A Random Matrix Approach to Echo-State Neural Networks
Proceedings of The 33rd International Conference on Machine Learning, PMLR 48:517-525, 2016.
Recurrent neural networks, especially in their linear version, have provided many qualitative insights on their performance under different configurations. This article provides, through a novel random matrix framework, the quantitative counterpart of these performance results, specifically in the case of echo-state networks. Beyond mere insights, our approach conveys a deeper understanding on the core mechanism under play for both training and testing.