Machine Learning

Sequence stacking using dual encoder Seq2Seq recurrent networks

Tagged: , ,

This topic contains 0 replies, has 1 voice, and was last updated by  arXiv 1 month, 2 weeks ago.


  • arXiv
    5 pts

    Sequence stacking using dual encoder Seq2Seq recurrent networks

    A widely studied non-polynomial (NP) hard problem lies in finding a route between the two nodes of a graph. Often meta-heuristics algorithms such as $A^{*}$ are employed on graphs with a large number of nodes. Here, we propose a deep recurrent neural network architecture based on the Sequence-2-Sequence model, widely used, for instance in text translation. Particularly, we illustrate that utilising a context vector that has been learned from two different recurrent networks enables increased accuracies in learning the shortest route of a graph. Additionally, we show that one can boost the performance of the Seq2Seq network by smoothing the loss function using a homotopy continuation of the decoder’s loss function.

    Sequence stacking using dual encoder Seq2Seq recurrent networks
    by Alessandro Bay, Biswa Sengupta
    https://arxiv.org/pdf/1710.04211v1.pdf

You must be logged in to reply to this topic.