Sciweavers

986 search results - page 24 / 198
» Zero-data Learning of New Tasks
Sort
View
C5
2005
IEEE
15 years 3 months ago
Suggestions for New Features to Support Collaborative Learning in Virtual Worlds
The authors have some experience in building virtual worlds for education purposes, in archaeology and for language learning. However, many mainstream world-building applications ...
Erik Champion, Sachiyo Sekiguchi
DCC
2006
IEEE
15 years 9 months ago
Compression and Machine Learning: A New Perspective on Feature Space Vectors
The use of compression algorithms in machine learning tasks such as clustering and classification has appeared in a variety of fields, sometimes with the promise of reducing probl...
D. Sculley, Carla E. Brodley
ILP
2003
Springer
15 years 2 months ago
Relational IBL in Music with a New Structural Similarity Measure
It is well known that many hard tasks considered in machine learning and data mining can be solved in an rather simple and robust way with an instance- and distance-based approach....
Asmir Tobudic, Gerhard Widmer
NCI
2004
142views Neural Networks» more  NCI 2004»
14 years 11 months ago
A competitive and cooperative learning approach to robust data clustering
This paper presents a new semi-competitive learning paradigm named Competitive and Cooperative Learning (CCL), in which seed points not only compete each other for updating to ada...
Yiu-ming Cheung
NIPS
1997
14 years 11 months ago
A Framework for Multiple-Instance Learning
Multiple-instance learning is a variation on supervised learning, where the task is to learn a concept given positive and negative bags of instances. Each bag may contain many ins...
Oded Maron, Tomás Lozano-Pérez