no code implementations • 6 Mar 2019 • Danilo Vasconcellos Vargas, Junichi Murata, Hirotaka Takano
In this paper, both problems are solved together without approximations or simplifications.
1 code implementation • 6 Jan 2019 • Danilo Vasconcellos Vargas, Junichi Murata
The combination of Spectrum Diversity with a unified neuron representation enables the algorithm to either surpass or equal NeuroEvolution of Augmenting Topologies (NEAT) on all of the five classes of problems tested.
1 code implementation • 2 Jan 2019 • Danilo Vasconcellos Vargas, Junichi Murata, Hirotaka Takano, Alexandre Claudio Botazzo Delbem
Structured evolutionary algorithms have been investigated for some time.
no code implementations • 20 Nov 2018 • Danilo Vasconcellos Vargas, Hirotaka Takano, Junichi Murata
In fact, the proposed algorithm possesses a dynamical population structure that self-organizes itself to better project the input space into a map.
no code implementations • 20 Nov 2018 • Danilo Vasconcellos Vargas, Hirotaka Takano, Junichi Murata
Experiments are conducted with the contingency training applied to neural networks over traditional datasets as well as datasets with additional irrelevant variables.
no code implementations • 20 Nov 2018 • Danilo Vasconcellos Vargas, Hirotaka Takano, Junichi Murata
Here, a variation of the first algorithm is proposed which uses a parameterless self organizing map (SOM).
no code implementations • 19 Sep 2018 • Danilo Vasconcellos Vargas, Hirotaka Takano, Junichi Murata
Moreover, NOTC is compared with NeuroEvolution of Augmenting Topologies (NEAT) in these problems, revealing a trade-off between the approaches.