Improved Data Modeling Using Coupled Artificial Neural Networks

Zvi Boger, Danny Kogan, Nadav Joseph, Yehuda Zeiri

Research output: Contribution to journalArticlepeer-review

2 Scopus citations

Abstract

Our senses perceive the world, but what happens if one of the senses is degraded through illness or injury? In such situations, the brain compensates by enhancing the remaining senses. This suggests that networks that process the data received by the senses are coupled. Similar situations can occur in scientific and engineering problems when independent measurement methods, based on different principles, are used to study the same characteristics of a system. In such situation, one can develop reliable artificial neural network (ANN) based models; each trained using data obtained by a different measurement method. This raises the question if it is possible to couple these different models to obtain and improved more accurate model. In this paper, we explore this possibility by training two ANN models that can recognize alphabet letters in a noisy environment. The performance of these ANNs are optimized by varying the number of hidden neurons (HN). The first ANN model trained using pictorial presentation of the letters while the second by corresponding audio signals. The two separate ANNs are trained using the two alphabet letters presentation to which different levels of white noise are added. Different schemes to couple the two systems are examined. For some coupling schemes, the combined system result in highly improved letter recognition than the two original separate ANNs did. Examination of the entropy related to the number of HNs showed that increased entropy is related to a higher error in letter recognition.

Original languageEnglish
Pages (from-to)577-590
Number of pages14
JournalNeural Processing Letters
Volume51
Issue number1
DOIs
StatePublished - 1 Feb 2020

Keywords

  • Coupled artificial neural networks
  • Hidden layer entropy
  • Letter recognition
  • Noisy environment

ASJC Scopus subject areas

  • Software
  • Neuroscience (all)
  • Computer Networks and Communications
  • Artificial Intelligence

Fingerprint

Dive into the research topics of 'Improved Data Modeling Using Coupled Artificial Neural Networks'. Together they form a unique fingerprint.

Cite this