Sciweavers

497 search results - page 76 / 100
» Netlearning and Learning through Networks
Sort
View
103
Voted
IJCNN
2000
IEEE
15 years 6 months ago
Continuous Optimization of Hyper-Parameters
Many machine learning algorithms can be formulated as the minimization of a training criterion which involves (1) \training errors" on each training example and (2) some hype...
Yoshua Bengio
JITECH
2010
116views more  JITECH 2010»
15 years 10 days ago
Design theory for dynamic complexity in information infrastructures: the case of building internet
We propose a design theory that tackles dynamic complexity in the design for Information Infrastructures (IIs) defined as a shared, open, heterogeneous and evolving socio-technica...
Ole Hanseth, Kalle Lyytinen
NN
2010
Springer
183views Neural Networks» more  NN 2010»
15 years 9 days ago
Dimensionality reduction for density ratio estimation in high-dimensional spaces
The ratio of two probability density functions is becoming a quantity of interest these days in the machine learning and data mining communities since it can be used for various d...
Masashi Sugiyama, Motoaki Kawanabe, Pui Ling Chui
NECO
2011
14 years 8 months ago
Least-Squares Independent Component Analysis
Accurately evaluating statistical independence among random variables is a key element of Independent Component Analysis (ICA). In this paper, we employ a squared-loss variant of ...
Taiji Suzuki, Masashi Sugiyama
CORR
2011
Springer
177views Education» more  CORR 2011»
14 years 5 months ago
Gossip PCA
Eigenvectors of data matrices play an important role in many computational problems, ranging from signal processing to machine learning and control. For instance, algorithms that ...
Satish Babu Korada, Andrea Montanari, Sewoong Oh