Upload
patience-ryan
View
216
Download
0
Tags:
Embed Size (px)
Citation preview
04/21/23 1Intelligent Systems and Soft Computing
Lecture 0Lecture 0
What is Soft ComputingWhat is Soft Computing
04/21/23 2Intelligent Systems and Soft Computing
Soft computing differs from conventional (hard) computing in that, unlike hard computing, it is tolerant of imprecision, uncertainty, partial truth, andapproximation. In effect, the role model for soft computing is the human mind.
What is Soft Computing ?(Ref: L.A. Zadeh)
04/21/23 3Intelligent Systems and Soft Computing
•Hard computing, i.e., conventional computing, requires a precisely stated analytical model and often a lot of computation time.
•Many analytical models are valid for ideal cases.
•Real world problems exist in a non-ideal environment.
What is Hard Computing ?
04/21/23 4Intelligent Systems and Soft Computing
•The principal constituents, i.e., tools, techniques, of Soft Computing (SC) are
•Fuzzy Logic (FL), •Artificial Neural Networks (ANN), •Evolutionary Computation (EC), •Swarm Intelligence (i.e. Ant colony optimization and Particle swarm optimization, )•Additionally Some Machine Learning (ML) and Probabilistic Reasoning (PR) areas.
What is Soft Computing ?(continued)
04/21/23 5Intelligent Systems and Soft Computing
• The real world problems are pervasively imprecise and uncertain
• Precision and certainty carry a cost
• Some problems may not even have any precise solutions
Premises of Soft Computing
04/21/23 6Intelligent Systems and Soft Computing
The guiding principle of soft computing is: •Exploit the tolerance for imprecision, uncertainty, partial truth, and approximation to achieve non-conventional solutions, tractability (easily handled, managed, or controlled), robustness and low costs.
Guiding Principle of Soft Computing
04/21/23 7Intelligent Systems and Soft Computing
Hard Computing
•Premises and guiding principles of Hard Computing are
- Precision, Certainty, and Rigor.
• Many contemporary problems do not lend themselves to precise solutions such as
- Recognition problems (handwriting, speech, objects, images, texts)
- Mobile robot coordination, forecasting,
combinatorial problems etc.- Reasoning on natural languages
04/21/23 8Intelligent Systems and Soft Computing
•Soft computing employs ANN, EC, FL etc, in acomplementary rather than a competitive way.• One example of a particularly effectivecombination is "neurofuzzy systems.”• Such systems are becoming increasingly visibleas consumer products ranging from airconditioners and washing machines tophotocopiers, camcorders and many industrialapplications.
Implications of Soft Computing
04/21/23 9Intelligent Systems and Soft Computing
Unique Property of Soft computing
• Learning from experimental data generalization • Soft computing techniques derive their power of generalization from approximating or interpolating to produce outputs from previously unseen inputs by using outputs from previous learned inputs• Generalization is usually done in a high dimensional space.
04/21/23 10Intelligent Systems and Soft Computing
• Handwriting recognition• Automotive systems and manufacturing• Image processing and data compression• Architecture• Decision-support systems• Data Mining• Power systems• Control Systems
Current Applications using Soft Computing
04/21/23 11Intelligent Systems and Soft Computing
• Soft computing is likely to play an especiallyimportant role in science and engineering, buteventually its influence may extend muchfarther.• Soft computing represents a significant paradigm shift in the aims of computing
•A shift which reflects the fact that the human mind, unlike present day computers, possesses a remarkable ability to store and process information which is pervasively imprecise, uncertain and lacking in categoricity.
Future of Soft Computing(Ref: L.A. Zadeh)
AI and Soft Computing: AI and Soft Computing: A Different PerspectiveA Different Perspective
AI: predicate logic and symbol AI: predicate logic and symbol manipulation techniquesmanipulation techniques
Use
r In
terf
ace
Inference Engine
Explanation Facility
Knowledge Acquisition
KB: •Fact•rules
GlobalDatabase
KnowledgeEngineer
HumanExpert
Question
Response
Expert Systems
User
AI and Soft ComputingAI and Soft Computing
ANNLearning and
adaptation
Fuzzy Set TheoryKnowledge representation
ViaFuzzy if-then RULE
Genetic AlgorithmsSystematic
Random Search
AI and Soft ComputingAI and Soft Computing
ANNLearning and
adaptation
Fuzzy Set TheoryKnowledge representation
ViaFuzzy if-then RULE
Genetic AlgorithmsSystematic
Random Search
AISymbolic
Manipulation
AI and Soft ComputingAI and Soft Computing
cat
cut
knowledge
Animal? cat
Neural characterrecognition