Sciweavers

69 search results - page 9 / 14
» Phone recognition using Restricted Boltzmann Machines
Sort
View
AAI
2010
195views more  AAI 2010»
13 years 4 months ago
Automatic Extraction of Go Game Positions from Images: a Multi-Strategical Approach to Constrained Multi-Object Recognition
Here, we present a constrained object recognition task that has been robustly solved largely with simple machine learning methods, using a small corpus of about 100 images taken u...
Alexander K. Seewald
ICML
2008
IEEE
14 years 8 months ago
On the quantitative analysis of deep belief networks
Deep Belief Networks (DBN's) are generative models that contain many layers of hidden variables. Efficient greedy algorithms for learning and approximate inference have allow...
Ruslan Salakhutdinov, Iain Murray
VRST
2010
ACM
13 years 5 months ago
An adaptive training-free feature tracker for mobile phones
While tracking technologies based on fiducial markers have dominated the development of Augmented Reality (AR) applications for almost a decade, various real-time capable approach...
Jan Herling, Wolfgang Broll
INTERSPEECH
2010
13 years 2 months ago
Improved language recognition using mixture components statistics
One successful approach to language recognition is to focus on the most discriminative high level features of languages, such as phones and words. In this paper, we applied a simi...
Abualsoud Hanani, Michael J. Carey 0002, Martin J....
SENSYS
2010
ACM
13 years 5 months ago
The Jigsaw continuous sensing engine for mobile phone applications
Supporting continuous sensing applications on mobile phones is challenging because of the resource demands of long-term sensing, inference and communication algorithms. We present...
Hong Lu, Jun Yang, Zhigang Liu, Nicholas D. Lane, ...