Sciweavers

NIPS
1998
13 years 11 months ago
Convergence of the Wake-Sleep Algorithm
The W-S (Wake-Sleep) algorithm is a simple learning rule for the models with hidden variables. It is shown that this algorithm can be applied to a factor analysis model which is a...
Shiro Ikeda, Shun-ichi Amari, Hiroyuki Nakahara
BMVC
1997
13 years 11 months ago
Robust Recursive Structure and Motion Recovery under Affine Projection
In this paper we present an algorithm for structure and motion (SM) recovery under affine projection from video sequences. The algorithm tracks the motion of a single structure, b...
Miroslav Trajkovic, Mark Hedley
IRMA
2000
13 years 11 months ago
Recognizing bounds of context change in on-line learning
The on-line algorithms in machine learning are intended to discover unknown function of the domain based on incremental observing of it instance by instance. These algorithms have...
Helen Kaikova, Vagan Y. Terziyan, Borys Omelayenko
IWMMDBMS
1998
117views more  IWMMDBMS 1998»
13 years 11 months ago
Motion-based Parsing of Compressed Video
An algorithm for detecting scene changes in compressed video streams is proposed. The proposed algorithm directly exploits the motion compensation information and the prediction e...
Suchendra M. Bhandarkar, Aparna A. Khombhadia
ACL
1997
13 years 11 months ago
A Portable Algorithm for Mapping Bitext Correspondence
The first step in most empirical work in multilingual NLP is to construct maps of the correspondence between texts and their translations (bitext maps). The Smooth Injective Map R...
I. Dan Melamed
IPCO
1998
87views Optimization» more  IPCO 1998»
13 years 11 months ago
Simple Generalized Maximum Flow Algorithms
We introduce a gain-scaling technique for the generalized maximum ow problem. Using this technique, we present three simple and intuitive polynomial-time combinatorialalgorithms fo...
Éva Tardos, Kevin D. Wayne
ICMAS
2000
13 years 11 months ago
Using Similarity Criteria to Make Negotiation Trade-Offs
This paper addresses the issues involved in software agents making trade-offs during automated negotiations in which they have information uncertainty and resource limitations. In...
Peyman Faratin, Carles Sierra, Nicholas R. Jenning...
AAAI
1997
13 years 11 months ago
Worst-Case Absolute Loss Bounds for Linear Learning Algorithms
The absolute loss is the absolute difference between the desired and predicted outcome. I demonstrateworst-case upper bounds on the absolute loss for the perceptron algorithm and ...
Tom Bylander
WSCG
2003
145views more  WSCG 2003»
13 years 11 months ago
Real-Time Soft Shadows Using a Single Light Sample
We present a real-time rendering algorithm that generates soft shadows of dynamic scenes using a single light sample. As a depth-map algorithm it can handle arbitrary shadowed sur...
Florian Kirsch, Jürgen Döllner
ESANN
2000
13 years 11 months ago
An algorithm for the addition of time-delayed connections to recurrent neural networks
: Recurrent neural networks possess interesting universal approximation capabilities, making them good candidates for time series modeling. Unfortunately, long term dependencies ar...
Romuald Boné, Michel Crucianu, Jean Pierre ...