Author ORCID Identifier

0000-0001-5795-8728

Document Type

Article

Rights

Available under a Creative Commons Attribution Non-Commercial Share Alike 4.0 International Licence

Disciplines

Computer Sciences

Publication Details

International Conference on Neural Information Processing ICONIP 2020: Neural Information Processing

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.

DOI

https://doi.org/10.1007/978-3-030-63823-8_70


Share

COinS