Sciweavers

505 search results - page 62 / 101
» Importance weighted active learning
Sort
View
SIGPRO
2010
111views more  SIGPRO 2010»
13 years 3 months ago
Semi-supervised speaker identification under covariate shift
In this paper, we propose a novel semi-supervised speaker identification method that can alleviate the influence of non-stationarity such as session dependent variation, the recor...
Makoto Yamada, Masashi Sugiyama, Tomoko Matsui
CSCWD
2005
Springer
14 years 2 months ago
Workflow-based e-learning platform
E-learning has become one of most important means for the future education, especially for universities. This paper is based our e-learning teaching experience which comes from on...
Jianming Yong
BC
2002
70views more  BC 2002»
13 years 8 months ago
Mechanisms and significance of spike-timing dependent plasticity
Hebb's original postulate left two important issues unaddressed: (i) what is the effective time window between pre- and postsynaptic activity that will result in potentiation?...
Uma R. Karmarkar, Mark T. Najarian, Dean V. Buonom...
ICIP
2010
IEEE
13 years 6 months ago
Saliency detection based on short-term sparse representation
Representation and measurement are two important issues for saliency models. Different with previous works that learnt sparse features from large scale natural statistics, we prop...
Xiaoshuai Sun, Hongxun Yao, Rongrong Ji, Pengfei X...
BC
2002
108views more  BC 2002»
13 years 8 months ago
Spike-timing-dependent plasticity: common themes and divergent vistas
Abstract. Recent experimental observations of spiketiming-dependent synaptic plasticity (STDP) have revitalized the study of synaptic learning rules. The most surprising aspect of ...
Ádám Kepecs, Mark C. W. van Rossum, ...