Sciweavers

4578 search results - page 127 / 916
» Learning from Multi-source Data
Sort
View
JMLR
2010
106views more  JMLR 2010»
14 years 8 months ago
Why Does Unsupervised Pre-training Help Deep Learning?
Much recent research has been devoted to learning algorithms for deep architectures such as Deep Belief Networks and stacks of auto-encoder variants, with impressive results obtai...
Dumitru Erhan, Yoshua Bengio, Aaron C. Courville, ...
IJCAI
2001
15 years 3 months ago
Using Case-Base Data to Learn Adaptation Knowledge for Design
One advantage of Case-Based Reasoning (CBR) is the relative ease of constructing and maintaining CBR systems, especially as a number of commercial CBR tools are available. However...
Jacek Jarmulak, Susan Craw, Ray Rowe
ISWC
2006
IEEE
15 years 7 months ago
Towards Less Supervision in Activity Recognition from Wearable Sensors
Activity Recognition has gained a lot of interest in recent years due to its potential and usefulness for context-aware wearable computing. However, most approaches for activity r...
Tâm Huynh, Bernt Schiele
BIOCOMP
2006
15 years 3 months ago
Polyome: A Learning System for Extracting Bioinformatic Data
: The exponential growth in the quantity of publicly available genetic data and the proliferation of bioinformatic databases mean that scientists need computerized tools more than ...
Bob Myers, Trevor I. Dix, Ross L. Coppel, David G....
COLT
2005
Springer
15 years 7 months ago
From Graphs to Manifolds - Weak and Strong Pointwise Consistency of Graph Laplacians
In the machine learning community it is generally believed that graph Laplacians corresponding to a finite sample of data points converge to a continuous Laplace operator if the s...
Matthias Hein, Jean-Yves Audibert, Ulrike von Luxb...