Evolving neural networks through augmenting topologies
Evolutionary Computation
Generating large-scale neural networks through discovering geometric regularities
Proceedings of the 9th annual conference on Genetic and evolutionary computation
Evolutionary reinforcement learning of artificial neural networks
International Journal of Hybrid Intelligent Systems - Hybridization of Intelligent Systems
Accelerated Neural Evolution through Cooperatively Coevolved Synapses
The Journal of Machine Learning Research
Forex trading using geometry sensitive neural networks
Proceedings of the 14th annual conference companion on Genetic and evolutionary computation
Preliminary results for neuroevolutionary optimization phase order generation for static compilation
Proceedings of the 11th Workshop on Optimizations for DSP and Embedded Systems
| Hi-index | 0.00 |
The goal of this paper is twofold. First, to briefly present a novel type of memetic algorithm based Topology and Weight Evolving Artificial Neural Network (TWEANN) system called DXNN, among whose numerous novel features are: a simple and database friendly tuple based NN encoding method, a two phase neuroevolutionary approach which produces high diversity populations, a new "Targeted Tuning Phase" aimed at dealing with "the curse of dimensionality", and a new Random Intensity Mutation (RIM) method that removes the need for cross-over algorithms. Second, to discuss the excellent experimental results of applying DXNN to co-evolutionary artificial life simulations.