Hierarchical Temporal Representation in Linear Reservoir Computing

05/16/2017
by   Claudio Gallicchio, et al.
0

Recently, studies on deep Reservoir Computing (RC) highlighted the role of layering in deep recurrent neural networks (RNNs). In this paper, the use of linear recurrent units allows us to bring more evidence on the intrinsic hierarchical temporal representation in deep RNNs through frequency analysis applied to the state signals. The potentiality of our approach is assessed on the class of Multiple Superimposed Oscillator tasks. Furthermore, our investigation provides useful insights to open a discussion on the main aspects that characterize the deep learning framework in the temporal domain.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
12/12/2017

Deep Echo State Network (DeepESN): A Brief Survey

The study of deep recurrent neural networks (RNNs) and, in particular, o...
research
05/19/2022

Analyzing Echo-state Networks Using Fractal Dimension

This work joins aspects of reservoir optimization, information-theoretic...
research
08/04/2023

Universal Approximation of Linear Time-Invariant (LTI) Systems through RNNs: Power of Randomness in Reservoir Computing

Recurrent neural networks (RNNs) are known to be universal approximators...
research
03/12/2019

Richness of Deep Echo State Network Dynamics

Reservoir Computing (RC) is a popular methodology for the efficient desi...
research
06/02/2017

Reservoir Computing for Detection of Steady State in Performance Tests of Compressors

Fabrication of devices in industrial plants often includes undergoing qu...
research
07/22/2019

Reservoir Computing Models for Patient-Adaptable ECG Monitoring in Wearable Devices

The reservoir computing paradigm is employed to classify heartbeat anoma...
research
02/01/2023

Quantifying the HIV reservoir with dilution assays and deep viral sequencing

People living with HIV on antiretroviral therapy often have undetectable...

Please sign up or login with your details

Forgot password? Click here to reset