Neural Networks 22 (2009) 489–490
Contents lists available at ScienceDirect
Neural Networks journal homepage: www.elsevier.com/locate/neunet
2009 Special Issue
Advances in neural networks research: An introduction Robert Kozma a,∗ , Steven Bressler b , Leonid Perlovsky c , Ganesh Kumar Venayagamoorthy d a
The University of Memphis, FedEx Institute of Technology, Memphis, TN, USA
b
Florida Atlantic University, Boca Raton, FL, USA
c
Harvard University, Cambridge, MA, USA
d
Missouri Science and Technology University, MO, USA
article Keywords: Neuroscience Cognition Machine Learning Hybrid Systems Soft Computing Dynamic Systems Image Processing Bioinformatics Robotics Power Systems
info
abstract The present Special Issue ‘‘Advances in Neural Networks Research: IJCNN2009’’ provides a state-of-art overview of the field of neural networks. It includes 39 papers from selected areas of the 2009 International Joint Conference on Neural Networks (IJCNN2009). IJCNN2009 took place on June 14-19, 2009 in Atlanta, Georgia, USA, and it represents an exemplary collaboration between the International Neural Networks Society and the IEEE Computational Intelligence Society. Topics in this issue include neuroscience and cognitive science, computational intelligence and machine learning, hybrid techniques, nonlinear dynamics and chaos, various soft computing technologies, intelligent signal processing and pattern recognition, bioinformatics and biomedicine, and engineering applications. © 2009 Elsevier Ltd. All rights reserved.
Overview of Neural Networks Research at IJCNN2009 The International Joint Conference on Neural Networks – IJCNN2009 – is the premier international conference on neural networks theory, analysis, and a wide range of applications. The conference theme in 2009 has been ‘‘The Century of Brain Computation — Neural Network Alliances with Cognitive Computing and Intelligent Machine Embodiments.’’ Studies into higher cognition and brain functions represent an ultimate frontier of scientific research. It was more than 50 years ago when John Von Neumann introduced his groundbreaking work on self-organization in cellular automata and on the intimate relationship between computers and the brain (VonNeumann, 1958). In the past decades, in particular since the rebirth and explosive development of the field in the mid 80s, neural network approaches have demonstrated their excellent potential to support fundamental theoretical and practical research towards new generations of artificial intelligence and intelligent computing. IJCNN2009 is a truly interdisciplinary event with a broad range of contributions on recent advances in neural networks, including neuroscience and cognitive science, computational intelligence and machine learning, hybrid techniques, nonlinear dynamics and chaos, various soft computing technologies, bioinformatics and biomedicine, and engineering applications. The conference program included 519 papers which appeared in the proceedings
∗
Corresponding author. Tel.: +1 901 678 2497; fax: +1 901 678 2480. E-mail address:
[email protected] (R. Kozma).
0893-6080/$ – see front matter © 2009 Elsevier Ltd. All rights reserved. doi:10.1016/j.neunet.2009.07.008
of IJCNN2009, published by IEEE Press, Piscataway, NJ, USA. The final program of the conference reflects the broad international impact of neural network science with authors from 52 countries and from six continents of the world. Following the traditions, the Neural Networks journal has a Special Issue containing extended versions of selected papers presented at IJCNN. This special issue includes 39 papers from selected areas covering the IJCNN2009 topics. The articles of this Special Issue represent significantly extended and revised versions of the short conference papers published in the Proceedings of IJCNN2009. Each paper has been thoroughly reviewed and consequently revised by the authors, before final acceptance for publication in the Neural Networks journal. The Special Issue starts with papers on neuroscience and cognition, which provide important biological and cognitive inspiration for neural network research. The papers in this section deal with miscroscopic, mesoscopic and macroscopic aspects of neural systems and high-level cognitive functions, such as spatio-temporal orientation, multisensory perception, emotions, and language. The second section includes papers on Machine Learning (ML) techniques. Machine learning is traditionally a key component of artificial intelligence and it provides innovative ideas for learning and adaptation utilized in neural network models and in novel memory designs. Soft computing and hybrid algorithms combine neural, fuzzy, and evolutionary approaches to computational intelligence; recent developments include artificial immune systems and quantum computing. Hybrid methods significantly contribute to the robustness of intelligent technologies and find their applications
490
R. Kozma et al. / Neural Networks 22 (2009) 489–490
in a wide range of practical areas as demonstrated in this Special Issue. Nonlinear systems theory and chaos computing are important emergent methods injecting innovative ideas into the dynamic development of neural networks. Topics of significance in this area include stability of neural dynamic systems, the role of nonconvergent and chaotic trajectories in robust system performance, the constructive role of noise in biologically-inspired neural approaches. Intelligent signal processing is a major field where neural networks have clearly demonstrated their advantages with respect to traditional statistical techniques. Neural networks have been very successful in solving difficult signal processing and pattern recognition problems. The present Special Issue includes excellent examples of innovations in this area, including image processing, time series analysis and prediction. Bioinformatics and biomedical applications are among the most successful areas demonstrating the usefulness of intelligent technologies. With the rapid growth of the health industry, there is a clear demand for intelligent technologies, and our Special Issue shows excellent examples of innovative solutions. Engineering applications of neural networks
include robotics and machine embodiments, adaptive control of complex systems, including power systems, manufacturing, transportation. Cutting-edge research presented in the last chapter demonstrates the latest achievements in the industrial application area. Acknowledgements The Guest Editors of this Special Issue, Robert Kozma, Steven Bressler, Leonid Perlovsky, and Ganesh Kumar Venayagamoorthy appreciate the cooperation of IJCNN organizers and reviewers, who made possible to produce this timely volume. We believe that this comprehensive collection of high-quality papers by leading experts in the field will stimulate and promote progress of neural networks, and will lead to future successes in neural networks research. References Von Neumann, J. (1958). The computer and the brain. Yale University Press.