35 search results - page 4 / 7 » Optimising the topology of complex neural networks |
IJCNN
2007
IEEE
14 years 1 months ago
2007
IEEE
— To approximate complex data, we propose new type of low-dimensional “principal object”: principal cubic complex. This complex is a generalization of linear and nonlinear pr...
GECCO
2003
Springer
14 years 19 days ago
2003
Springer
Abstract. In developing algorithms that dynamically changes the structure and weights of ANN (Artificial Neural Networks), there must be a proper balance between network complexit...
GECCO
2006
Springer
13 years 11 months ago
2006
Springer
The Layered Pareto Coevolution Archive (LAPCA) was recently proposed as an effective Coevolutionary Memory (CM) which, under certain assumptions, approximates monotonic progress i...
AAAI
1996
13 years 8 months ago
1996
Research on mobile robot navigation has produced two major paradigms for mapping indoorenvironments: grid-based and topological. While grid-based methods produce accurate metric m...
ESANN
2007
13 years 8 months ago
2007
Training recurrent neural networks is hard. Recently it has however been discovered that it is possible to just construct a random recurrent topology, and only train a single linea...