
Sequence stacking using dual encoder Seq2Seq recurrent networks
A widely studied nonpolynomial (NP) hard problem lies in finding a rout...
read it

Approximating metaheuristics with homotopic recurrent neural networks
Much combinatorial optimisation problems constitute a nonpolynomial (NP...
read it

GeoSeq2Seq: Information Geometric SequencetoSequence Networks
The Fisher information metric is an important foundation of information ...
read it

Shortest Reconfiguration Sequence for Sliding Tokens on Spiders
Suppose that two independent sets I and J of a graph with I = J are ...
read it

Generating Shortest Synchronizing Sequences using Answer Set Programming
For a finite state automaton, a synchronizing sequence is an input seque...
read it

Coloring Big Graphs with AlphaGoZero
We show that recent innovations in deep reinforcement learning can effec...
read it
StackSeq2Seq: Dual Encoder Seq2Seq Recurrent Networks
A widely studied nondeterministic polynomial time (NP) hard problem lies in finding a route between the two nodes of a graph. Often metaheuristics 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 Sequence2Sequence (Seq2Seq) 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
Comments
There are no comments yet.