Pre-trainable Reservoir Computing with Recursive Neural Gas

by   Luca Carcano, et al.
University of Pavia
ST Microelectronics

Echo State Networks (ESN) are a class of Recurrent Neural Networks (RNN) that has gained substantial popularity due to their effectiveness, ease of use and potential for compact hardware implementation. An ESN contains the three network layers input, reservoir and readout where the reservoir is the truly recurrent network. The input and reservoir layers of an ESN are initialized at random and never trained afterwards and the training of the ESN is applied to the readout layer only. The alternative of Recursive Neural Gas (RNG) is one of the many proposals of fully-trainable reservoirs that can be found in the literature. Although some improvements in performance have been reported with RNG, to the best of authors' knowledge, no experimental comparative results are known with benchmarks for which ESN is known to yield excellent results. This work describes an accurate model of RNG together with some extensions to the models presented in the literature and shows comparative results on three well-known and accepted datasets. The experimental results obtained show that, under specific circumstances, RNG-based reservoirs can achieve better performance.


page 1

page 2

page 3

page 4


Hierarchical Architectures in Reservoir Computing Systems

Reservoir computing (RC) offers efficient temporal data processing with ...

Reservoir Computing on the Hypersphere

Reservoir Computing (RC) refers to a Recurrent Neural Networks (RNNs) fr...

Simple Cycle Reservoirs are Universal

Reservoir computation models form a subclass of recurrent neural network...

Deep Reservoir Computing Using Cellular Automata

Recurrent Neural Networks (RNNs) have been a prominent concept within ar...

Analyzing Echo-state Networks Using Fractal Dimension

This work joins aspects of reservoir optimization, information-theoretic...

A characterization of the Edge of Criticality in Binary Echo State Networks

Echo State Networks (ESNs) are simplified recurrent neural network model...

Integer Echo State Networks: Hyperdimensional Reservoir Computing

We propose an integer approximation of Echo State Networks (ESN) based o...

Please sign up or login with your details

Forgot password? Click here to reset