Sciweavers

1860 search results - page 307 / 372
» Boosting Methods for Regression
Sort
View
INFORMATICALT
1998
89views more  INFORMATICALT 1998»
14 years 11 months ago
Simply Invertible Matrices and Fast Prediction
Abstract. We study invertibility of big n × n matrices. There exists a number of algorithms, especially in mathematical statistics and numerical mathematics, requiring to invert s...
Valdas Diciunas
JAIR
1998
198views more  JAIR 1998»
14 years 11 months ago
Probabilistic Inference from Arbitrary Uncertainty using Mixtures of Factorized Generalized Gaussians
This paper presents a general and efficient framework for probabilistic inference and learning from arbitrary uncertain information. It exploits the calculation properties of fini...
Alberto Ruiz, Pedro E. López-de-Teruel, M. ...
NECO
2007
115views more  NECO 2007»
14 years 11 months ago
Training Recurrent Networks by Evolino
In recent years, gradient-based LSTM recurrent neural networks (RNNs) solved many previously RNN-unlearnable tasks. Sometimes, however, gradient information is of little use for t...
Jürgen Schmidhuber, Daan Wierstra, Matteo Gag...
ICANN
2010
Springer
14 years 10 months ago
Autonomous Generation of Internal Representations for Associative Learning
In this contribution, we explore the possibilities of learning in large-scale, multimodal processing systems operating under real-world conditions. Using an instance of a large-sca...
Michaël Garcia Ortiz, Benjamin Dittes, Jannik...
ACL
2010
14 years 9 months ago
Cross-Language Document Summarization Based on Machine Translation Quality Prediction
Cross-language document summarization is a task of producing a summary in one language for a document set in a different language. Existing methods simply use machine translation ...
Xiaojun Wan, Huiying Li, Jianguo Xiao