Learning Sequence Neighbourhood Metrics
Neural and Evolutionary Computing
2013-08-23 v2 Machine Learning
Abstract
Recurrent neural networks (RNNs) in combination with a pooling operator and the neighbourhood components analysis (NCA) objective function are able to detect the characterizing dynamics of sequences and embed them into a fixed-length vector space of arbitrary dimensionality. Subsequently, the resulting features are meaningful and can be used for visualization or nearest neighbour classification in linear time. This kind of metric learning for sequential data enables the use of algorithms tailored towards fixed length vector spaces such as R^n.
Cite
@article{arxiv.1109.2034,
title = {Learning Sequence Neighbourhood Metrics},
author = {Justin Bayer and Christian Osendorfer and Patrick van der Smagt},
journal= {arXiv preprint arXiv:1109.2034},
year = {2013}
}
Comments
Artificial Neural Networks and Machine Learning ICANN 2012 Springer Berlin Heidelberg 2012. 531-538