Sciweavers

240 search results - page 12 / 48
» An Evolutionary Approach for Learning Motion Class Patterns
Sort
View
PR
2007
118views more  PR 2007»
13 years 7 months ago
A cooperative constructive method for neural networks for pattern recognition
In this paper, we propose a new constructive method, based on cooperative coevolution, for designing automatically the structure of a neural network for classification. Our appro...
Nicolás García-Pedrajas, Domingo Ort...
TFS
2011
194views Education» more  TFS 2011»
13 years 2 months ago
Top-Down Induction of Fuzzy Pattern Trees
Fuzzy pattern tree induction was recently introduced as a novel machine learning method for classification. Roughly speaking, a pattern tree is a hierarchical, tree-like structur...
R. Senge, Eyke Hüllermeier
IJCV
2008
167views more  IJCV 2008»
13 years 7 months ago
Learning Layered Motion Segmentations of Video
We present an unsupervised approach for learning a generative layered representation of a scene from a video for motion segmentation. The learnt model is a composition of layers, ...
M. Pawan Kumar, Philip H. S. Torr, Andrew Zisserma...
GECCO
2006
Springer
185views Optimization» more  GECCO 2006»
13 years 11 months ago
Robot gaits evolved by combining genetic algorithms and binary hill climbing
In this paper an evolutionary algorithm is used for evolving gaits in a walking biped robot controller. The focus is fast learning in a real-time environment. An incremental appro...
Lena Mariann Garder, Mats Erling Høvin
GECCO
2005
Springer
141views Optimization» more  GECCO 2005»
14 years 1 months ago
Constructing good learners using evolved pattern generators
Self-organization of brain areas in animals begins prenatally, evidently driven by spontaneously generated internal patterns. The neural structures continue to develop postnatally...
Vinod K. Valsalam, James A. Bednar, Risto Miikkula...