Back to search

Goldsmiths, University of London

Sequential recurrent connectionist algorithms for time series modeling of nonlinear dynamical systems

Abstract

dc:description

This thesis deals with the methodology of building data driven models of nonlinear systems through the framework of dynamic modeling. More specifically this thesis focuses on sequential optimization of nonlinear dynamic models called recurrent neural networks (RNNs). In particular, the thesis considers fully connected recurrent neural networks with one hidden layer of neurons for modeling of nonlinear dynamical systems. The general objective is to improve sequential training of the RNN through sequential second-order methods and to improve generalization of the RNN by regularization. The total contributions of the proposed thesis can be summarized as follows: 1. First, a sequential Bayesian training and regularization strategy for recurrent neural networks based on an extension of the Evidence Framework is developed. 2. Second, an efficient ensemble method for Sequential Monte Carlo filtering is proposed. The methodology allows for efficient O(H 2 ) sequential training of the RNN. 3. Last, the Expectation Maximization (EM) framework is proposed for training RNNs sequentially.

Author and committee

dc:creator, dc:contributor.*
Author dc:creator
  • Mirikitani, Derrick Takeshi

Subjects

dc:subject × 1

Rights

Language dc:language
eng

Identifiers

dc:identifier.*
Identifier
Mirikitani, Derrick Takeshi. 2010. Sequential recurrent connectionist algorithms for time series modeling of nonlinear dynamical systems. Doctoral thesis, Goldsmiths, University of London [Thesis]

Chain of custody

source
Harvested from
Goldsmiths, University of London
Base URL
research.gold.ac.uk/cgi/oai2
Last updated
2026-11-18
Source record
OAI-PMH GetRecord
citation

Mirikitani, Derrick Takeshi. Sequential recurrent connectionist algorithms for time series modeling of nonlinear dynamical systems. 2010.