Sciweavers

370 search results - page 57 / 74
» Evolving neural network ensembles for control problems
Sort
View
HAIS
2009
Springer
14 years 8 days ago
Pareto-Based Multi-output Model Type Selection
In engineering design the use of approximation models (= surrogate models) has become standard practice for design space exploration, sensitivity analysis, visualization and optimi...
Dirk Gorissen, Ivo Couckuyt, Karel Crombecq, Tom D...
GECCO
2009
Springer
188views Optimization» more  GECCO 2009»
13 years 11 months ago
Exploiting multiple classifier types with active learning
Many approaches to active learning involve training one classifier by periodically choosing new data points about which the classifier has the least confidence, but designing a co...
Zhenyu Lu, Josh Bongard
IJON
2007
85views more  IJON 2007»
13 years 7 months ago
Hierarchical dynamical models of motor function
Hierarchical models of motor function are described in which the motor system encodes a hierarchy of dynamical motor primitives. The models are based on continuous attractor neura...
Simon M. Stringer, Edmund T. Rolls
CORR
2010
Springer
152views Education» more  CORR 2010»
13 years 7 months ago
Neuroevolutionary optimization
Temporal difference methods are theoretically grounded and empirically effective methods for addressing reinforcement learning problems. In most real-world reinforcement learning ...
Eva Volná
BC
2000
95views more  BC 2000»
13 years 7 months ago
Cerebellar learning of accurate predictive control for fast-reaching movements
Long conduction delays in the nervous system prevent the accurate control of movements by feedback control alone. We present a new, biologically plausible cerebellar model to study...
Jacob Spoelstra, Nicolas Schweighofer, Michael A. ...