A Theoretical Framework for Parallel Implementation of Deep Higher Order Neural Networks

A Theoretical Framework for Parallel Implementation of Deep Higher Order Neural Networks

Shuxiang Xu, Yunling Liu
ISBN13: 9781522507888|ISBN10: 1522507884|EISBN13: 9781522507895
DOI: 10.4018/978-1-5225-0788-8.ch001
Cite Chapter Cite Chapter

MLA

Xu, Shuxiang, and Yunling Liu. "A Theoretical Framework for Parallel Implementation of Deep Higher Order Neural Networks." Nature-Inspired Computing: Concepts, Methodologies, Tools, and Applications, edited by Information Resources Management Association, IGI Global, 2017, pp. 1-11. https://doi.org/10.4018/978-1-5225-0788-8.ch001

APA

Xu, S. & Liu, Y. (2017). A Theoretical Framework for Parallel Implementation of Deep Higher Order Neural Networks. In I. Management Association (Ed.), Nature-Inspired Computing: Concepts, Methodologies, Tools, and Applications (pp. 1-11). IGI Global. https://doi.org/10.4018/978-1-5225-0788-8.ch001

Chicago

Xu, Shuxiang, and Yunling Liu. "A Theoretical Framework for Parallel Implementation of Deep Higher Order Neural Networks." In Nature-Inspired Computing: Concepts, Methodologies, Tools, and Applications, edited by Information Resources Management Association, 1-11. Hershey, PA: IGI Global, 2017. https://doi.org/10.4018/978-1-5225-0788-8.ch001

Export Reference

Mendeley
Favorite

Abstract

This chapter proposes a theoretical framework for parallel implementation of Deep Higher Order Neural Networks (HONNs). First, we develop a new partitioning approach for mapping HONNs to individual computers within a master-slave distributed system (a local area network). This will allow us to use a network of computers (rather than a single computer) to train a HONN to drastically increase its learning speed: all of the computers will be running the HONN simultaneously (parallel implementation). Next, we develop a new learning algorithm so that it can be used for HONN learning in a distributed system environment. Finally, we propose to improve the generalisation ability of the new learning algorithm as used in a distributed system environment. Theoretical analysis of the proposal is thoroughly conducted to verify the soundness of the new approach. Experiments will be performed to test the new algorithm in the future.

Request Access

You do not own this content. Please login to recommend this title to your institution's librarian or purchase it from the IGI Global bookstore.