OPTIMIZATION ALGORITHMS & APPL
OPTIMIZATION ALGORITHMS & APPL DSES 6961
Popular in Course
Popular in Decision Sciences
verified elite notetaker
This 8 page Class Notes was uploaded by Mrs. Rickey Hoppe on Monday October 19, 2015. The Class Notes belongs to DSES 6961 at Rensselaer Polytechnic Institute taught by Staff in Fall. Since its upload, it has received 12 views. For similar materials see /class/224789/dses-6961-rensselaer-polytechnic-institute in Decision Sciences at Rensselaer Polytechnic Institute.
Reviews for OPTIMIZATION ALGORITHMS & APPL
Report this Material
What is Karma?
Karma is the currency of StudySoup.
Date Created: 10/19/15
Computational Intelligence Cl or Soft Computing SC A Brief Overview Piero P Bonissone GE Global Research Schenectady NY 12309 USA Bonissonecrd ge com Outline Typical Requirements of Real World Applications Soft Computing Components and Characteristics Fall 2nn5 rRPl DSES 69m Outline Typical Requirements of Real World Applications Integration of Domain knowledge eld data lmperfectlnformation Uncertainty and lncompleteness Environmental and cognitive changes Soft Computing Components and Characteristics Fall 2nn5 7w DSES 69m Real World Applications Usually ill defined systems difficult to model with large solution spaces Precise models tend to be impractical too expensive or nonexistent Generate approximate solutions by leveraging two types of resources Problem domain knowledge of the process or product and Field data that characterize the system s behavior Domain knowledge combines first principles and empirical knowledge Often incomplete and sometimes erroneous Field data a collection of O measurements representing instances of the system39s behavior Generally incomplete and noisy Soft computing is a flexible framework in which we can find a broad spectrum of design choices to perform the integration of knowledge and data in the construction of approximate models Fall 2nn5 rRPl DSES 69m Outline Typical Requirements of Real World Applications Soft Computing Components and Characteristics Fall 2nn5 7w DSES 69m Problem Solving Technologies In contrast to traditional hard computing soft computing exploits the tolerance for imprecision uncertainty and partial truth to achieve tractability robustness low solutioncost and better rapport with realityquot Zadeh 1991 HARD COMPUTING Precise Models Symbolic Logic Reasoning Traditional AI 3933 Approximate Models Traditiona Functional Numerical APPFOleate Approximatio Modeling an Reasoning and Randomi Search Fall ZDUErRPl DSES Soft Computing Probabilistic Systems Approximate Functional Approximation r Reasoning Randomized Search l Probabilistic Multivalued amp Neural Evolutionary Models Fuzzy Logics Networks Algorithms Bayesian Belief Nets Dempster Shafer Example BBN used for Generators Fault Diagnosis Soft Computing Hybrid Probabilistic Systems Approximate Reasoning Probabilistic Multivalued amp Neural Evolutionary Models Fuzzy Logics Networks Algorithms Belief Nets Dempster Shafer HYBRID PROBA 39 Belief of y Evolved Fuzzy Influence BBN Events Diagrams Probability of Fuzzy Events Soft Computing FL Systems Approximate Functional Approximation Reasoning Randomized Search Probabilistic Multivalued amp Neural Evolutionary Models Fuzzy Logics Networks Algorithms r Fuzzy Multivalued Systems Algebras Fuzzy Logic Controllers l 7 7055 395 N 5 Input Bl r z Help 1 Close 1 H Example Fuzzy Logic Controller I Soft Computing Hybrid FL Systems Approximate Functional Approximation Randomized Search Reasoning Evolutionary Algorithms Neu ral Networks in FS A a ll P39r39eiliciidrii Classi cation Probabilistic Multivalued amp Models Fuzzy Logics Fuzzy Multivalued Systems Algebras Fuzzy Logic Controllers Home Y 7 HYBRID FL SYSTE V NN NN modified by F3 FLC Tuned by FLC Generated Fuzzy Neural Neura39 Fuzzy and Tuned by EA Systems Systems 39C39on39trol z Emblem Soft Computing NN Systems Reasoning Probabilistic Multivalued amp Models Fuzzy Logics Functional Approximation Randomized Search Evolutionary Algorithms Neural Networks Example of Feedforward NN Soft Computing ybrid NN Systems Functional Approximation Randomized Search Evolutionary Algorithms Neural Networks ecurrent NN J i7 NN topology ampIor weights generated by EAs NN parameters learning rate 11 momentum a Soft Computirig EA Systems Approximate Functional Approximation Reasoning Randomized Search Probabilistic Multivalued amp Neural Evolutionary Models Fuzzy Logics Networks Algorithms Evolution Genetic Strategies Algorithms r Evolutionary Genetic mmmn Pro rams Pror HIM mum nrrrrm nrrrrm Example of Binary Encoded GA Soft Computinglebrid EA System Functional Approximation Randomized Search Probabilistic Multivalued amp Neural Evolutionary Models Fuzzy Logics Networks Algorithms Evolution Genetic V V Strategies Algorithms A J P39 bem he EA parameters N Pen Pmu ontrolled by FL Evolutionary x Genetic Prorams EAbased search EA parameters intertwined with Pop size select controlled by EA hillclimbing Notes We will start with an introduction on Fuzzy Systems Sept 1 an introduction on and Evolutionary Algorithms Sept 8 Then we will cover Fuzzy Systems Theories selected applications and case studies Sept 22 Oct 20 Hybrid Fuzzy Systems NN FS or EA FS Oct 27 Nov 10 Evolutionary MultiObjective OptimizationDecision Nov 17Dec 1 Other selected areas of Soft Computing using case studies Dec 8 Fall 2nn5 7w DSES 69m