Mutual Information Decay Curves and Hyper-parameter Grid Search Design for Recurrent Neural Architectures.
ICONIP (5)(2020)
摘要
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.
更多查看译文
关键词
Long Distance Dependencies, Recurrent neural architectures, Hyper-parameter tuning, Vanishing gradients
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要