A Neural Architecture Based on the Adaptive Resonant Theory and Recurrent Neural Networks

In this paper, we propose a novel neural architecture that adaptively learns an input -output mapping using both supervised and non-supervised trainings. This neural architecture consists of a combination of an ART2 (Adaptive Resonance Theory) neural network and recurrent neural networks. For this end, we developed an Extended Kalman Filter (EKF) based training algorithm for the involved recurrent neural networks. The proposed ART2/EKF neural network is inspired in the visual cortex and the brain mechanisms. More precisely, the non-supervised ART2 neural network is used to coordinate specialized recurrent neural networks in a specific input space domain. Our aim is to design a neural system that learns in real time a new input pattern without retraining the neural network with the whole training set. The proposed neural architecture is used to adaptively predict the traffic volume in a computer network. We verify that the ART2/EKF is capable of finding patterns in the traffic time series as well as to obtain the transmission rate that should be made available in order to avoid byte losses in a computer network link.

[1]  R. C. Katz.  Book Review: The Positive Psychology of Buddhism and Yoga: Paths to Mature Happiness. By Marvin Levine. Mahwah, New Jersey: Lawrence Erlbaum Associates. 2000 , 2000 .

[2]  Paul Zarchan,et al.  Fundamentals of Kalman Filtering: A Practical Approach , 2001 .

[3]  S. Grossberg.  Adaptive Resonance Theory , 2006 .

[4]  Danchi Jiang,et al.  Neural network prediction of radio propagation , 2005, 2005 Australian Communications Theory Workshop.

[5]  D A Pollen,et al.  On the neural correlates of visual perception. , 1999, Cerebral cortex.

[6]  Michael A. Arbib,et al.  The handbook of brain theory and neural networks , 1995, A Bradford book.

[7]  S. Grossberg,et al.  ART 2: self-organization of stable category recognition codes for analog input patterns. , 1987, Applied optics.

[8]  Stephen Grossberg,et al.  Art 2: Self-Organization Of Stable Category Recognition Codes For Analog Input Patterns , 1988, Other Conferences.

[9]  San-qi Li,et al.  Predictive Dynamic Bandwidth Allocation for Efficient Transport of Real-Time VBR Video over ATM , 1995, IEEE J. Sel. Areas Commun..

[10]  Sharad Singhal,et al.  Training Multilayer Perceptrons with the Extende Kalman Algorithm , 1988, NIPS.

[11]  Lee A. Feldkamp,et al.  Neurocontrol of nonlinear dynamical systems with Kalman filter trained recurrent networks , 1994, IEEE Trans. Neural Networks.

[12]  Ronald J. Williams,et al.  Training recurrent networks using the extended Kalman filter , 1992, [Proceedings 1992] IJCNN International Joint Conference on Neural Networks.

[13]  Flávio Henrique,et al.  Alocação Dinâmica de Taxa de Transmissão em Redes de Pacotes Utilizando Redes Neurais Recorrentes Treinadas com Algoritmos em Tempo Real , 2003 .

[14]  Stefanos D. Kollias,et al.  An adaptable neural-network model for recursive nonlinear traffic prediction and modeling of MPEG video sources , 2003, IEEE Trans. Neural Networks.

[15]  D. Levine.  Introduction to Neural and Cognitive Modeling , 2018 .

[16]  M. Page,et al.  Connectionist modelling in psychology: A localist manifesto , 2000, Behavioral and Brain Sciences.