Sciweavers

106 search results - page 18 / 22
» Almost Square Packing
Sort
View
ICONIP
2008
14 years 10 days ago
On Weight-Noise-Injection Training
Abstract. While injecting weight noise during training has been proposed for more than a decade to improve the convergence, generalization and fault tolerance of a neural network, ...
Kevin Ho, Chi-Sing Leung, John Sum
IJCAI
2007
14 years 10 days ago
Fast Image Alignment Using Anytime Algorithms
Image alignment refers to finding the best transformation from a fixed reference image to a new image of a scene. This process is often guided by similarity measures between ima...
Rupert Brooks, Tal Arbel, Doina Precup
NIPS
2008
14 years 10 days ago
Learning with Consistency between Inductive Functions and Kernels
Regularized Least Squares (RLS) algorithms have the ability to avoid over-fitting problems and to express solutions as kernel expansions. However, we observe that the current RLS ...
Haixuan Yang, Irwin King, Michael R. Lyu
MSV
2004
14 years 9 days ago
MABAC - Matrix Based Clustering Algorithm
Clustering is a prominent method in the data mining field. It is a discovery process that groups data such that intra cluster similarity is maximized and the inter cluster similar...
Yonghui Chen, Alan P. Sprague, Kevin D. Reilly
CORR
2008
Springer
97views Education» more  CORR 2008»
13 years 11 months ago
Spreading Signals in the Wideband Limit
Abstract-- Wideband communications are asymptotically impossible with signals that are spread over a very wide band and are transmitted over a multipath channel unknown ahead of ti...
Elchanan Zwecher, Dana Porrat