Sciweavers

1227 search results - page 11 / 246
» Learning Rates for Q-Learning
Sort
View
PAMI
2012
13 years 2 days ago
Learning Optimal Embedded Cascades
—The problem of automatic and optimal design of embedded object detector cascades is considered. Two main challenges are identified: optimization of the cascade configuration and...
Mohammad Javad Saberian, Nuno Vasconcelos
ECTEL
2009
Springer
15 years 4 months ago
Assessing Collaboration Quality in Synchronous CSCL Problem-Solving Activities: Adaptation and Empirical Evaluation of a Rating
The work described is part of an ongoing interdisciplinary collaboration between two research teams of the University of Patras, Greece and the University of Freiburg, Germany, whi...
Georgios Kahrimanis, Anne Meier, Irene-Angelica Ch...
CDC
2010
IEEE
196views Control Systems» more  CDC 2010»
14 years 4 months ago
Convergence and convergence rate of stochastic gradient search in the case of multiple and non-isolated extrema
The asymptotic behavior of stochastic gradient algorithms is studied. Relying on some results of differential geometry (Lojasiewicz gradient inequality), the almost sure pointconve...
Vladislav B. Tadic
79
Voted
NIPS
2004
14 years 11 months ago
Rate- and Phase-coded Autoassociative Memory
Areas of the brain involved in various forms of memory exhibit patterns of neural activity quite unlike those in canonical computational models. We show how to use well-founded Ba...
Máté Lengyel, Peter Dayan
CHI
2003
ACM
15 years 10 months ago
Combined model for text entry rate development
We combine the power law of learning and theoretical upper limit predictions to describe the development of text entry rates from users' first contact to asymptotic expert us...
Poika Isokoski, I. Scott MacKenzie