Computational Intelligence: Retrospection and Future

2017 ◽  
Vol 21 (1) ◽  
pp. 9-12
Author(s):  
Witold Pedrycz ◽  
Keyword(s):  
Neural Networks ◽  
Fuzzy Sets ◽  
Computational Intelligence ◽  
Intelligent Systems ◽  
Applied Research ◽  
Evolutionary Optimization ◽  
Retrospective View ◽  
Analysis And Synthesis

This study is aimed at a brief, carefully focused retrospective view at the Computational Intelligence – a paradigm supporting the analysis and synthesis of intelligent systems. We stress the reason behind the emergence of this discipline and identify its main features. We highlight the synergistic aspects of Computational Intelligence arising from an interaction and collaboration of fuzzy sets, neural networks, and evolutionary optimization. Some promising directions of future fundamental and applied research are also identified.

Selected Papers from SCIS & ISIS 2006 – No.1

2007 ◽  
Vol 11 (6) ◽  
pp. 535-535
Author(s):  
Naoyuki Kubota ◽  
Keyword(s):  
Neural Networks ◽  
Soft Computing ◽  
Computational Intelligence ◽  
Intelligent Systems ◽  
Manufacturing Systems ◽  
Current Issue ◽  
Multi Agent Systems ◽  
Special Issue ◽  
Tokyo Institute ◽  
Institute Of Technology

SCIS & ISIS is a biennial international joint conference in the field of soft computing and intelligent systems, including branches of researches from fuzzy systems, neural networks, evolutionary computation, multi-agent systems, artificial intelligence or robotics. SCIS & ISIS 2006 falls on the 3rd International Conference on Soft Computing and Intelligent Systems (SCIS) and the 7th International Symposium on Advanced Intelligent Systems (ISIS) held at Tokyo Institute of Technology, in Tokyo, Japan, on September 20-24, 2006. In this conference, 464 original papers were accepted for presentation and the number of attendees was 526. After preliminary selection and review made by the session chairs and the International Program Committees of SCIS & ISIS 2006, we have selected more than 50 papers to be published in extended form in the Special Issue of the Journal of Advanced Computational Intelligence and Intelligent Informatics. The accepted papers are published as the special issues in Vol.11, No.6, 7, and 8 in 2007. This current issue presents 23 papers and covers most of the topics of the conference including fuzzy theories, self-organizing maps, and the optimization of neural networks. The learning and search methods in computational intelligence and real-world applications to image processing, robotics and manufacturing systems are highlighted in this current issue. I would like to thank all the authors and reviewers for their contribution to make this special issue possible. I am also grateful to Prof. Toshio Fukuda, Nagoya University and Prof. Kaoru Hirota, Tokyo Institute of Technology, Editors-in-chief, for inviting me to serve as Guest Editor of this Journal.

Advanced Computational Intelligence in Control Theory and Applications

1999 ◽  
Vol 3 (2) ◽  
pp. 67-67
Author(s):  
Kazuo Tanaka ◽  
Keyword(s):  
Neural Networks ◽  
Genetic Algorithms ◽  
Fuzzy Logic ◽  
Control Theory ◽  
Soft Computing ◽  
Computational Intelligence ◽  
Intelligent Systems ◽  
Special Issue ◽  
Systems And Control ◽  
And Control

We are witnessing a rapidly growing interest in the field of advanced computational intelligence, a "soft computing" technique. As Prof. Zadeh has stated, soft computing integrates fuzzy logic, neural networks, evolutionary computation, and chaos. Soft computing is the most important technology available for designing intelligent systems and control. The difficulties of fuzzy logic involve acquiring knowledge from experts and finding knowledge for unknown tasks. This is related to design problems in constructing fuzzy rules. Neural networks and genetic algorithms are attracting attention for their potential in raising the efficiency of knowledge finding and acquisition. Combining the technologies of fuzzy logic and neural networks and genetic algorithms, i.e., soft computing techniques will have a tremendous impact on the fields of intelligent systems and control design. To explain the apparent success of soft computing, we must determine the basic capabilities of different soft computing frameworks. Give the great amount of research being done in these fields, this issue addresses fundamental capabilities. This special issue is devoted to advancing computational intelligence in control theory and applications. It contains nine excellent papers dealing with advanced computational intelligence in control theory and applications such as fuzzy control and stability, mobile robot control, neural networks, gymnastic bar action, petroleum plant control, genetic programming, Petri net, and modeling and prediction of complex systems. As editor of this special issue, I believe that the excellent research results it contains provide the basis for leadership in coming research on advanced computational intelligence in control theory and applications.

Selected Papers from ISCIIA'04

2005 ◽  
Vol 9 (6) ◽  
pp. 579-579
Author(s):  
Yaohong Kang ◽  
◽  
Shibin Zhao ◽  
Kazuhiko Kawamoto
Keyword(s):  
Neural Networks ◽  
Computational Intelligence ◽  
Intelligent Systems ◽  
Industrial Applications ◽  
Careful Consideration ◽  
Intelligence Community ◽  
Special Issue ◽  
Research Areas ◽  
Processing Control

This special issue contains 14 papers selected from the first International Symposium on Computational Intelligence and Industrial Applications (ISCIIA'04), held in Haikou, China, December 20-24, 2004. Of the 82 papers from 8 countries submitted to the symposium, 62 were accepted for the proceedings. Based on reviewer's recommendations and guest editor's careful consideration, the authors of 14 papers have revised and extended their symposium papers for this issue. Computational intelligence is the study of the design of "intelligent" systems, which is flexible in changing environments and changing goals with uncertainty, and covers artificial intelligence, neural networks, fuzzy systems, evolutionary computation, and hybrid systems. The objective of this special issue is to reveal current challenges, research topics, and technology solutions critical to algorithms and applications involving computational intelligence. These 14 papers cover such important research areas as neural networks, image processing, control, financial engineering, robotics, and related technologies in computational intelligence. We believe that the information in this issue will become a valuable new resource for the computational intelligence community. We thank the authors and referees whose selfless work and valuable comments have made this special issue possible and improved the overall quality of the papers.

scholarly journals Off-the-shelf deep learning is not enough, and requires parsimony, Bayesianity, and causality

2021 ◽  
Vol 7 (1) ◽  
Author(s):  
Rama K. Vasudevan ◽  
Maxim Ziatdinov ◽  
Lukas Vlcek ◽  
Sergei V. Kalinin
Keyword(s):  
Neural Networks ◽  
Computer Vision ◽  
Deep Learning ◽  
Bayesian Methods ◽  
Deep Neural Networks ◽  
Applied Research ◽  
Modern Science ◽  
Generative Models ◽  
Knowledge Development ◽  
Physical Constraints

AbstractDeep neural networks (‘deep learning’) have emerged as a technology of choice to tackle problems in speech recognition, computer vision, finance, etc. However, adoption of deep learning in physical domains brings substantial challenges stemming from the correlative nature of deep learning methods compared to the causal, hypothesis driven nature of modern science. We argue that the broad adoption of Bayesian methods incorporating prior knowledge, development of solutions with incorporated physical constraints and parsimonious structural descriptors and generative models, and ultimately adoption of causal models, offers a path forward for fundamental and applied research.

Sign in / Sign up

Export Citation Format

Share Document