DropELM: Fast Neural Network Regularization with Dropout and DropConnect

Ioannis Pitas, Alexandros Iosifidis, Anastasios Tefas

Research output: Contribution to journalArticle (Academic Journal)peer-review

32 Citations (Scopus)
343 Downloads (Pure)

Abstract

In this paper, we propose an extension of the Extreme Learning Machine algorithm for Single-hidden Layer Feedforward Neural network training that incorporates Dropout and DropConnect regularization in its optimization process. We show that both types of regularization lead to the same solution for the network output weights calculation, which is adopted by the proposed DropELM network. The proposed algorithm is able to exploit Dropout and DropConnect regularization, without computationally intensive iterative weight tuning. We show that the adoption of such a regularization approach can lead to better solutions for the network output weights. We incorporate the proposed regularization approach in several recently proposed ELM algorithms and show that their performance can be enhanced without requiring much additional computational cost.
Original languageEnglish
Pages (from-to)57-66
JournalNeurocomputing
Volume162
Early online date13 Apr 2015
DOIs
Publication statusPublished - 25 Aug 2015

Keywords

  • Single Hidden Layer Feedforward Networks
  • Extreme Learning Machine
  • Regularization
  • Dropout
  • DropConnect

Fingerprint Dive into the research topics of 'DropELM: Fast Neural Network Regularization with Dropout and DropConnect'. Together they form a unique fingerprint.

Cite this