Sciweavers

456 search results - page 33 / 92
» Unsupervised Learning of Generalized Names
Sort
View
ICTAI
2009
IEEE
15 years 5 months ago
EBLearn: Open-Source Energy-Based Learning in C++
Energy-based learning (EBL) is a general framework to describe supervised and unsupervised training methods for probabilistic and non-probabilistic factor graphs. An energy-based ...
Pierre Sermanet, Koray Kavukcuoglu, Yann LeCun
MM
2005
ACM
145views Multimedia» more  MM 2005»
15 years 4 months ago
Multiple instance learning for labeling faces in broadcasting news video
Labeling faces in news video with their names is an interesting research problem which was previously solved using supervised methods that demand significant user efforts on lab...
Jun Yang 0003, Rong Yan, Alexander G. Hauptmann
CIKM
2005
Springer
15 years 4 months ago
A hybrid approach to NER by MEMM and manual rules
This paper describes a framework for defining domain specific Feature Functions in a user friendly form to be used in a Maximum Entropy Markov Model (MEMM) for the Named Entity Re...
Moshe Fresko, Binyamin Rosenfeld, Ronen Feldman
86
Voted
ISCAS
2006
IEEE
103views Hardware» more  ISCAS 2006»
15 years 5 months ago
Towards autonomous adaptive behavior in a bio-inspired CNN-controlled robot
— This paper describes a general approach for the unsupervised learning of behaviors in a behavior-based robot. The key idea is to formalize a behavior produced by a Motor Map dr...
Paolo Arena, Luigi Fortuna, Mattia Frasca, Luca Pa...
CCR
2006
136views more  CCR 2006»
14 years 11 months ago
Traffic classification on the fly
The early detection of applications associated with TCP flows is an essential step for network security and traffic engineering. The classic way to identify flows, i.e. looking at...
Laurent Bernaille, Renata Teixeira, Ismael Akodken...