Recurrent neural networks with multi-branch structure

Takashi Yamashita*, Shingo Mabu, Kotaro Hirasawa, Takayuki Furuzuki

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review


Universal Learning Networks (ULNs) provide a generalized framework for many kinds of structures in neural networks with supervised learning. Multi-Branch Neural Networks (MBNNs) which use the framework of ULNs have already been shown to have better representation ability in feedforward neural networks (FNNs). The multi-branch structure of MBNNs can be easily extended to recurrent neural networks (RNNs) because the characteristics of ULNs include the connection of multiple branches with arbitrary time delays. In this paper, therefore, RNNs with multi-branch structure are proposed and are shown to have better representation ability than conventional RNNs. RNNs can represent dynamical systems and are useful for time series prediction. The performance evaluation of RNNs with multi-branch structure was carried out using a benchmark of time series prediction. Simulation results showed that RNNs with multi-branch structure could obtain better performance than conventional RNNs, and also showed that they could improve the representation ability even if they are smaller-sized networks.

Original languageEnglish
Pages (from-to)37-44
Number of pages8
JournalElectronics and Communications in Japan, Part II: Electronics (English translation of Denshi Tsushin Gakkai Ronbunshi)
Issue number9
Publication statusPublished - 2008


  • Multi-branch
  • Recurrent neural networks
  • Time series prediction
  • Universal learning networks

ASJC Scopus subject areas

  • General Physics and Astronomy
  • Computer Networks and Communications
  • Electrical and Electronic Engineering


Dive into the research topics of 'Recurrent neural networks with multi-branch structure'. Together they form a unique fingerprint.

Cite this