ResearchTrend.AI
  • Papers
  • Communities
  • Events
  • Blog
  • Pricing
Papers
Communities
Social Events
Terms and Conditions
Pricing
Parameter LabParameter LabTwitterGitHubLinkedInBlueskyYoutube

© 2025 ResearchTrend.AI, All rights reserved.

  1. Home
  2. Papers
  3. 2006.08305
19
0

Inner Ensemble Networks: Average Ensemble as an Effective Regularizer

15 June 2020
Abduallah A. Mohamed
Muhammed Mohaimin Sadiq
Ehab Albadawy
Mohamed Elhoseiny
Christian G. Claudel
ArXivPDFHTML
Abstract

We introduce Inner Ensemble Networks (IENs) which reduce the variance within the neural network itself without an increase in the model complexity. IENs utilize ensemble parameters during the training phase to reduce the network variance. While in the testing phase, these parameters are removed without a change in the enhanced performance. IENs reduce the variance of an ordinary deep model by a factor of 1/mL−11/m^{L-1}1/mL−1, where mmm is the number of inner ensembles and LLL is the depth of the model. Also, we show empirically and theoretically that IENs lead to a greater variance reduction in comparison with other similar approaches such as dropout and maxout. Our results show a decrease of error rates between 1.7\% and 17.3\% in comparison with an ordinary deep model. We also show that IEN was preferred by Neural Architecture Search (NAS) methods over prior approaches. Code is available at https://github.com/abduallahmohamed/inner_ensemble_nets.

View on arXiv
Comments on this paper