Quo Vadis Computational Intelligence?

Wlodzislaw Duch^1,2 and Jacek Mandziuk³
¹School of Computer Engineering, Nanyang Technological University, Singapore,
²Department of Informatics, Nicolaus Copernicus University, Grudziadzka 5, 87-100 Torun, Poland.
³Faculty of Mathematics and Information Science, Warsaw University of Technology, Plac Politechniki 1, 00-661 Warsaw, Poland.

Abstract.

What are the most important problems of computational intelligence?
A sketch of the road to intelligent systems is presented.
Several experts have made interesting comments on the most challenging problems.

Introduction.
The ultimate goals of CI.
A roadmap to creative systems.
- Threshold neurons and perceptrons.
- Increasing complexity of internal PE states
- Increasing complexity of PE interactions
- Beyond the vector space concept
- Flexible incremental approaches
- Evolution of networks
- Transition to symbolic processing
- Up to the brains and the societies of brains
Problems pointed out by experts
General CI problems related to human-like intelligence
General problems within certain CI disciplines
Summmary

Reference: Duch W, Mandziuk J, Quo Vadis Computational Intelligence? In: Machine Intelligence. Quo Vadis? Eds: P. Sinčák, J. Vaščák, K. Hirota. Advances in Fuzzy Systems - Applications and Theory - Vol. 21, World Scientific, 2004, pp. 3-28

Preprint for comments in PDF, 160 KB.

BACK to the publications of W. Duch.
BACK to the on-line publications of the Department of Informatics, NCU.