Sciweavers

657 search results - page 93 / 132
» On the Identification of a Class of Linear Models
Sort
View
ICML
2004
IEEE
15 years 10 months ago
Learning and discovery of predictive state representations in dynamical systems with reset
Predictive state representations (PSRs) are a recently proposed way of modeling controlled dynamical systems. PSR-based models use predictions of observable outcomes of tests that...
Michael R. James, Satinder P. Singh
BC
2008
72views more  BC 2008»
14 years 10 months ago
Spike-train spectra and network response functions for non-linear integrate-and-fire neurons
Reduced models have long been used as a tool for the analysis of the complex activity taking place in neurons and their coupled networks. Recent advanced in experimental and theore...
Magnus J. E. Richardson
CDC
2009
IEEE
225views Control Systems» more  CDC 2009»
15 years 2 months ago
High performance adaptive robust control for nonlinear system with unknown input backlash
—A high performance adaptive robust control (ARC) algorithm is developed for a class of nonlinear system with unknown input backlash, parametric uncertainties and uncertain nonli...
Jian Guo, Bin Yao, Qingwei Chen, Xiaobei Wu
ATAL
2006
Springer
15 years 1 months ago
A constraint optimization framework for fractured robot teams
In dangerous and uncertain environments initial plans must be revised. Communication failures hamper this replanning. We introduce fractured subteams as a novel formalism for mode...
Mary Koes, Katia P. Sycara, Illah R. Nourbakhsh
NIPS
2001
14 years 11 months ago
On the Generalization Ability of On-Line Learning Algorithms
In this paper, it is shown how to extract a hypothesis with small risk from the ensemble of hypotheses generated by an arbitrary on-line learning algorithm run on an independent an...
Nicolò Cesa-Bianchi, Alex Conconi, Claudio ...