SlideShare ist ein Scribd-Unternehmen logo
1 von 24
Downloaden Sie, um offline zu lesen
Introduction to Machine
       Learning
                  Lecture 19
       Genetic Fuzzy Systems

                 Albert Orriols i Puig
             http://www.albertorriols.net
             htt //       lb t i l      t
                aorriols@salle.url.edu

      Artificial Intelligence – Machine Learning
                        g                      g
          Enginyeria i Arquitectura La Salle
                 Universitat Ramon Llull
Recap of Lectures 5-18
Supervised learning
  p               g
        Data classification
                Labeled data
                Build a model that
                covers all the space



Unsupervised
Uns per ised learning
        Clustering
                Unlabeled data
                Group similar objects

        Association rule analysis
                Unlabeled data
                Get the most frequent/important associations
                                                               Slide 2
Artificial Intelligence                    Machine Learning
Today’s Agenda


        Fuzzy Logics
        Fuzzy Systems
        Genetic Fuzzy Systems




                                                  Slide 3
Artificial Intelligence        Machine Learning
Fuzzy Logics
        Looking up in the dictionary…
              gp                   y
                Fuzzy = “not clear, distinct, or precise; blurred”
        The
        Th world is imprecise, not clear, blurred…
               ld i i       i    tl       bl    d
        The world is fuzzy!


        Definition of fuzzy logics
                          yg
                A form of knowledge representation suitable for notions that
                cannot be defined precisely, but which depend upon their
                                  p       y,             p      p
                contexts


        Let’s go from true and false (traditional logics) to
        something more powerful

                                                                           Slide 4
Artificial Intelligence                 Machine Learning
Fuzzy Logics
        Traditional logic representation
                      g     p




                           Slow                      Fast



        Logic rep
                Slow      speed = 0
                Fast      speed = 1




                                                            Slide 5
Artificial Intelligence               Machine Learning
Fuzzy Logics
        How fast is fast?
                Definition of slow and fast depend on the eyes of the beholder
                Natural language contains many subjective t
                N t ll              ti           bj ti terms


        How can I deal with this?
        H         d l ith thi ?




                                                          Fast     Very fast
         Very slow             Slow

                These four are linguistic terms
                St ,
                Still, I need to de e t e se a t cs o eac
                          eed define the semantics of each
                linguistic term!
                                                                           Slide 6
Artificial Intelligence                Machine Learning
Fuzzy Logics
        Classical view
                Define intervals:
                          very slow [0 – 0.25]
                          slow [0.25 – 0.5]
                          fast [0.5 – 0.75]
                          very fast [0.75 – 1]

        Fuzzy logics view
            yg
                Consider the degree with which each observation belongs to each
                linguistic term
                Define a membership function




                                                                              Slide 7
Artificial Intelligence                          Machine Learning
Fuzzy Logics
        Member ship functions
                Semantics of the system




                                                      Fast      Very fast
                          Very slow   Slow




                             0        0.25          0.50          0.75      1



                                                                                Slide 8
Artificial Intelligence                      Machine Learning
Fuzzy Logics
        Many different membership functions. Some of them are
           y                    p




                                                 1




                                                          c
                                                     ab       d


                                                                  Slide 9
Artificial Intelligence       Machine Learning
Fuzzy Systems
        Fuzzy systems
            yy
                are fundamental methodologies to represent and process
                   gu s c o a o
                linguistic information
                use fuzzy logic to either represent the knowledge or model the
                interactions a d relationships a o g the sys e variables in
                   e ac o s and e a o s ps among e system a ab es
                environments where there is uncertainty and imprecision.
                          E.g. of knowledge representation:
                              If john is tall and fast then strong

        Genetic fuzzy systems
                    yy
                The use of genetic/evolutionary algorithms (GAs) to design
                fuzzy systems
                    yy




                                                                             Slide 10
Artificial Intelligence                          Machine Learning
GFS




                                             Slide 11
Artificial Intelligence   Machine Learning
GFS
        Two key elements:
              y
                Fuzzy system
                          In our case, we will focus on rule-based systems
                                 case
                Genetic algorithm


        Fuzzy system
            yy




                                                                             Slide 12
Artificial Intelligence                      Machine Learning
Fuzzy Rule-Based Systems
        Rule base
                If size is small and weight is small then quality is bad
                If size is small and weight i l
                    ii        ll d     i ht is large th quality i medium
                                                     then  lit is   di
                If size is large and weight is small then quality is medium
                If size is large and weight is large then quality is good
        Data base




                                                                              Slide 13
Artificial Intelligence                Machine Learning
Fuzzy Rule-Based Systems
        Operation of the inference system




                                                Centre of
                                                 gravity




                                                            Slide 14
Artificial Intelligence      Machine Learning
Fuzzy Rule-Based Systems
        Great, I know how to infer… But who gives me
             ,                              g
                The rules
                The i f
                Th information of the data base (the semantics)
                          ti    f th d t b      (th       ti )
                The inference engine
                          Inference system
                          Defuzzification methods


        Use a genetic algorithm for this task




                                                                  Slide 15
Artificial Intelligence                      Machine Learning
Recall GAs?

                                                              Population

                                                          Individual 1   Fit. 1
                                                          Individual 2   Fit. 2
                                                                                             Individual i
                          Population                           ...        ...
                                                          Individual n   Fit. n              Individual j
                          Individual 1
    Initialization
                          Individual 2                                                       Individual 1
                               ...
                                                                                             Individual n
                          Individual n


                                                                             Individual i’
                                         Individual i’’
                                                           Mutation          Individual j’
                                         Individual j’’
                                                                            Individual
                                                                            I di id l 1’
                                         Individual 1’’
                                                                            Individual n’
                                         Individual n’’



        Selection + Mutation: Continuous improvement and local search
        Selection + Recombination: Innovation


                                                                                                            Slide 16
Artificial Intelligence                         Machine Learning
Where Do we Use the GA?
        Taxonomy of GFS (
               y        (Herrera, 2008)
                                ,     )




                                                Slide 17
Artificial Intelligence      Machine Learning
Where Do we Use the GA?
        Taxonomy of GFS (
               y        (Herrera, 2008)
                                ,     )




                                                Slide 18
Artificial Intelligence      Machine Learning
Topics
        We are going to see
               g   g
                 Genetic tuning
        1.

                 Genetic rule learning
                 G   ti    ll      i
        2.

                 Genetic rule selection
        3.

                 Genetic DB learning
        4.

                 S u ta eous genetic ea
                 Simultaneous ge et c learning o KB co po e ts
                                             g of   components
        5
        5.

                 Genetic learning of KB components and inference engine
        6.
                 pa a ete s
                 parameters


                1st seen i thi l t
                         in this lecture. 2nd-5th seen i next l t
                                              5        in   t lecture
                Information based on the paper Herrera (2009) and the
                corresponding presentation
                          di         t ti

                                                                          Slide 19
Artificial Intelligence                   Machine Learning
1. Genetic Tuning
        Typically membership functions
         yp     y          p
                are defined by domain experts
                are j t selected f
                    just l t d from general f
                                          l forms: triangles, t
                                                   ti    l    trapezoids,
                                                                     id
                Gaussian…
        But,
        B t could we have better membership functions?
               ld    h    b tt      b   hi f    ti   ?
                Let a GA tune the membership functions




                Also, tune the inference parameters


                                                                            Slide 20
Artificial Intelligence               Machine Learning
1. Genetic Tuning
        How do we
        apply the GA?




                So, we are modifying
                the partitions of the
                feature space


                                                           Slide 21
Artificial Intelligence                 Machine Learning
1. Genetic Tuning
        An example: Tuning triangular membership functions
               p         g      g              p
                Each chromosome encodes a different DB definition
                          2 vars x 3 ling. labels = 6 mem. functions
                                        g
                          Triangles   3 real values to code them
                          Chromosome length = 18 genes




                Note that the RB remains unchanged!
                                                                       Slide 22
Artificial Intelligence                         Machine Learning
Next Class

        Next l
        N t class
                 Genetic rule learning
        1.

                 Genetic rule selection
        2.

                 Genetic DB learning
        3.

                 Simultaneous genetic learning of KB components
        4.

                 Genetic learning of KB components and inference engine
                 G    ti l    i    f            t    di f           i
        5.
                 parameters


        Applications




                                                                          Slide 23
Artificial Intelligence                   Machine Learning
Introduction to Machine
       Learning
                  Lecture 19
       Genetic Fuzzy Systems

                 Albert Orriols i Puig
             http://www.albertorriols.net
             htt //       lb t i l      t
                aorriols@salle.url.edu

      Artificial Intelligence – Machine Learning
                        g                      g
          Enginyeria i Arquitectura La Salle
                 Universitat Ramon Llull

Weitere ähnliche Inhalte

Was ist angesagt?

New Challenges in Learning Classifier Systems: Mining Rarities and Evolving F...
New Challenges in Learning Classifier Systems: Mining Rarities and Evolving F...New Challenges in Learning Classifier Systems: Mining Rarities and Evolving F...
New Challenges in Learning Classifier Systems: Mining Rarities and Evolving F...Albert Orriols-Puig
 
CCIA'2008: Can Evolution Strategies Improve Learning Guidance in XCS? Design ...
CCIA'2008: Can Evolution Strategies Improve Learning Guidance in XCS? Design ...CCIA'2008: Can Evolution Strategies Improve Learning Guidance in XCS? Design ...
CCIA'2008: Can Evolution Strategies Improve Learning Guidance in XCS? Design ...Albert Orriols-Puig
 
HIS'2008: Genetic-based Synthetic Data Sets for the Analysis of Classifiers B...
HIS'2008: Genetic-based Synthetic Data Sets for the Analysis of Classifiers B...HIS'2008: Genetic-based Synthetic Data Sets for the Analysis of Classifiers B...
HIS'2008: Genetic-based Synthetic Data Sets for the Analysis of Classifiers B...Albert Orriols-Puig
 
IWLCS'2008: First Approach toward Online Evolution of Association Rules wit...
IWLCS'2008: First Approach toward Online Evolution of Association Rules wit...IWLCS'2008: First Approach toward Online Evolution of Association Rules wit...
IWLCS'2008: First Approach toward Online Evolution of Association Rules wit...Albert Orriols-Puig
 
CCIA'2008: On the dimensions of data complexity through synthetic data sets
CCIA'2008: On the dimensions of data complexity through synthetic data setsCCIA'2008: On the dimensions of data complexity through synthetic data sets
CCIA'2008: On the dimensions of data complexity through synthetic data setsAlbert Orriols-Puig
 
GECCO'2007: Modeling XCS in Class Imbalances: Population Size and Parameter S...
GECCO'2007: Modeling XCS in Class Imbalances: Population Size and Parameter S...GECCO'2007: Modeling XCS in Class Imbalances: Population Size and Parameter S...
GECCO'2007: Modeling XCS in Class Imbalances: Population Size and Parameter S...Albert Orriols-Puig
 
HIS'2008: New Crossover Operator for Evolutionary Rule Discovery in XCS
HIS'2008: New Crossover Operator for Evolutionary Rule Discovery in XCSHIS'2008: New Crossover Operator for Evolutionary Rule Discovery in XCS
HIS'2008: New Crossover Operator for Evolutionary Rule Discovery in XCSAlbert Orriols-Puig
 
101 Webinar - Artificial Intelligence, Deep Learning and Geospatial
101 Webinar - Artificial Intelligence, Deep Learning and Geospatial101 Webinar - Artificial Intelligence, Deep Learning and Geospatial
101 Webinar - Artificial Intelligence, Deep Learning and GeospatialGeospatial Media & Communications
 
Intelligent Tutoring Systems: The DynaLearn Approach
Intelligent Tutoring Systems: The DynaLearn ApproachIntelligent Tutoring Systems: The DynaLearn Approach
Intelligent Tutoring Systems: The DynaLearn ApproachWouter Beek
 
Machine Learning
Machine LearningMachine Learning
Machine Learningbutest
 

Was ist angesagt? (20)

Lecture6 - C4.5
Lecture6 - C4.5Lecture6 - C4.5
Lecture6 - C4.5
 
Lecture23
Lecture23Lecture23
Lecture23
 
Lecture4 - Machine Learning
Lecture4 - Machine LearningLecture4 - Machine Learning
Lecture4 - Machine Learning
 
Lecture24
Lecture24Lecture24
Lecture24
 
Lecture18
Lecture18Lecture18
Lecture18
 
New Challenges in Learning Classifier Systems: Mining Rarities and Evolving F...
New Challenges in Learning Classifier Systems: Mining Rarities and Evolving F...New Challenges in Learning Classifier Systems: Mining Rarities and Evolving F...
New Challenges in Learning Classifier Systems: Mining Rarities and Evolving F...
 
Lecture8 - From CBR to IBk
Lecture8 - From CBR to IBkLecture8 - From CBR to IBk
Lecture8 - From CBR to IBk
 
Lecture11 - neural networks
Lecture11 - neural networksLecture11 - neural networks
Lecture11 - neural networks
 
Lecture5 - C4.5
Lecture5 - C4.5Lecture5 - C4.5
Lecture5 - C4.5
 
CCIA'2008: Can Evolution Strategies Improve Learning Guidance in XCS? Design ...
CCIA'2008: Can Evolution Strategies Improve Learning Guidance in XCS? Design ...CCIA'2008: Can Evolution Strategies Improve Learning Guidance in XCS? Design ...
CCIA'2008: Can Evolution Strategies Improve Learning Guidance in XCS? Design ...
 
HIS'2008: Genetic-based Synthetic Data Sets for the Analysis of Classifiers B...
HIS'2008: Genetic-based Synthetic Data Sets for the Analysis of Classifiers B...HIS'2008: Genetic-based Synthetic Data Sets for the Analysis of Classifiers B...
HIS'2008: Genetic-based Synthetic Data Sets for the Analysis of Classifiers B...
 
IWLCS'2008: First Approach toward Online Evolution of Association Rules wit...
IWLCS'2008: First Approach toward Online Evolution of Association Rules wit...IWLCS'2008: First Approach toward Online Evolution of Association Rules wit...
IWLCS'2008: First Approach toward Online Evolution of Association Rules wit...
 
CCIA'2008: On the dimensions of data complexity through synthetic data sets
CCIA'2008: On the dimensions of data complexity through synthetic data setsCCIA'2008: On the dimensions of data complexity through synthetic data sets
CCIA'2008: On the dimensions of data complexity through synthetic data sets
 
GECCO'2007: Modeling XCS in Class Imbalances: Population Size and Parameter S...
GECCO'2007: Modeling XCS in Class Imbalances: Population Size and Parameter S...GECCO'2007: Modeling XCS in Class Imbalances: Population Size and Parameter S...
GECCO'2007: Modeling XCS in Class Imbalances: Population Size and Parameter S...
 
Lecture12 - SVM
Lecture12 - SVMLecture12 - SVM
Lecture12 - SVM
 
HIS'2008: New Crossover Operator for Evolutionary Rule Discovery in XCS
HIS'2008: New Crossover Operator for Evolutionary Rule Discovery in XCSHIS'2008: New Crossover Operator for Evolutionary Rule Discovery in XCS
HIS'2008: New Crossover Operator for Evolutionary Rule Discovery in XCS
 
101 Webinar - Artificial Intelligence, Deep Learning and Geospatial
101 Webinar - Artificial Intelligence, Deep Learning and Geospatial101 Webinar - Artificial Intelligence, Deep Learning and Geospatial
101 Webinar - Artificial Intelligence, Deep Learning and Geospatial
 
Abhinav
AbhinavAbhinav
Abhinav
 
Intelligent Tutoring Systems: The DynaLearn Approach
Intelligent Tutoring Systems: The DynaLearn ApproachIntelligent Tutoring Systems: The DynaLearn Approach
Intelligent Tutoring Systems: The DynaLearn Approach
 
Machine Learning
Machine LearningMachine Learning
Machine Learning
 

Andere mochten auch

Lecture1 AI1 Introduction to artificial intelligence
Lecture1 AI1 Introduction to artificial intelligenceLecture1 AI1 Introduction to artificial intelligence
Lecture1 AI1 Introduction to artificial intelligenceAlbert Orriols-Puig
 
Lecture14 - Advanced topics in association rules
Lecture14 - Advanced topics in association rulesLecture14 - Advanced topics in association rules
Lecture14 - Advanced topics in association rulesAlbert Orriols-Puig
 
Lecture16 - Advances topics on association rules PART III
Lecture16 - Advances topics on association rules PART IIILecture16 - Advances topics on association rules PART III
Lecture16 - Advances topics on association rules PART IIIAlbert Orriols-Puig
 
HAIS09-BeyondHomemadeArtificialDatasets
HAIS09-BeyondHomemadeArtificialDatasetsHAIS09-BeyondHomemadeArtificialDatasets
HAIS09-BeyondHomemadeArtificialDatasetsAlbert Orriols-Puig
 
Artificial Intelligence
Artificial IntelligenceArtificial Intelligence
Artificial Intelligenceu053675
 

Andere mochten auch (10)

Lecture22
Lecture22Lecture22
Lecture22
 
Lecture1 AI1 Introduction to artificial intelligence
Lecture1 AI1 Introduction to artificial intelligenceLecture1 AI1 Introduction to artificial intelligence
Lecture1 AI1 Introduction to artificial intelligence
 
Lecture21
Lecture21Lecture21
Lecture21
 
Lecture14 - Advanced topics in association rules
Lecture14 - Advanced topics in association rulesLecture14 - Advanced topics in association rules
Lecture14 - Advanced topics in association rules
 
Lecture16 - Advances topics on association rules PART III
Lecture16 - Advances topics on association rules PART IIILecture16 - Advances topics on association rules PART III
Lecture16 - Advances topics on association rules PART III
 
HAIS09-BeyondHomemadeArtificialDatasets
HAIS09-BeyondHomemadeArtificialDatasetsHAIS09-BeyondHomemadeArtificialDatasets
HAIS09-BeyondHomemadeArtificialDatasets
 
Lecture10 - Naïve Bayes
Lecture10 - Naïve BayesLecture10 - Naïve Bayes
Lecture10 - Naïve Bayes
 
Lecture13 - Association Rules
Lecture13 - Association RulesLecture13 - Association Rules
Lecture13 - Association Rules
 
Decision tree Using c4.5 Algorithm
Decision tree Using c4.5 AlgorithmDecision tree Using c4.5 Algorithm
Decision tree Using c4.5 Algorithm
 
Artificial Intelligence
Artificial IntelligenceArtificial Intelligence
Artificial Intelligence
 

Ähnlich wie Lecture19

Artificial Intelligence
Artificial IntelligenceArtificial Intelligence
Artificial Intelligencearpitnot4u
 
Python AI tutorial
Python AI tutorialPython AI tutorial
Python AI tutorialgrinu
 
Fuzzy Sets Introduction With Example
Fuzzy Sets Introduction With ExampleFuzzy Sets Introduction With Example
Fuzzy Sets Introduction With Exampleraisnasir
 
[DSC Europe 23] Danijela Horak - The Innovator’s Dilemma: to Build or Not to ...
[DSC Europe 23] Danijela Horak - The Innovator’s Dilemma: to Build or Not to ...[DSC Europe 23] Danijela Horak - The Innovator’s Dilemma: to Build or Not to ...
[DSC Europe 23] Danijela Horak - The Innovator’s Dilemma: to Build or Not to ...DataScienceConferenc1
 
Yann le cun
Yann le cunYann le cun
Yann le cunYandex
 
Foundations of Intelligence Agents
Foundations of Intelligence AgentsFoundations of Intelligence Agents
Foundations of Intelligence Agentsmahutte
 
Artificial intelligence quiz ai and fuzzy logic priti sajja
Artificial intelligence quiz ai and fuzzy logic priti sajjaArtificial intelligence quiz ai and fuzzy logic priti sajja
Artificial intelligence quiz ai and fuzzy logic priti sajjaPriti Srinivas Sajja
 
Gerald.mulenburg
Gerald.mulenburgGerald.mulenburg
Gerald.mulenburgNASAPMC
 
Artificial Intelligence
Artificial IntelligenceArtificial Intelligence
Artificial Intelligenceiarthur
 
AI - history and recent breakthroughs
AI - history and recent breakthroughs AI - history and recent breakthroughs
AI - history and recent breakthroughs Armando Vieira
 
NNFL 16- Guru Nanak Dev Engineering College
NNFL   16- Guru Nanak Dev Engineering CollegeNNFL   16- Guru Nanak Dev Engineering College
NNFL 16- Guru Nanak Dev Engineering CollegeMR. VIKRAM SNEHI
 

Ähnlich wie Lecture19 (20)

Artificial Intelligence
Artificial IntelligenceArtificial Intelligence
Artificial Intelligence
 
Python AI tutorial
Python AI tutorialPython AI tutorial
Python AI tutorial
 
(Ch#1) artificial intelligence
(Ch#1) artificial intelligence(Ch#1) artificial intelligence
(Ch#1) artificial intelligence
 
Fuzzy Sets Introduction With Example
Fuzzy Sets Introduction With ExampleFuzzy Sets Introduction With Example
Fuzzy Sets Introduction With Example
 
Kiran computer
Kiran computerKiran computer
Kiran computer
 
[DSC Europe 23] Danijela Horak - The Innovator’s Dilemma: to Build or Not to ...
[DSC Europe 23] Danijela Horak - The Innovator’s Dilemma: to Build or Not to ...[DSC Europe 23] Danijela Horak - The Innovator’s Dilemma: to Build or Not to ...
[DSC Europe 23] Danijela Horak - The Innovator’s Dilemma: to Build or Not to ...
 
Ai lect 1
Ai lect 1Ai lect 1
Ai lect 1
 
lecture1423723637.pdf
lecture1423723637.pdflecture1423723637.pdf
lecture1423723637.pdf
 
Yann le cun
Yann le cunYann le cun
Yann le cun
 
Foundations of Intelligence Agents
Foundations of Intelligence AgentsFoundations of Intelligence Agents
Foundations of Intelligence Agents
 
Pc Seminar Jordi
Pc Seminar JordiPc Seminar Jordi
Pc Seminar Jordi
 
Introduction to soft computing
 Introduction to soft computing Introduction to soft computing
Introduction to soft computing
 
Artificial intelligence quiz ai and fuzzy logic priti sajja
Artificial intelligence quiz ai and fuzzy logic priti sajjaArtificial intelligence quiz ai and fuzzy logic priti sajja
Artificial intelligence quiz ai and fuzzy logic priti sajja
 
Gerald.mulenburg
Gerald.mulenburgGerald.mulenburg
Gerald.mulenburg
 
Basics of Soft Computing
Basics of Soft  Computing Basics of Soft  Computing
Basics of Soft Computing
 
Fuzzy logic
Fuzzy logicFuzzy logic
Fuzzy logic
 
Artificial Intelligence
Artificial IntelligenceArtificial Intelligence
Artificial Intelligence
 
AI - history and recent breakthroughs
AI - history and recent breakthroughs AI - history and recent breakthroughs
AI - history and recent breakthroughs
 
NNFL 16- Guru Nanak Dev Engineering College
NNFL   16- Guru Nanak Dev Engineering CollegeNNFL   16- Guru Nanak Dev Engineering College
NNFL 16- Guru Nanak Dev Engineering College
 
Adarsh gupta ppt
Adarsh gupta pptAdarsh gupta ppt
Adarsh gupta ppt
 

Kürzlich hochgeladen

Sulphonamides, mechanisms and their uses
Sulphonamides, mechanisms and their usesSulphonamides, mechanisms and their uses
Sulphonamides, mechanisms and their usesVijayaLaxmi84
 
4.9.24 Social Capital and Social Exclusion.pptx
4.9.24 Social Capital and Social Exclusion.pptx4.9.24 Social Capital and Social Exclusion.pptx
4.9.24 Social Capital and Social Exclusion.pptxmary850239
 
Narcotic and Non Narcotic Analgesic..pdf
Narcotic and Non Narcotic Analgesic..pdfNarcotic and Non Narcotic Analgesic..pdf
Narcotic and Non Narcotic Analgesic..pdfPrerana Jadhav
 
How to Uninstall a Module in Odoo 17 Using Command Line
How to Uninstall a Module in Odoo 17 Using Command LineHow to Uninstall a Module in Odoo 17 Using Command Line
How to Uninstall a Module in Odoo 17 Using Command LineCeline George
 
An Overview of the Calendar App in Odoo 17 ERP
An Overview of the Calendar App in Odoo 17 ERPAn Overview of the Calendar App in Odoo 17 ERP
An Overview of the Calendar App in Odoo 17 ERPCeline George
 
Team Lead Succeed – Helping you and your team achieve high-performance teamwo...
Team Lead Succeed – Helping you and your team achieve high-performance teamwo...Team Lead Succeed – Helping you and your team achieve high-performance teamwo...
Team Lead Succeed – Helping you and your team achieve high-performance teamwo...Association for Project Management
 
Decoding the Tweet _ Practical Criticism in the Age of Hashtag.pptx
Decoding the Tweet _ Practical Criticism in the Age of Hashtag.pptxDecoding the Tweet _ Practical Criticism in the Age of Hashtag.pptx
Decoding the Tweet _ Practical Criticism in the Age of Hashtag.pptxDhatriParmar
 
BÀI TẬP BỔ TRỢ TIẾNG ANH 8 - I-LEARN SMART WORLD - CẢ NĂM - CÓ FILE NGHE (BẢN...
BÀI TẬP BỔ TRỢ TIẾNG ANH 8 - I-LEARN SMART WORLD - CẢ NĂM - CÓ FILE NGHE (BẢN...BÀI TẬP BỔ TRỢ TIẾNG ANH 8 - I-LEARN SMART WORLD - CẢ NĂM - CÓ FILE NGHE (BẢN...
BÀI TẬP BỔ TRỢ TIẾNG ANH 8 - I-LEARN SMART WORLD - CẢ NĂM - CÓ FILE NGHE (BẢN...Nguyen Thanh Tu Collection
 
Blowin' in the Wind of Caste_ Bob Dylan's Song as a Catalyst for Social Justi...
Blowin' in the Wind of Caste_ Bob Dylan's Song as a Catalyst for Social Justi...Blowin' in the Wind of Caste_ Bob Dylan's Song as a Catalyst for Social Justi...
Blowin' in the Wind of Caste_ Bob Dylan's Song as a Catalyst for Social Justi...DhatriParmar
 
MS4 level being good citizen -imperative- (1) (1).pdf
MS4 level   being good citizen -imperative- (1) (1).pdfMS4 level   being good citizen -imperative- (1) (1).pdf
MS4 level being good citizen -imperative- (1) (1).pdfMr Bounab Samir
 
BÀI TẬP BỔ TRỢ TIẾNG ANH 11 THEO ĐƠN VỊ BÀI HỌC - CẢ NĂM - CÓ FILE NGHE (GLOB...
BÀI TẬP BỔ TRỢ TIẾNG ANH 11 THEO ĐƠN VỊ BÀI HỌC - CẢ NĂM - CÓ FILE NGHE (GLOB...BÀI TẬP BỔ TRỢ TIẾNG ANH 11 THEO ĐƠN VỊ BÀI HỌC - CẢ NĂM - CÓ FILE NGHE (GLOB...
BÀI TẬP BỔ TRỢ TIẾNG ANH 11 THEO ĐƠN VỊ BÀI HỌC - CẢ NĂM - CÓ FILE NGHE (GLOB...Nguyen Thanh Tu Collection
 
The role of Geography in climate education: science and active citizenship
The role of Geography in climate education: science and active citizenshipThe role of Geography in climate education: science and active citizenship
The role of Geography in climate education: science and active citizenshipKarl Donert
 
Grade Three -ELLNA-REVIEWER-ENGLISH.pptx
Grade Three -ELLNA-REVIEWER-ENGLISH.pptxGrade Three -ELLNA-REVIEWER-ENGLISH.pptx
Grade Three -ELLNA-REVIEWER-ENGLISH.pptxkarenfajardo43
 
CLASSIFICATION OF ANTI - CANCER DRUGS.pptx
CLASSIFICATION OF ANTI - CANCER DRUGS.pptxCLASSIFICATION OF ANTI - CANCER DRUGS.pptx
CLASSIFICATION OF ANTI - CANCER DRUGS.pptxAnupam32727
 
Healthy Minds, Flourishing Lives: A Philosophical Approach to Mental Health a...
Healthy Minds, Flourishing Lives: A Philosophical Approach to Mental Health a...Healthy Minds, Flourishing Lives: A Philosophical Approach to Mental Health a...
Healthy Minds, Flourishing Lives: A Philosophical Approach to Mental Health a...Osopher
 
Shark introduction Morphology and its behaviour characteristics
Shark introduction Morphology and its behaviour characteristicsShark introduction Morphology and its behaviour characteristics
Shark introduction Morphology and its behaviour characteristicsArubSultan
 
Satirical Depths - A Study of Gabriel Okara's Poem - 'You Laughed and Laughed...
Satirical Depths - A Study of Gabriel Okara's Poem - 'You Laughed and Laughed...Satirical Depths - A Study of Gabriel Okara's Poem - 'You Laughed and Laughed...
Satirical Depths - A Study of Gabriel Okara's Poem - 'You Laughed and Laughed...HetalPathak10
 
Employablity presentation and Future Career Plan.pptx
Employablity presentation and Future Career Plan.pptxEmployablity presentation and Future Career Plan.pptx
Employablity presentation and Future Career Plan.pptxryandux83rd
 
CHUYÊN ĐỀ ÔN THEO CÂU CHO HỌC SINH LỚP 12 ĐỂ ĐẠT ĐIỂM 5+ THI TỐT NGHIỆP THPT ...
CHUYÊN ĐỀ ÔN THEO CÂU CHO HỌC SINH LỚP 12 ĐỂ ĐẠT ĐIỂM 5+ THI TỐT NGHIỆP THPT ...CHUYÊN ĐỀ ÔN THEO CÂU CHO HỌC SINH LỚP 12 ĐỂ ĐẠT ĐIỂM 5+ THI TỐT NGHIỆP THPT ...
CHUYÊN ĐỀ ÔN THEO CÂU CHO HỌC SINH LỚP 12 ĐỂ ĐẠT ĐIỂM 5+ THI TỐT NGHIỆP THPT ...Nguyen Thanh Tu Collection
 
Q-Factor HISPOL Quiz-6th April 2024, Quiz Club NITW
Q-Factor HISPOL Quiz-6th April 2024, Quiz Club NITWQ-Factor HISPOL Quiz-6th April 2024, Quiz Club NITW
Q-Factor HISPOL Quiz-6th April 2024, Quiz Club NITWQuiz Club NITW
 

Kürzlich hochgeladen (20)

Sulphonamides, mechanisms and their uses
Sulphonamides, mechanisms and their usesSulphonamides, mechanisms and their uses
Sulphonamides, mechanisms and their uses
 
4.9.24 Social Capital and Social Exclusion.pptx
4.9.24 Social Capital and Social Exclusion.pptx4.9.24 Social Capital and Social Exclusion.pptx
4.9.24 Social Capital and Social Exclusion.pptx
 
Narcotic and Non Narcotic Analgesic..pdf
Narcotic and Non Narcotic Analgesic..pdfNarcotic and Non Narcotic Analgesic..pdf
Narcotic and Non Narcotic Analgesic..pdf
 
How to Uninstall a Module in Odoo 17 Using Command Line
How to Uninstall a Module in Odoo 17 Using Command LineHow to Uninstall a Module in Odoo 17 Using Command Line
How to Uninstall a Module in Odoo 17 Using Command Line
 
An Overview of the Calendar App in Odoo 17 ERP
An Overview of the Calendar App in Odoo 17 ERPAn Overview of the Calendar App in Odoo 17 ERP
An Overview of the Calendar App in Odoo 17 ERP
 
Team Lead Succeed – Helping you and your team achieve high-performance teamwo...
Team Lead Succeed – Helping you and your team achieve high-performance teamwo...Team Lead Succeed – Helping you and your team achieve high-performance teamwo...
Team Lead Succeed – Helping you and your team achieve high-performance teamwo...
 
Decoding the Tweet _ Practical Criticism in the Age of Hashtag.pptx
Decoding the Tweet _ Practical Criticism in the Age of Hashtag.pptxDecoding the Tweet _ Practical Criticism in the Age of Hashtag.pptx
Decoding the Tweet _ Practical Criticism in the Age of Hashtag.pptx
 
BÀI TẬP BỔ TRỢ TIẾNG ANH 8 - I-LEARN SMART WORLD - CẢ NĂM - CÓ FILE NGHE (BẢN...
BÀI TẬP BỔ TRỢ TIẾNG ANH 8 - I-LEARN SMART WORLD - CẢ NĂM - CÓ FILE NGHE (BẢN...BÀI TẬP BỔ TRỢ TIẾNG ANH 8 - I-LEARN SMART WORLD - CẢ NĂM - CÓ FILE NGHE (BẢN...
BÀI TẬP BỔ TRỢ TIẾNG ANH 8 - I-LEARN SMART WORLD - CẢ NĂM - CÓ FILE NGHE (BẢN...
 
Blowin' in the Wind of Caste_ Bob Dylan's Song as a Catalyst for Social Justi...
Blowin' in the Wind of Caste_ Bob Dylan's Song as a Catalyst for Social Justi...Blowin' in the Wind of Caste_ Bob Dylan's Song as a Catalyst for Social Justi...
Blowin' in the Wind of Caste_ Bob Dylan's Song as a Catalyst for Social Justi...
 
MS4 level being good citizen -imperative- (1) (1).pdf
MS4 level   being good citizen -imperative- (1) (1).pdfMS4 level   being good citizen -imperative- (1) (1).pdf
MS4 level being good citizen -imperative- (1) (1).pdf
 
BÀI TẬP BỔ TRỢ TIẾNG ANH 11 THEO ĐƠN VỊ BÀI HỌC - CẢ NĂM - CÓ FILE NGHE (GLOB...
BÀI TẬP BỔ TRỢ TIẾNG ANH 11 THEO ĐƠN VỊ BÀI HỌC - CẢ NĂM - CÓ FILE NGHE (GLOB...BÀI TẬP BỔ TRỢ TIẾNG ANH 11 THEO ĐƠN VỊ BÀI HỌC - CẢ NĂM - CÓ FILE NGHE (GLOB...
BÀI TẬP BỔ TRỢ TIẾNG ANH 11 THEO ĐƠN VỊ BÀI HỌC - CẢ NĂM - CÓ FILE NGHE (GLOB...
 
The role of Geography in climate education: science and active citizenship
The role of Geography in climate education: science and active citizenshipThe role of Geography in climate education: science and active citizenship
The role of Geography in climate education: science and active citizenship
 
Grade Three -ELLNA-REVIEWER-ENGLISH.pptx
Grade Three -ELLNA-REVIEWER-ENGLISH.pptxGrade Three -ELLNA-REVIEWER-ENGLISH.pptx
Grade Three -ELLNA-REVIEWER-ENGLISH.pptx
 
CLASSIFICATION OF ANTI - CANCER DRUGS.pptx
CLASSIFICATION OF ANTI - CANCER DRUGS.pptxCLASSIFICATION OF ANTI - CANCER DRUGS.pptx
CLASSIFICATION OF ANTI - CANCER DRUGS.pptx
 
Healthy Minds, Flourishing Lives: A Philosophical Approach to Mental Health a...
Healthy Minds, Flourishing Lives: A Philosophical Approach to Mental Health a...Healthy Minds, Flourishing Lives: A Philosophical Approach to Mental Health a...
Healthy Minds, Flourishing Lives: A Philosophical Approach to Mental Health a...
 
Shark introduction Morphology and its behaviour characteristics
Shark introduction Morphology and its behaviour characteristicsShark introduction Morphology and its behaviour characteristics
Shark introduction Morphology and its behaviour characteristics
 
Satirical Depths - A Study of Gabriel Okara's Poem - 'You Laughed and Laughed...
Satirical Depths - A Study of Gabriel Okara's Poem - 'You Laughed and Laughed...Satirical Depths - A Study of Gabriel Okara's Poem - 'You Laughed and Laughed...
Satirical Depths - A Study of Gabriel Okara's Poem - 'You Laughed and Laughed...
 
Employablity presentation and Future Career Plan.pptx
Employablity presentation and Future Career Plan.pptxEmployablity presentation and Future Career Plan.pptx
Employablity presentation and Future Career Plan.pptx
 
CHUYÊN ĐỀ ÔN THEO CÂU CHO HỌC SINH LỚP 12 ĐỂ ĐẠT ĐIỂM 5+ THI TỐT NGHIỆP THPT ...
CHUYÊN ĐỀ ÔN THEO CÂU CHO HỌC SINH LỚP 12 ĐỂ ĐẠT ĐIỂM 5+ THI TỐT NGHIỆP THPT ...CHUYÊN ĐỀ ÔN THEO CÂU CHO HỌC SINH LỚP 12 ĐỂ ĐẠT ĐIỂM 5+ THI TỐT NGHIỆP THPT ...
CHUYÊN ĐỀ ÔN THEO CÂU CHO HỌC SINH LỚP 12 ĐỂ ĐẠT ĐIỂM 5+ THI TỐT NGHIỆP THPT ...
 
Q-Factor HISPOL Quiz-6th April 2024, Quiz Club NITW
Q-Factor HISPOL Quiz-6th April 2024, Quiz Club NITWQ-Factor HISPOL Quiz-6th April 2024, Quiz Club NITW
Q-Factor HISPOL Quiz-6th April 2024, Quiz Club NITW
 

Lecture19

  • 1. Introduction to Machine Learning Lecture 19 Genetic Fuzzy Systems Albert Orriols i Puig http://www.albertorriols.net htt // lb t i l t aorriols@salle.url.edu Artificial Intelligence – Machine Learning g g Enginyeria i Arquitectura La Salle Universitat Ramon Llull
  • 2. Recap of Lectures 5-18 Supervised learning p g Data classification Labeled data Build a model that covers all the space Unsupervised Uns per ised learning Clustering Unlabeled data Group similar objects Association rule analysis Unlabeled data Get the most frequent/important associations Slide 2 Artificial Intelligence Machine Learning
  • 3. Today’s Agenda Fuzzy Logics Fuzzy Systems Genetic Fuzzy Systems Slide 3 Artificial Intelligence Machine Learning
  • 4. Fuzzy Logics Looking up in the dictionary… gp y Fuzzy = “not clear, distinct, or precise; blurred” The Th world is imprecise, not clear, blurred… ld i i i tl bl d The world is fuzzy! Definition of fuzzy logics yg A form of knowledge representation suitable for notions that cannot be defined precisely, but which depend upon their p y, p p contexts Let’s go from true and false (traditional logics) to something more powerful Slide 4 Artificial Intelligence Machine Learning
  • 5. Fuzzy Logics Traditional logic representation g p Slow Fast Logic rep Slow speed = 0 Fast speed = 1 Slide 5 Artificial Intelligence Machine Learning
  • 6. Fuzzy Logics How fast is fast? Definition of slow and fast depend on the eyes of the beholder Natural language contains many subjective t N t ll ti bj ti terms How can I deal with this? H d l ith thi ? Fast Very fast Very slow Slow These four are linguistic terms St , Still, I need to de e t e se a t cs o eac eed define the semantics of each linguistic term! Slide 6 Artificial Intelligence Machine Learning
  • 7. Fuzzy Logics Classical view Define intervals: very slow [0 – 0.25] slow [0.25 – 0.5] fast [0.5 – 0.75] very fast [0.75 – 1] Fuzzy logics view yg Consider the degree with which each observation belongs to each linguistic term Define a membership function Slide 7 Artificial Intelligence Machine Learning
  • 8. Fuzzy Logics Member ship functions Semantics of the system Fast Very fast Very slow Slow 0 0.25 0.50 0.75 1 Slide 8 Artificial Intelligence Machine Learning
  • 9. Fuzzy Logics Many different membership functions. Some of them are y p 1 c ab d Slide 9 Artificial Intelligence Machine Learning
  • 10. Fuzzy Systems Fuzzy systems yy are fundamental methodologies to represent and process gu s c o a o linguistic information use fuzzy logic to either represent the knowledge or model the interactions a d relationships a o g the sys e variables in e ac o s and e a o s ps among e system a ab es environments where there is uncertainty and imprecision. E.g. of knowledge representation: If john is tall and fast then strong Genetic fuzzy systems yy The use of genetic/evolutionary algorithms (GAs) to design fuzzy systems yy Slide 10 Artificial Intelligence Machine Learning
  • 11. GFS Slide 11 Artificial Intelligence Machine Learning
  • 12. GFS Two key elements: y Fuzzy system In our case, we will focus on rule-based systems case Genetic algorithm Fuzzy system yy Slide 12 Artificial Intelligence Machine Learning
  • 13. Fuzzy Rule-Based Systems Rule base If size is small and weight is small then quality is bad If size is small and weight i l ii ll d i ht is large th quality i medium then lit is di If size is large and weight is small then quality is medium If size is large and weight is large then quality is good Data base Slide 13 Artificial Intelligence Machine Learning
  • 14. Fuzzy Rule-Based Systems Operation of the inference system Centre of gravity Slide 14 Artificial Intelligence Machine Learning
  • 15. Fuzzy Rule-Based Systems Great, I know how to infer… But who gives me , g The rules The i f Th information of the data base (the semantics) ti f th d t b (th ti ) The inference engine Inference system Defuzzification methods Use a genetic algorithm for this task Slide 15 Artificial Intelligence Machine Learning
  • 16. Recall GAs? Population Individual 1 Fit. 1 Individual 2 Fit. 2 Individual i Population ... ... Individual n Fit. n Individual j Individual 1 Initialization Individual 2 Individual 1 ... Individual n Individual n Individual i’ Individual i’’ Mutation Individual j’ Individual j’’ Individual I di id l 1’ Individual 1’’ Individual n’ Individual n’’ Selection + Mutation: Continuous improvement and local search Selection + Recombination: Innovation Slide 16 Artificial Intelligence Machine Learning
  • 17. Where Do we Use the GA? Taxonomy of GFS ( y (Herrera, 2008) , ) Slide 17 Artificial Intelligence Machine Learning
  • 18. Where Do we Use the GA? Taxonomy of GFS ( y (Herrera, 2008) , ) Slide 18 Artificial Intelligence Machine Learning
  • 19. Topics We are going to see g g Genetic tuning 1. Genetic rule learning G ti ll i 2. Genetic rule selection 3. Genetic DB learning 4. S u ta eous genetic ea Simultaneous ge et c learning o KB co po e ts g of components 5 5. Genetic learning of KB components and inference engine 6. pa a ete s parameters 1st seen i thi l t in this lecture. 2nd-5th seen i next l t 5 in t lecture Information based on the paper Herrera (2009) and the corresponding presentation di t ti Slide 19 Artificial Intelligence Machine Learning
  • 20. 1. Genetic Tuning Typically membership functions yp y p are defined by domain experts are j t selected f just l t d from general f l forms: triangles, t ti l trapezoids, id Gaussian… But, B t could we have better membership functions? ld h b tt b hi f ti ? Let a GA tune the membership functions Also, tune the inference parameters Slide 20 Artificial Intelligence Machine Learning
  • 21. 1. Genetic Tuning How do we apply the GA? So, we are modifying the partitions of the feature space Slide 21 Artificial Intelligence Machine Learning
  • 22. 1. Genetic Tuning An example: Tuning triangular membership functions p g g p Each chromosome encodes a different DB definition 2 vars x 3 ling. labels = 6 mem. functions g Triangles 3 real values to code them Chromosome length = 18 genes Note that the RB remains unchanged! Slide 22 Artificial Intelligence Machine Learning
  • 23. Next Class Next l N t class Genetic rule learning 1. Genetic rule selection 2. Genetic DB learning 3. Simultaneous genetic learning of KB components 4. Genetic learning of KB components and inference engine G ti l i f t di f i 5. parameters Applications Slide 23 Artificial Intelligence Machine Learning
  • 24. Introduction to Machine Learning Lecture 19 Genetic Fuzzy Systems Albert Orriols i Puig http://www.albertorriols.net htt // lb t i l t aorriols@salle.url.edu Artificial Intelligence – Machine Learning g g Enginyeria i Arquitectura La Salle Universitat Ramon Llull