.png){kind=icon}
.png){kind=icon}
Return
Deep reservoir computing: A critical experimental analysis
.png){kind=icon}
OA
AI
DOI：10.1016/j.neucom.2016.12.089.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
In this paper, we propose an empirical analysis of deep recurrent neural network (RNN) architectures with stacked layers. The main aim is to address some fundamental open research issues on the significance of creating deep layered architectures in RNN and to characterize the inherent hierarchical representation of time in such models, especially for efficient implementations. In particular, the analysis aims at the study and proposal of approaches to develop and enhance hierarchical dynamics in deep architectures within the efficient Reservoir Computing (RC) framework for RNN modeling. The effect of a deep layered organization of RC models is investigated in terms of both occurrence of multiple time-scale and increasing of richness of the dynamics. It turns out that a deep layering of recurrent models allows an effective diversification of temporal representations in the layers of the hierarchy, by amplifying the effects of the factors influencing the time-scales and the richness of the dynamics, measured as the entropy of recurrent units activations. The advantages of the proposed approach are also highlighted by measuring the increment of the short-term memory capacity of the RC models. (C) 2017 Elsevier B.V. All rights reserved.
Keywords:
Reservoir computing
Echo State Networks
Deep Learning
Deep neural networks
Recurrent neural networks
Multiple time-scale dynamics
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.