Sequence stacking using dual encoder Seq2Seq recurrent networks

10/11/2017
by   Alessandro Bay, et al.
0

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.

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 3

10/11/2017

StackSeq2Seq: Dual Encoder Seq2Seq Recurrent Networks

A widely studied non-deterministic polynomial time (NP) hard problem lie...
09/07/2017

Approximating meta-heuristics with homotopic recurrent neural networks

Much combinatorial optimisation problems constitute a non-polynomial (NP...
10/25/2017

GeoSeq2Seq: Information Geometric Sequence-to-Sequence Networks

The Fisher information metric is an important foundation of information ...
08/20/2020

Faster Heuristics for Graph Burning

Graph burning is a process of information spreading through the network ...
12/20/2013

Generating Shortest Synchronizing Sequences using Answer Set Programming

For a finite state automaton, a synchronizing sequence is an input seque...
02/11/2021

Variational Bayesian Sequence-to-Sequence Networks for Memory-Efficient Sign Language Translation

Memory-efficient continuous Sign Language Translation is a significant c...
02/06/2018

Multi-Temporal Land Cover Classification with Sequential Recurrent Encoders

Earth observation (EO) sensors deliver data with daily or weekly tempora...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.