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 ℝn. |
Year | DOI | Venue |
---|---|---|
2012 | 10.1007/978-3-642-33269-2_67 | international conference on artificial neural networks |
Keywords | DocType | Volume |
arbitrary dimensionality,metric learning,fixed length vector space,objective function,nearest neighbour classification,linear time,recurrent neural network,sequence neighbourhood metrics,neighbourhood components analysis,fixed-length vector space,sequential data,evolutionary computing,vector space | Conference | abs/1109.2034 |
Citations | PageRank | References |
2 | 0.45 | 15 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Justin Bayer | 1 | 157 | 32.38 |
Christian Osendorfer | 2 | 125 | 13.24 |
Patrick van der Smagt | 3 | 188 | 24.23 |