Efficient non-linear control through neuroevolution
ECML'06 Proceedings of the 17th European conference on Machine Learning
COVNET: a cooperative coevolutionary model for evolving artificial neural networks
IEEE Transactions on Neural Networks
EvoBIO'13 Proceedings of the 11th European conference on Evolutionary Computation, Machine Learning and Data Mining in Bioinformatics
Hi-index | 0.00 |
Cartesian Genetic Programming based Neuroevolutionary algorithm is proposed. It encodes the neural network attributes namely weights, topology and functions and then evolves them for best possible weight, topology and function. The architecture generated are both feedforward and recurrent. The proposed algorithm is applied on the standard benchmark control problem: balancing single and double pole at both markovian and non-markovian states. Results demonstrate that CGPANN has the potential to generate neural architecture and parameters in substantially fewer number of evaluations in comparison to earlier neuroevolutionary techniques. The power of CGPANN is its representation which leads to a thorough evolutionary search producing generalized networks. This opens new avenues of applying the proposed technique to any non-linear and dynamic problem.