Sciweavers

139 search results - page 16 / 28
» On the Generalization Ability of On-Line Learning Algorithms
Sort
View
NIPS
2008
14 years 11 months ago
On the Complexity of Linear Prediction: Risk Bounds, Margin Bounds, and Regularization
This work characterizes the generalization ability of algorithms whose predictions are linear in the input vector. To this end, we provide sharp bounds for Rademacher and Gaussian...
Sham M. Kakade, Karthik Sridharan, Ambuj Tewari
71
Voted
GECCO
2005
Springer
204views Optimization» more  GECCO 2005»
15 years 3 months ago
Modeling systems with internal state using evolino
Existing Recurrent Neural Networks (RNNs) are limited in their ability to model dynamical systems with nonlinearities and hidden internal states. Here we use our general framework...
Daan Wierstra, Faustino J. Gomez, Jürgen Schm...
104
Voted
ISCIS
2005
Springer
15 years 3 months ago
Classification of Volatile Organic Compounds with Incremental SVMs and RBF Networks
Support Vector Machines (SVMs) have been applied to solve the classification of volatile organic compounds (VOC) data in some recent studies. SVMs provide good generalization perfo...
Zeki Erdem, Robi Polikar, Nejat Yumusak, Fikret S....
IMC
2007
ACM
14 years 11 months ago
Learning network structure from passive measurements
The ability to discover network organization, whether in the form of explicit topology reconstruction or as embeddings that approximate topological distance, is a valuable tool. T...
Brian Eriksson, Paul Barford, Robert Nowak, Mark C...
ICASSP
2010
IEEE
14 years 10 months ago
Semi-Supervised Fisher Linear Discriminant (SFLD)
Supervised learning uses a training set of labeled examples to compute a classifier which is a mapping from feature vectors to class labels. The success of a learning algorithm i...
Seda Remus, Carlo Tomasi