Sciweavers

993 search results - page 65 / 199
» Learning RoboCup-Keepaway with Kernels
Sort
View
142
Voted
ICML
2004
IEEE
16 years 6 months ago
SVM-based generalized multiple-instance learning via approximate box counting
The multiple-instance learning (MIL) model has been very successful in application areas such as drug discovery and content-based imageretrieval. Recently, a generalization of thi...
Qingping Tao, Stephen D. Scott, N. V. Vinodchandra...
ECCV
2010
Springer
15 years 10 months ago
Learning to Recognize Objects from Unseen Modalities
Abstract. In this paper we investigate the problem of exploiting multiple sources of information for object recognition tasks when additional modalities that are not present in the...
WEBI
2010
Springer
15 years 3 months ago
Image Set Classification Using Multi-layer Multiple Instance Learning with Application to Cannabis Website Classification
We propose using multi-layer multiple instance learning (MMIL) for image set classification and applying it to the task of cannabis website classification. We treat each image as a...
Nianhua Xie, Haibin Ling, Weiming Hu
ICML
2008
IEEE
16 years 6 months ago
Deep learning via semi-supervised embedding
We show how nonlinear embedding algorithms popular for use with shallow semisupervised learning techniques such as kernel methods can be applied to deep multilayer architectures, ...
Frédéric Ratle, Jason Weston, Ronan ...
ICML
2004
IEEE
15 years 11 months ago
Kernel-based discriminative learning algorithms for labeling sequences, trees, and graphs
We introduce a new perceptron-based discriminative learning algorithm for labeling structured data such as sequences, trees, and graphs. Since it is fully kernelized and uses poin...
Hisashi Kashima, Yuta Tsuboi