Author ORCID Identifier
Available under a Creative Commons Attribution Non-Commercial Share Alike 4.0 International Licence
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.
Mahalunkar, A & Kelleher, John D. (2020) Mutual Information Decay Curves and Hyper-parameter Grid Search Design for Recurrent Neural Architectures,In book: Neural Information Processing, 27th International Conference, ICONIP 2020, Bangkok, Thailand, November 18–22, 2020, Proceedings, Part V (pp.616-624) DOI:10.1007/978-3-030-63823-8_70