Sciweavers

986 search results - page 168 / 198
» Zero-data Learning of New Tasks
Sort
View
AND
2010
14 years 7 months ago
Reshaping automatic speech transcripts for robust high-level spoken document analysis
High-level spoken document analysis is required in many applications seeking access to the semantic content of audio data, such as information retrieval, machine translation or au...
Julien Fayolle, Fabienne Moreau, Christian Raymond...
ICDE
2012
IEEE
304views Database» more  ICDE 2012»
13 years 7 days ago
Learning-based Query Performance Modeling and Prediction
— Accurate query performance prediction (QPP) is central to effective resource management, query optimization and query scheduling. Analytical cost models, used in current genera...
Mert Akdere, Ugur Çetintemel, Matteo Rionda...
IJCNN
2006
IEEE
15 years 3 months ago
Adaptation of Artificial Neural Networks Avoiding Catastrophic Forgetting
— In connectionist learning, one relevant problem is “catastrophic forgetting” that may occur when a network, trained with a large set of patterns, has to learn new input pat...
Dario Albesano, Roberto Gemello, Pietro Laface, Fr...
ICML
2006
IEEE
15 years 10 months ago
Efficient lazy elimination for averaged one-dependence estimators
Semi-naive Bayesian classifiers seek to retain the numerous strengths of naive Bayes while reducing error by weakening the attribute independence assumption. Backwards Sequential ...
Fei Zheng, Geoffrey I. Webb
ICML
2000
IEEE
15 years 10 months ago
Maximum Entropy Markov Models for Information Extraction and Segmentation
Hidden Markov models (HMMs) are a powerful probabilistic tool for modeling sequential data, and have been applied with success to many text-related tasks, such as part-of-speech t...
Andrew McCallum, Dayne Freitag, Fernando C. N. Per...