Recurrent Neural Networks with Multi-Branch Structure

DOI DOI Web Site Web Site Web Site View 1 Remaining Hide 16 References Open Access
  • Yamashita Takashi
    Graduate School of Information, Production and Systems, Waseda University
  • Mabu Shingo
    Graduate School of Information, Production and Systems, Waseda University
  • Hirasawa Kotaro
    Graduate School of Information, Production and Systems, Waseda University
  • Furuzuki Takayuki
    Graduate School of Information, Production and Systems, Waseda University

Bibliographic Information

Other Title
  • マルチブランチ構造を有するリカレントニューラルネットワーク
  • マルチブランチ コウゾウ オ ユウスル リカレント ニューラル ネットワーク
  • Recurrent neural networks with multi‐branch structure

Search this article

Description

Universal Learning Networks (ULNs) provide a generalized framework to many kinds of structures of neural networks with supervised learning. Multi-Branch Neural Networks (MBNNs) which use the framework of ULNs have been already shown that they have better representation ability in feedforward neural networks (FNNs). 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 they show that their representation ability is better 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.

Journal

References(16)*help

See more

Keywords

Details 詳細情報について

Report a problem

Back to top