Negatively Correlated Echo State Networks
نویسندگان
چکیده
Echo State Network (ESN) is a special type of recurrent neural network with fixed random recurrent part (reservoir) and a trainable reservoir-to-output readout mapping (typically obtained by linear regression). In this work we utilise an ensemble of ESNs with diverse reservoirs whose collective read-out is obtained through Negative Correlation Learning (NCL) of ensemble of Multi-Layer Perceptrons (MLP), where each individual MPL realises the readout from a single ESN. Experimental results on three data sets confirm that, compared with both single ESN and flat ensembles of ESNs, NCL based ESN ensembles achieve better generalisation performance.
منابع مشابه
An artificial Neural Network approach to monitor and diagnose multi-attribute quality control processes
One of the existing problems of multi-attribute process monitoring is the occurrence of high number of false alarms (Type I error). Another problem is an increase in the probability of not detecting defects when the process is monitored by a set of independent uni-attribute control charts. In this paper, we address both of these problems and consider monitoring correlated multi-attributes proce...
متن کاملGraph theoretical analysis of functional networks and its relationship to cognitive decline in patients with carotid stenosis.
Significant carotid stenosis compromises hemodynamics and impairs cognitive functions. The interplay between these changes and brain connectivity has rarely been investigated. We aimed to discover the changes of functional connectivity and its relation to cognitive decline in carotid stenosis patients. Twenty-seven patients with unilateral carotid stenosis (≥60%) and 20 age- and sex-matched con...
متن کاملRandomness and isometries in echo state networks and compressed sensing
Although largely different concepts, echo state networks and compressed sensing models both rely on collections of random weights; as the reservoir dynamics for echo state networks, and the sensing coefficients in compressed sensing. Several methods for generating the random matrices and metrics to indicate desirable performance are well-studied in compressed sensing, but less so for echo state...
متن کاملThe impact of global signal regression on resting state correlations: Are anti-correlated networks introduced?
Low-frequency fluctuations in fMRI signal have been used to map several consistent resting state networks in the brain. Using the posterior cingulate cortex as a seed region, functional connectivity analyses have found not only positive correlations in the default mode network but negative correlations in another resting state network related to attentional processes. The interpretation is that...
متن کاملModular Echo State Neural Networks in Time Series Prediction
Echo State neural networks (ESN), which are a special case of recurrent neural networks, are studied from the viewpoint of their learning ability, with a goal to achieve their greater predictive ability. In this paper we study the influence of the memory length on predictive abilities of Echo State neural networks. The conclusion is that Echo State neural networks with fixed memory length can h...
متن کامل