Sciweavers

2178 search results - page 165 / 436
» Problems of learning in multi-agent systems
Sort
View
NCA
2007
IEEE
15 years 4 months ago
Using evolution to improve neural network learning: pitfalls and solutions
: Autonomous neural network systems typically require fast learning and good generalization performance, and there is potentially a trade-off between the two. The use of evolutiona...
John A. Bullinaria
AAAI
1996
15 years 5 months ago
Post-Analysis of Learned Rules
Rule induction research implicitly assumes that after producing the rules from a dataset, these rules will be used directly by an expert system or a human user. In real-life appli...
Bing Liu, Wynne Hsu
CDC
2010
IEEE
106views Control Systems» more  CDC 2010»
14 years 11 months ago
Optimal cross-layer wireless control policies using TD learning
We present an on-line crosslayer control technique to characterize and approximate optimal policies for wireless networks. Our approach combines network utility maximization and ad...
Sean P. Meyn, Wei Chen, Daniel O'Neill
IV
2005
IEEE
142views Visualization» more  IV 2005»
15 years 10 months ago
Beyond Guidelines: What Can We Learn from the Visual Information Seeking Mantra?
The field of information visualization offers little methodological guidance to practitioners who seek to design novel systems. Though many sources describe the foundations of the...
Brock Craft, Paul A. Cairns
CVPR
2010
IEEE
16 years 19 days ago
PROST: Parallel Robust Online Simple Tracking
Tracking-by-detection is increasingly popular in order to tackle the visual tracking problem. Existing adaptive methods suffer from the drifting problem, since they rely on selfup...
Jakob Santner, Christian Leistner, Amir Saffari, T...