Deep Echo State Network (DeepESN): A Brief Survey

Abstract

The study of deep recurrent neural networks (RNNs) and, in particular, of deep Reservoir Computing (RC) is gaining an increasing research attention in the neural networks community. The recently introduced Deep Echo State Network (DeepESN) model opened the way to an extremely efficient approach for designing deep neural networks for temporal data. At the same time, the study of DeepESNs allowed to shed light on the intrinsic properties of state dynamics developed by hierarchical compositions of recurrent layers, i.e. on the bias of depth in RNNs architectural design. In this paper, we summarize the advancements in the development, analysis and applications of DeepESNs.

References in corpus (2)

• Comparison between DeepESNs and gated RNNs on multivariate time-series prediction
• Deep Echo State Networks for Diagnosis of Parkinson's Disease

Cited by in corpus (11)

• Deep learning for time series classification: a review
• Review: Deep Learning in Electron Microscopy
• A Review of Designs and Applications of Echo State Networks
• Richness of Deep Echo State Network Dynamics
• Reservoir Topology in Deep Echo State Networks
• Echo State Neural Machine Translation
• Deep learning for time series classification
• Deep Reservoir Networks with Learned Hidden Reservoir Weights using Direct Feedback Alignment
• KNN, An Underestimated Model for Regional Rainfall Forecasting
• TE-ESN: Time Encoding Echo State Network for Prediction Based on Irregularly Sampled Time Series Data
• Empirical Analysis of Limits for Memory Distance in Recurrent Neural Networks