Lotfi A. Zadeh
Computer Science Division and the Electronics
Research Laboratory
Department of EECS
University of California
Berkeley, USA
e-mail: zadeh@cs.berkeley.edu
Title:
The Roles of Soft Computing and Fuzzy Logic in the Conception, Design and Deployment of Intelligent Systems
Abstract:
Soft Computing (SC) is a consortium of methodologies which provide a foundation for the conception, design and deployment of intelligent systems. The principal members of SC are fuzzy logic (FL), neurocomputing (NC), genetic computing (GC) and probabilistic computing (PC), with PC subsuming evidential reasoning, management of uncertainty and parts of machine learning theory. Within SC, the main contribution of FL is a methodology for dealing with imprecision, approximate reasoning, fuzzy information granulation and computing with words; that of NC is system identification, learning and adaption; that of GC is systematized random research, tuning and optimization; and that of PC is decision analysis and management of uncertainty. The essence of soft computing is that unlike the traditional, hard computing, soft computing is aimed at an accommodation with the pervasive imprecision of the real world. Thus, the guiding principle of soft computing is: Exploit the tolerance for imprecision, uncertainty and partial truth to achieve tractability, robustness, low solution cost and betterrapport with reality.
In the main, FL, NC, GC and PC are complementary rather than competitive. For this reason, it is frequently advantageous to use FL, NC, GC and PC in combination rather than exclusively, leading to so-called "hybrid intelligent systems." At this juncture, the most visible systems of this type are neuro-fuzzy systems. We are also beginning to see fuzzy- genetic, neuro-genetic and neuro-fuzzy-genetic systems. Such systems are likely to become ubiquitous in the not distant future. In coming years, the ubiquity of intelligent systems is certain to have a profound impact on the ways in which man-made systems are conceived, designed, manufactured, employed and interacted with. This is the perspective in which the basic issues relating to soft computing and intelligent systems are addressed in my lecture.
OPENING LECTURE (July 3, 9:00):
Enric Trillas
Department of Artificial Intelligence
Technical University of Madrid
Madrid, Spain
e-mail: etrillas@fi.upm.es
Title:
On a mathematical Model for Indicative Conditionals
Abstract:
This address deals with the concept of µ-T-Conditional in Indicative Mode, is inscribed in what perhaps can be called Theretical Fuzzy Logic, summarizes a part of the previous work did alone or with some colleagues and concerns something controversial from the very beginning in the history of Logic. Of course, many other authors did relevant contributions to this subject in the field of Fuzzy Logic.
Firstly, the concepts of Implication and Conditional in boolean Classical Logic are shortly reconsidered. Secondly, the evolution from Implication Functions to T-Conditionals Generating Functions is reviewed, µ-T- conditionals are characterized and particularized to the crisp case and both Logical T-States and the obtention of Fuzzy Consequences from Fuzzy Premises are considered. Thirdly, after define, particularize to the crisp case and when possible characterize two types of Monotonic Fuzzy Relations, it is shown that the obtained results allow to write as many non-monotonic fuzzy or crisp Conditionals as we like.
INVITED LECTURE (July 4, 9:00):
James C. Bezdek
Computer Science Department
University of West Florida
Pensacola, USA
e-mail: jbezdek@ai.uwf.edu
Title:
A Mixed c-Means Clustering Model
Authors:
Nikhil R. Pal*, Kuhu Pal*, James C. Bezdek
* Machine Intelligence Unit
Indian Statistical Institute
Calcutta, India
Abstract:
We justify the need for computing both membership and typicality values when clustering unlabeled data. Then we propose a new model called fuzzy- possibilistic c.means (FPCM). Unlike the fuzzy and possibilistic c-means (FCM/PCM) models, FPCM simultaneously produces both memberships and possibilities, along with the usual point prototypes or cluster centers for each cluster. We show that FPCM solves the noise sensitivity defect of FCM, and also overcomes the coincident clusters problem of PCM. Then we derive first order necessary conditions for extrema of the FPCM objective function, and use them as the basisfor a standard alternating optimixation approach to finding loical minima. Three numrerical examples are given that compare FCM to FPCM. Our calculations show that FPCM compares favorably to FCM.
INVITED LECTURE (July 5, 9:00):
Henri Prade
Institut de Recherche en Informatique de Toulouse
(IRIT) - CNRS,
Toulouse, France
e-mail: prade@irit.fr
Title:
Constraint Satisfaction and Decision under Uncertainty Based on Qualitative Possibility Theory
Authors:
Didier Dubois and Henri Prade
Institut de Recherche en Informatique de Toulouse
(IRIT) - CNRS
Université Paul Sabatier,
Toulouse, France
Abstract:
This paper surveys the modeling capabilities of qualitative possibility theory in decision analysis for the representation and the aggregation of preferences, for the treatment of uncertainty and for the handling of situations similar to previously encountered ones. "Qualitative" here means that we restrict ourselves to linearly ordered valuation sets (only the ordering of the grades is meaningful) for the assessment of preferences, uncertainty and similarity. Moreover all the evaluations are referred to the same valuation set (commensurability assumption). Such a qualitative structure is poor but not very demanding from an elicitation point of view; however, it is sufficient for giving birth to a valuable set of modeling tools.
|
|
|
FLAT |
