Authors
Oriol Vinyals, Meire Fortunato, Navdeep Jaitly
Publication date
2015
Conference
Advances in Neural Information Processing Systems
Pages
2692-2700
Description
Abstract We introduce a new neural architecture to learn the conditional probability of an
output sequence with elements that arediscrete tokens corresponding to positions in an
input sequence. Such problems cannot be trivially addressed by existent approaches such
as sequence-to-sequence and Neural Turing Machines, because the number of target
classes in eachstep of the output depends on the length of the input, which is variable.
Problems such as sorting variable sized sequences, and various ...
Total citations
20152016829
Scholar articles
O Vinyals, M Fortunato, N Jaitly - Advances in Neural Information Processing Systems, 2015