Sciweavers

66 search results - page 4 / 14
» Stochastic gradient descent on GPUs
Sort
View
JMLR
2012
12 years 2 days ago
Krylov Subspace Descent for Deep Learning
In this paper, we propose a second order optimization method to learn models where both the dimensionality of the parameter space and the number of training samples is high. In ou...
Oriol Vinyals, Daniel Povey
JMLR
2008
95views more  JMLR 2008»
13 years 9 months ago
Learning Similarity with Operator-valued Large-margin Classifiers
A method is introduced to learn and represent similarity with linear operators in kernel induced Hilbert spaces. Transferring error bounds for vector valued large-margin classifie...
Andreas Maurer
CDC
2010
IEEE
138views Control Systems» more  CDC 2010»
13 years 4 months ago
Sensor-based robot deployment algorithms
Abstract-- In robot deployment problems, the fundamental issue is to optimize a steady state performance measure that depends on the spatial configuration of a group of robots. For...
Jerome Le Ny, George J. Pappas
WWW
2010
ACM
14 years 4 months ago
Web-scale k-means clustering
We present two modifications to the popular k-means clustering algorithm to address the extreme requirements for latency, scalability, and sparsity encountered in user-facing web...
D. Sculley
ICIP
2000
IEEE
14 years 11 months ago
Curve Evolution, Boundary-Value Stochastic Processes, the Mumford-Shah Problem, and Missing Data Applications
We present an estimation-theoretic approach to curve evolution for the Mumford-Shah problem. By viewing an active contour as the set of discontinuities in the Mumford-Shah problem...
Andy Tsai, Anthony J. Yezzi, Alan S. Willsky