Neural Network Based Nonlinear Weighted Finite Automata

09/13/2017
by   Tianyu Li, et al.
0

Weighted finite automata (WFA) can expressively model functions defined over strings. However, a WFA is inherently a linear model. In this paper, we propose a neural network based nonlinear WFA model along with a learning algorithm. Our learning algorithm performs a nonlinear decomposition of the so-called Hankel matrix (using an encode decoder neural network) from which the transition operators of the model are recovered. We assessed the performance of the proposed model in a simulation study.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
07/04/2018

Connecting Weighted Automata and Recurrent Neural Networks through Spectral Learning

In this paper, we unravel a fundamental connection between weighted fini...
research
10/20/2018

BCR-Net: a neural network based on the nonstandard wavelet form

This paper proposes a novel neural network architecture inspired by the ...
research
10/19/2020

Connecting Weighted Automata, Tensor Networks and Recurrent Neural Networks through Spectral Learning

In this paper, we present connections between three models used in diffe...
research
05/09/2022

Energy Büchi Problems

We show how to efficiently solve energy Büchi problems in finite weighte...
research
03/28/2018

Unreasonable Effectivness of Deep Learning

We show how well known rules of back propagation arise from a weighted c...
research
06/08/2022

Sequential Density Estimation via NCWFAs Sequential Density Estimation via Nonlinear Continuous Weighted Finite Automata

Weighted finite automata (WFAs) have been widely applied in many fields....
research
07/28/2017

Human in the Loop: Interactive Passive Automata Learning via Evidence-Driven State-Merging Algorithms

We present an interactive version of an evidence-driven state-merging (E...

Please sign up or login with your details

Forgot password? Click here to reset