Skip to main navigation Skip to search Skip to main content

Mutual Information Decay Curves and Hyper-parameter Grid Search Design for Recurrent Neural Architectures

  • Abhijit Mahalunkar
  • , John D. Kelleher

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

We present an approach to design the grid searches for hyper-parameter optimization for recurrent neural architectures. The basis for this approach is the use of mutual information to analyze long distance dependencies (LDDs) within a dataset. We also report a set of experiments that demonstrate how using this approach, we obtain state-of-the-art results for DilatedRNNs across a range of benchmark datasets.

Original languageEnglish
Title of host publicationNeural Information Processing - 27th International Conference, ICONIP 2020, Proceedings
EditorsHaiqin Yang, Kitsuchart Pasupa, Andrew Chi-Sing Leung, James T. Kwok, Jonathan H. Chan, Irwin King
PublisherSpringer Science and Business Media Deutschland GmbH
Pages616-624
Number of pages9
ISBN (Print)9783030638221
DOIs
Publication statusPublished - 2020
Event27th International Conference on Neural Information Processing, ICONIP 2020 - Bangkok, Thailand
Duration: 18 Nov 202022 Nov 2020

Publication series

NameCommunications in Computer and Information Science
Volume1333
ISSN (Print)1865-0929
ISSN (Electronic)1865-0937

Conference

Conference27th International Conference on Neural Information Processing, ICONIP 2020
Country/TerritoryThailand
CityBangkok
Period18/11/2022/11/20

Keywords

  • Hyper-parameter tuning
  • Long Distance Dependencies
  • Recurrent neural architectures
  • Vanishing gradients

Fingerprint

Dive into the research topics of 'Mutual Information Decay Curves and Hyper-parameter Grid Search Design for Recurrent Neural Architectures'. Together they form a unique fingerprint.

Cite this