Evaluating the Learning of Automata through the Use of Recurrent Neural Networks

Authors

  • Alberto Lima
  • Lidio Mauro Lima de Campos Universidade Federal do Pará

Keywords:

Finite Automata, Applied computing, Recurrent Neural Networks.

Abstract

This paper presents the computational potentialities, demonstrating the learning capacity and extrapolation of recurrent neural networks (RNN) through the learning study of finite automata. Initially, the generalized delta rule is presented for a recurrent network. In addition, the theoretical basis on Finite Automata, Moore Machine and Mealy Machine are presented, showing the equivalence between them. We formalized the problem of parity using a Moore Machine and its equivalent Mealy Machine. We proceeded simulation and the results are presented for the problem and  simulation of Tomita languages 1 and 2, testing the extrapolation capacity of each RNN. The results indicated that the neural networks with recurrent architectures have a good capacity of extrapolation for the simulated problems.

Downloads

Download data is not yet available.

Author Biography

Lidio Mauro Lima de Campos, Universidade Federal do Pará

Lídio Mauro Lima de Campos works as Professor of the Federal University of Pará - UFPA at Faculdade de Computação / ICEN. PhD in Electrical Engineering with emphasis in Applied Computation by the Post-Graduation Program in Electrical Engineering - PPGGE in the same institution (2016), Master in Computer Science, Concentration Area: Knowledge Systems, Federal University of Santa Catarina - UFSC (2001) , Graduate in Electrical Engineering University of the Federal University of Pará - UFPA (1998). His research areas include: Natural Computing, Machine Learning, Computational Intelligence, Data Mining and Project Management.

Downloads

Published

2019-05-23

How to Cite

Lima, A., & Lima de Campos, L. M. (2019). Evaluating the Learning of Automata through the Use of Recurrent Neural Networks. IEEE Latin America Transactions, 16(10), 2609–2616. Retrieved from https://latamt.ieeer9.org/index.php/transactions/article/view/514