Sciweavers

4096 search results - page 570 / 820
» Fibring Neural Networks
Sort
View
ECCC
2000
158views more  ECCC 2000»
15 years 6 months ago
On the Computational Power of Winner-Take-All
This article initiates a rigorous theoretical analysis of the computational power of circuits that employ modules for computing winner-take-all. Computational models that involve ...
Wolfgang Maass
NN
2000
Springer
159views Neural Networks» more  NN 2000»
15 years 6 months ago
Independent component analysis for noisy data -- MEG data analysis
ICA (independent component analysis) is a new, simple and powerful idea for analyzing multi-variant data. One of the successful applications is neurobiological data analysis such ...
Shiro Ikeda, Keisuke Toyama
ML
1998
ACM
117views Machine Learning» more  ML 1998»
15 years 6 months ago
Learning Team Strategies: Soccer Case Studies
We use simulated soccer to study multiagent learning. Each team's players (agents) share action set and policy, but may behave di erently due to position-dependent inputs. All...
Rafal Salustowicz, Marco Wiering, Jürgen Schm...
NN
1998
Springer
15 years 6 months ago
A tennis serve and upswing learning robot based on bi-directional theory
We experimented on task-level robot learning based on bi-directional theory. The via-point representation was used for ‘learning by watching’. In our previous work, we had a r...
Hiroyuki Miyamoto, Mitsuo Kawato
NN
2002
Springer
125views Neural Networks» more  NN 2002»
15 years 6 months ago
Generalized relevance learning vector quantization
We propose a new scheme for enlarging generalized learning vector quantization (GLVQ) with weighting factors for the input dimensions. The factors allow an appropriate scaling of ...
Barbara Hammer, Thomas Villmann