Construction and Supervised Learning of Long-Term Grey Cognitive Networks

As a new brain-inspired computational model of artificial neural networks, spiking neural networks transmit and process information via precisely timed spike trains. Constructing efficient learning methods is a significant research field in spiking neural networks. In this paper, we present a supervised learning algorithm for multilayer feedforward spiking neural networks; all neurons can fire multiple spikes in all layers. The feedforward network consists of spiking neurons governed by biologically plausible long-term memory spike response model, in which the effect of earlier spikes on the refractoriness is not neglected to incorporate adaptation effects. The gradient descent method is employed to derive synaptic weight updating rule for learning spike trains. The proposed algorithm is tested and verified on spatiotemporal pattern learning problems, including a set of spike train learning tasks and nonlinear pattern classification problems on four UCI datasets. Simulation results indicate that the proposed algorithm can improve learning accuracy in comparison with other supervised learning algorithms.

Download Full-text

A Survey on Traffic Prediction Techniques Using Artificial Intelligence for Communication Networks

Telecom ◽

10.3390/telecom2040029 ◽

2021 ◽

Vol 2 (4) ◽

pp. 518-535

Author(s):

Aaron Chen ◽

Jeffrey Law ◽

Michal Aibin

Keyword(s):

Machine Learning ◽

Communication Networks ◽

Network Performance ◽

Research Effort ◽

Cognitive Networks ◽

Wide Area Networks ◽

Traffic Prediction ◽

Short Term ◽

Prediction Techniques

Much research effort has been conducted to introduce intelligence into communication networks in order to enhance network performance. Communication networks, both wired and wireless, are ever-expanding as more devices are increasingly connected to the Internet. This survey introduces machine learning and the motivations behind it for creating cognitive networks. We then discuss machine learning and statistical techniques to predict future traffic and classify each into short-term or long-term applications. Furthermore, techniques are sub-categorized into their usability in Local or Wide Area Networks. This paper aims to consolidate and present an overview of existing techniques to stimulate further applications in real-world networks.

Download Full-text

Nonsynaptic Error Backpropagation in Long-Term Cognitive Networks

IEEE Transactions on Neural Networks and Learning Systems ◽

10.1109/tnnls.2019.2910555 ◽

2020 ◽

Vol 31 (3) ◽

pp. 865-875 ◽

Cited By ~ 2

Author(s):

Gonzalo Nopoles ◽

Frank Vanhoenshoven ◽

Rafael Falcon ◽

Koen Vanhoof

Keyword(s):

Cognitive Networks

Download Full-text

Recommender system using Long-term Cognitive Networks

Knowledge-Based Systems ◽

10.1016/j.knosys.2020.106372 ◽

2020 ◽

Vol 206 ◽

pp. 106372 ◽

Cited By ~ 1

Author(s):

Gonzalo Nápoles ◽

Isel Grau ◽

Yamisleydi Salgueiro

Keyword(s):

Recommender System ◽

Cognitive Networks

Download Full-text

On the Performance of the Nonsynaptic Backpropagation for Training Long-term Cognitive Networks

10.1049/icp.2021.1434 ◽

2021 ◽

Author(s):

G. Nápoles ◽

I. Grau ◽

L. Concepción ◽

Yamisleydi Salgueiro

Keyword(s):

Cognitive Networks

Download Full-text

Dynamics of Fuzzy-Rough Cognitive Networks

Symmetry ◽

10.3390/sym13050881 ◽

2021 ◽

Vol 13 (5) ◽

pp. 881

Author(s):

István Á. Harmati

Keyword(s):

Cognitive Maps ◽

Black Box ◽

Discrete Dynamical Systems ◽

Cognitive Networks ◽

Fuzzy Cognitive Maps ◽

Classification Problems ◽

Mathematical Properties ◽

Structural Differences ◽

Theoretical Issues

Fuzzy-rough cognitive networks (FRCNs) are interpretable recurrent neural networks, primarily designed for solving classification problems. Their structure is simple and transparent, while the performance is comparable to the well-known black-box classifiers. Although there are many applications on fuzzy cognitive maps and recently for FRCNS, only a very limited number of studies discuss the theoretical issues of these models. In this paper, we examine the behaviour of FRCNs viewing them as discrete dynamical systems. It will be shown that their mathematical properties highly depend on the size of the network, i.e., there are structural differences between the long-term behaviour of FRCN models of different size, which may influence the performance of these modelling tools.

Download Full-text