SlideShare a Scribd company logo
1 of 60
CS 9633 Machine Learning Computational Learning Theory Adapted from notes by Tom Mitchell http://www-2.cs.cmu.edu/~tom/mlbook-chapter-slides.html
Theoretical Characterization of Learning Problems ,[object Object],[object Object]
Two Frameworks ,[object Object],[object Object],[object Object]
Theoretical Questions of Interest ,[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object]
Computational Learning Theory  ,[object Object],[object Object],[object Object],[object Object]
Inductive Learning of Target Function ,[object Object],[object Object],[object Object],[object Object],[object Object],[object Object]
Questions for Broad Classes of Learning Algorithms ,[object Object],[object Object],[object Object],[object Object],[object Object],[object Object]
PAC Learning ,[object Object],[object Object]
Problem Setting: Instances and Concepts ,[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object]
Problem Setting: Distribution ,[object Object],[object Object],[object Object],[object Object],[object Object]
Problem Setting:  Hypotheses ,[object Object],[object Object]
Example Problem (Classifying Executables) ,[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object]
M No Yes No No 10 B Yes No No No 9 M Yes No Yes Yes 8 M No Yes Yes Yes 7 F No No No Yes 6 B Yes No No Yes 5 M Yes Yes No No 4 F No Yes Yes No 3 B No No No Yes 2 B Yes No No Yes 1 Class a 4 a 3 a 2 a 1 Instance
True Error ,[object Object]
Error of h with respect to c Instance space  X + + + c h - - - -
Key Points ,[object Object],[object Object],[object Object],[object Object]
PAC Learnability ,[object Object],[object Object],[object Object],[object Object],[object Object],[object Object]
Weaken Demand on Learner ,[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object]
Definition of PAC-Learnability ,[object Object]
Requirements of Definition ,[object Object],[object Object],[object Object],[object Object]
Block Diagram of PAC Learning Model Learning algorithm L Training sample Control Parameters  ,   Hypothesis h
Examples of second requirement ,[object Object],[object Object],[object Object],[object Object]
Using the Concept of PAC Learning in Practice ,[object Object],[object Object]
Sample Complexity ,[object Object],[object Object],[object Object],[object Object]
Recall definition of VS ,[object Object]
VS and PAC learning by consistent learners ,[object Object],[object Object]
 -exhausted ,[object Object]
Exhausting the version space VS H,D error = 0.1 r=0.2 error = 0.3 r=0.2 error = 0.2 r=0 error = 0.1 r=0 error = 0.3 r=0.4 error = 0.2 r=0.3 Hypothesis Space H
Exhausting the Version Space ,[object Object],[object Object],[object Object],[object Object]
Theorem 7.1 ,[object Object],[object Object]
Proof of theorem ,[object Object]
Number of Training Examples  (Eq. 7.2)
Summary of Result ,[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object]
Problem ,[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object]
Limits of Equation 7.2 ,[object Object],[object Object]
Agnostic Learning and Inconsistent Hypotheses ,[object Object],[object Object],[object Object]
Concepts that are PAC-Learnable ,[object Object],[object Object],[object Object]
PAC Learnability of Conjunctions of Boolean Literals ,[object Object],[object Object],[object Object],[object Object],[object Object],[object Object]
Examples Needed to Learn Each Concept ,[object Object],[object Object],[object Object],[object Object]
Complexity Per Example ,[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object]
Theorem 7.2 ,[object Object]
Proof of Theorem 7.2 ,[object Object]
Interesting Results ,[object Object],[object Object],[object Object]
Sample Complexity with Infinite Hypothesis Spaces ,[object Object],[object Object],[object Object],[object Object],[object Object],[object Object]
Shattering a Set of Instances ,[object Object],[object Object],[object Object],[object Object],[object Object],[object Object]
Shattering a Hypothesis Space ,[object Object]
Vapnik-Chervonenkis Dimension ,[object Object],[object Object],[object Object]
Vapnik-Chervonenkis Dimension ,[object Object]
Shattered Instance Space
Example 1 of VC Dimension ,[object Object],[object Object],[object Object],[object Object]
Shattering the real number line -1.2 3.4 6.7 What is VC(H)? What is |H|? -1.2 3.4
Example 2 of VC Dimension ,[object Object],[object Object],[object Object]
Shattering the x-y plane 2 instances 3 instances VC(H) = ? |H| = ?
Proving limits on VC dimension ,[object Object],[object Object]
General result for r dimensional space ,[object Object]
Example 3 of VC dimension ,[object Object],[object Object],[object Object],[object Object]
Shattering conjunctions of literals ,[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object]
Sample Complexity and the VC dimension ,[object Object]
Comparing the Bounds
Lower Bound on Sample Complexity ,[object Object],[object Object]

More Related Content

What's hot

Inductive analytical approaches to learning
Inductive analytical approaches to learningInductive analytical approaches to learning
Inductive analytical approaches to learningswapnac12
 
Introduction to Deep Learning
Introduction to Deep LearningIntroduction to Deep Learning
Introduction to Deep LearningOswald Campesato
 
Ensemble learning
Ensemble learningEnsemble learning
Ensemble learningHaris Jamil
 
Using prior knowledge to initialize the hypothesis,kbann
Using prior knowledge to initialize the hypothesis,kbannUsing prior knowledge to initialize the hypothesis,kbann
Using prior knowledge to initialize the hypothesis,kbannswapnac12
 
Instance based learning
Instance based learningInstance based learning
Instance based learningSlideshare
 
Concept learning and candidate elimination algorithm
Concept learning and candidate elimination algorithmConcept learning and candidate elimination algorithm
Concept learning and candidate elimination algorithmswapnac12
 
Lecture 18: Gaussian Mixture Models and Expectation Maximization
Lecture 18: Gaussian Mixture Models and Expectation MaximizationLecture 18: Gaussian Mixture Models and Expectation Maximization
Lecture 18: Gaussian Mixture Models and Expectation Maximizationbutest
 
L2. Evaluating Machine Learning Algorithms I
L2. Evaluating Machine Learning Algorithms IL2. Evaluating Machine Learning Algorithms I
L2. Evaluating Machine Learning Algorithms IMachine Learning Valencia
 
Back propagation
Back propagationBack propagation
Back propagationNagarajan
 
Perceptron (neural network)
Perceptron (neural network)Perceptron (neural network)
Perceptron (neural network)EdutechLearners
 
Decision Tree Learning
Decision Tree LearningDecision Tree Learning
Decision Tree LearningMilind Gokhale
 
Machine learning Lecture 2
Machine learning Lecture 2Machine learning Lecture 2
Machine learning Lecture 2Srinivasan R
 
Naive bayes
Naive bayesNaive bayes
Naive bayesumeskath
 
Machine Learning: Introduction to Neural Networks
Machine Learning: Introduction to Neural NetworksMachine Learning: Introduction to Neural Networks
Machine Learning: Introduction to Neural NetworksFrancesco Collova'
 
Linear regression
Linear regressionLinear regression
Linear regressionMartinHogg9
 
Learning sets of rules, Sequential Learning Algorithm,FOIL
Learning sets of rules, Sequential Learning Algorithm,FOILLearning sets of rules, Sequential Learning Algorithm,FOIL
Learning sets of rules, Sequential Learning Algorithm,FOILPavithra Thippanaik
 
Learning set of rules
Learning set of rulesLearning set of rules
Learning set of rulesswapnac12
 

What's hot (20)

Bayesian learning
Bayesian learningBayesian learning
Bayesian learning
 
Inductive analytical approaches to learning
Inductive analytical approaches to learningInductive analytical approaches to learning
Inductive analytical approaches to learning
 
Introduction to Deep Learning
Introduction to Deep LearningIntroduction to Deep Learning
Introduction to Deep Learning
 
Ensemble learning
Ensemble learningEnsemble learning
Ensemble learning
 
Using prior knowledge to initialize the hypothesis,kbann
Using prior knowledge to initialize the hypothesis,kbannUsing prior knowledge to initialize the hypothesis,kbann
Using prior knowledge to initialize the hypothesis,kbann
 
Instance based learning
Instance based learningInstance based learning
Instance based learning
 
Module 4 part_1
Module 4 part_1Module 4 part_1
Module 4 part_1
 
Concept learning and candidate elimination algorithm
Concept learning and candidate elimination algorithmConcept learning and candidate elimination algorithm
Concept learning and candidate elimination algorithm
 
Lecture 18: Gaussian Mixture Models and Expectation Maximization
Lecture 18: Gaussian Mixture Models and Expectation MaximizationLecture 18: Gaussian Mixture Models and Expectation Maximization
Lecture 18: Gaussian Mixture Models and Expectation Maximization
 
L2. Evaluating Machine Learning Algorithms I
L2. Evaluating Machine Learning Algorithms IL2. Evaluating Machine Learning Algorithms I
L2. Evaluating Machine Learning Algorithms I
 
Back propagation
Back propagationBack propagation
Back propagation
 
Perceptron (neural network)
Perceptron (neural network)Perceptron (neural network)
Perceptron (neural network)
 
Decision Tree Learning
Decision Tree LearningDecision Tree Learning
Decision Tree Learning
 
Machine learning Lecture 2
Machine learning Lecture 2Machine learning Lecture 2
Machine learning Lecture 2
 
Naive bayes
Naive bayesNaive bayes
Naive bayes
 
Machine Learning: Introduction to Neural Networks
Machine Learning: Introduction to Neural NetworksMachine Learning: Introduction to Neural Networks
Machine Learning: Introduction to Neural Networks
 
Linear regression
Linear regressionLinear regression
Linear regression
 
Lecture 9 Perceptron
Lecture 9 PerceptronLecture 9 Perceptron
Lecture 9 Perceptron
 
Learning sets of rules, Sequential Learning Algorithm,FOIL
Learning sets of rules, Sequential Learning Algorithm,FOILLearning sets of rules, Sequential Learning Algorithm,FOIL
Learning sets of rules, Sequential Learning Algorithm,FOIL
 
Learning set of rules
Learning set of rulesLearning set of rules
Learning set of rules
 

Similar to Computational Learning Theory

lecture_mooney.ppt
lecture_mooney.pptlecture_mooney.ppt
lecture_mooney.pptbutest
 
AML_030607.ppt
AML_030607.pptAML_030607.ppt
AML_030607.pptbutest
 
Module 4_F.pptx
Module  4_F.pptxModule  4_F.pptx
Module 4_F.pptxSupriyaN21
 
-BayesianLearning in machine Learning 12
-BayesianLearning in machine Learning 12-BayesianLearning in machine Learning 12
-BayesianLearning in machine Learning 12Kumari Naveen
 
Alpaydin - Chapter 2
Alpaydin - Chapter 2Alpaydin - Chapter 2
Alpaydin - Chapter 2butest
 
Alpaydin - Chapter 2
Alpaydin - Chapter 2Alpaydin - Chapter 2
Alpaydin - Chapter 2butest
 
Machine Learning
Machine LearningMachine Learning
Machine Learningbutest
 
Statistical Machine________ Learning.ppt
Statistical Machine________ Learning.pptStatistical Machine________ Learning.ppt
Statistical Machine________ Learning.pptSandeepGupta229023
 
4-ML-UNIT-IV-Bayesian Learning.pptx
4-ML-UNIT-IV-Bayesian Learning.pptx4-ML-UNIT-IV-Bayesian Learning.pptx
4-ML-UNIT-IV-Bayesian Learning.pptxSaitama84
 
Bayesian Learning- part of machine learning
Bayesian Learning-  part of machine learningBayesian Learning-  part of machine learning
Bayesian Learning- part of machine learningkensaleste
 
Lecture 3 (Supervised learning)
Lecture 3 (Supervised learning)Lecture 3 (Supervised learning)
Lecture 3 (Supervised learning)VARUN KUMAR
 
original
originaloriginal
originalbutest
 
Lecture 7
Lecture 7Lecture 7
Lecture 7butest
 
Lecture 7
Lecture 7Lecture 7
Lecture 7butest
 
Operations management chapter 03 homework assignment use this
Operations management chapter 03 homework assignment use thisOperations management chapter 03 homework assignment use this
Operations management chapter 03 homework assignment use thisPOLY33
 

Similar to Computational Learning Theory (20)

Lecture5 xing
Lecture5 xingLecture5 xing
Lecture5 xing
 
.ppt
.ppt.ppt
.ppt
 
lecture_mooney.ppt
lecture_mooney.pptlecture_mooney.ppt
lecture_mooney.ppt
 
AML_030607.ppt
AML_030607.pptAML_030607.ppt
AML_030607.ppt
 
Module 4_F.pptx
Module  4_F.pptxModule  4_F.pptx
Module 4_F.pptx
 
-BayesianLearning in machine Learning 12
-BayesianLearning in machine Learning 12-BayesianLearning in machine Learning 12
-BayesianLearning in machine Learning 12
 
Alpaydin - Chapter 2
Alpaydin - Chapter 2Alpaydin - Chapter 2
Alpaydin - Chapter 2
 
Alpaydin - Chapter 2
Alpaydin - Chapter 2Alpaydin - Chapter 2
Alpaydin - Chapter 2
 
Machine Learning
Machine LearningMachine Learning
Machine Learning
 
ppt
pptppt
ppt
 
Statistical Machine________ Learning.ppt
Statistical Machine________ Learning.pptStatistical Machine________ Learning.ppt
Statistical Machine________ Learning.ppt
 
4-ML-UNIT-IV-Bayesian Learning.pptx
4-ML-UNIT-IV-Bayesian Learning.pptx4-ML-UNIT-IV-Bayesian Learning.pptx
4-ML-UNIT-IV-Bayesian Learning.pptx
 
tutorial.ppt
tutorial.ppttutorial.ppt
tutorial.ppt
 
Bayesian Learning- part of machine learning
Bayesian Learning-  part of machine learningBayesian Learning-  part of machine learning
Bayesian Learning- part of machine learning
 
Lecture 3 (Supervised learning)
Lecture 3 (Supervised learning)Lecture 3 (Supervised learning)
Lecture 3 (Supervised learning)
 
AI ML M5
AI ML M5AI ML M5
AI ML M5
 
original
originaloriginal
original
 
Lecture 7
Lecture 7Lecture 7
Lecture 7
 
Lecture 7
Lecture 7Lecture 7
Lecture 7
 
Operations management chapter 03 homework assignment use this
Operations management chapter 03 homework assignment use thisOperations management chapter 03 homework assignment use this
Operations management chapter 03 homework assignment use this
 

More from butest

EL MODELO DE NEGOCIO DE YOUTUBE
EL MODELO DE NEGOCIO DE YOUTUBEEL MODELO DE NEGOCIO DE YOUTUBE
EL MODELO DE NEGOCIO DE YOUTUBEbutest
 
1. MPEG I.B.P frame之不同
1. MPEG I.B.P frame之不同1. MPEG I.B.P frame之不同
1. MPEG I.B.P frame之不同butest
 
LESSONS FROM THE MICHAEL JACKSON TRIAL
LESSONS FROM THE MICHAEL JACKSON TRIALLESSONS FROM THE MICHAEL JACKSON TRIAL
LESSONS FROM THE MICHAEL JACKSON TRIALbutest
 
Timeline: The Life of Michael Jackson
Timeline: The Life of Michael JacksonTimeline: The Life of Michael Jackson
Timeline: The Life of Michael Jacksonbutest
 
Popular Reading Last Updated April 1, 2010 Adams, Lorraine The ...
Popular Reading Last Updated April 1, 2010 Adams, Lorraine The ...Popular Reading Last Updated April 1, 2010 Adams, Lorraine The ...
Popular Reading Last Updated April 1, 2010 Adams, Lorraine The ...butest
 
LESSONS FROM THE MICHAEL JACKSON TRIAL
LESSONS FROM THE MICHAEL JACKSON TRIALLESSONS FROM THE MICHAEL JACKSON TRIAL
LESSONS FROM THE MICHAEL JACKSON TRIALbutest
 
Com 380, Summer II
Com 380, Summer IICom 380, Summer II
Com 380, Summer IIbutest
 
The MYnstrel Free Press Volume 2: Economic Struggles, Meet Jazz
The MYnstrel Free Press Volume 2: Economic Struggles, Meet JazzThe MYnstrel Free Press Volume 2: Economic Struggles, Meet Jazz
The MYnstrel Free Press Volume 2: Economic Struggles, Meet Jazzbutest
 
MICHAEL JACKSON.doc
MICHAEL JACKSON.docMICHAEL JACKSON.doc
MICHAEL JACKSON.docbutest
 
Social Networks: Twitter Facebook SL - Slide 1
Social Networks: Twitter Facebook SL - Slide 1Social Networks: Twitter Facebook SL - Slide 1
Social Networks: Twitter Facebook SL - Slide 1butest
 
Facebook
Facebook Facebook
Facebook butest
 
Executive Summary Hare Chevrolet is a General Motors dealership ...
Executive Summary Hare Chevrolet is a General Motors dealership ...Executive Summary Hare Chevrolet is a General Motors dealership ...
Executive Summary Hare Chevrolet is a General Motors dealership ...butest
 
Welcome to the Dougherty County Public Library's Facebook and ...
Welcome to the Dougherty County Public Library's Facebook and ...Welcome to the Dougherty County Public Library's Facebook and ...
Welcome to the Dougherty County Public Library's Facebook and ...butest
 
NEWS ANNOUNCEMENT
NEWS ANNOUNCEMENTNEWS ANNOUNCEMENT
NEWS ANNOUNCEMENTbutest
 
C-2100 Ultra Zoom.doc
C-2100 Ultra Zoom.docC-2100 Ultra Zoom.doc
C-2100 Ultra Zoom.docbutest
 
MAC Printing on ITS Printers.doc.doc
MAC Printing on ITS Printers.doc.docMAC Printing on ITS Printers.doc.doc
MAC Printing on ITS Printers.doc.docbutest
 
Mac OS X Guide.doc
Mac OS X Guide.docMac OS X Guide.doc
Mac OS X Guide.docbutest
 
WEB DESIGN!
WEB DESIGN!WEB DESIGN!
WEB DESIGN!butest
 

More from butest (20)

EL MODELO DE NEGOCIO DE YOUTUBE
EL MODELO DE NEGOCIO DE YOUTUBEEL MODELO DE NEGOCIO DE YOUTUBE
EL MODELO DE NEGOCIO DE YOUTUBE
 
1. MPEG I.B.P frame之不同
1. MPEG I.B.P frame之不同1. MPEG I.B.P frame之不同
1. MPEG I.B.P frame之不同
 
LESSONS FROM THE MICHAEL JACKSON TRIAL
LESSONS FROM THE MICHAEL JACKSON TRIALLESSONS FROM THE MICHAEL JACKSON TRIAL
LESSONS FROM THE MICHAEL JACKSON TRIAL
 
Timeline: The Life of Michael Jackson
Timeline: The Life of Michael JacksonTimeline: The Life of Michael Jackson
Timeline: The Life of Michael Jackson
 
Popular Reading Last Updated April 1, 2010 Adams, Lorraine The ...
Popular Reading Last Updated April 1, 2010 Adams, Lorraine The ...Popular Reading Last Updated April 1, 2010 Adams, Lorraine The ...
Popular Reading Last Updated April 1, 2010 Adams, Lorraine The ...
 
LESSONS FROM THE MICHAEL JACKSON TRIAL
LESSONS FROM THE MICHAEL JACKSON TRIALLESSONS FROM THE MICHAEL JACKSON TRIAL
LESSONS FROM THE MICHAEL JACKSON TRIAL
 
Com 380, Summer II
Com 380, Summer IICom 380, Summer II
Com 380, Summer II
 
PPT
PPTPPT
PPT
 
The MYnstrel Free Press Volume 2: Economic Struggles, Meet Jazz
The MYnstrel Free Press Volume 2: Economic Struggles, Meet JazzThe MYnstrel Free Press Volume 2: Economic Struggles, Meet Jazz
The MYnstrel Free Press Volume 2: Economic Struggles, Meet Jazz
 
MICHAEL JACKSON.doc
MICHAEL JACKSON.docMICHAEL JACKSON.doc
MICHAEL JACKSON.doc
 
Social Networks: Twitter Facebook SL - Slide 1
Social Networks: Twitter Facebook SL - Slide 1Social Networks: Twitter Facebook SL - Slide 1
Social Networks: Twitter Facebook SL - Slide 1
 
Facebook
Facebook Facebook
Facebook
 
Executive Summary Hare Chevrolet is a General Motors dealership ...
Executive Summary Hare Chevrolet is a General Motors dealership ...Executive Summary Hare Chevrolet is a General Motors dealership ...
Executive Summary Hare Chevrolet is a General Motors dealership ...
 
Welcome to the Dougherty County Public Library's Facebook and ...
Welcome to the Dougherty County Public Library's Facebook and ...Welcome to the Dougherty County Public Library's Facebook and ...
Welcome to the Dougherty County Public Library's Facebook and ...
 
NEWS ANNOUNCEMENT
NEWS ANNOUNCEMENTNEWS ANNOUNCEMENT
NEWS ANNOUNCEMENT
 
C-2100 Ultra Zoom.doc
C-2100 Ultra Zoom.docC-2100 Ultra Zoom.doc
C-2100 Ultra Zoom.doc
 
MAC Printing on ITS Printers.doc.doc
MAC Printing on ITS Printers.doc.docMAC Printing on ITS Printers.doc.doc
MAC Printing on ITS Printers.doc.doc
 
Mac OS X Guide.doc
Mac OS X Guide.docMac OS X Guide.doc
Mac OS X Guide.doc
 
hier
hierhier
hier
 
WEB DESIGN!
WEB DESIGN!WEB DESIGN!
WEB DESIGN!
 

Computational Learning Theory

  • 1. CS 9633 Machine Learning Computational Learning Theory Adapted from notes by Tom Mitchell http://www-2.cs.cmu.edu/~tom/mlbook-chapter-slides.html
  • 2.
  • 3.
  • 4.
  • 5.
  • 6.
  • 7.
  • 8.
  • 9.
  • 10.
  • 11.
  • 12.
  • 13. M No Yes No No 10 B Yes No No No 9 M Yes No Yes Yes 8 M No Yes Yes Yes 7 F No No No Yes 6 B Yes No No Yes 5 M Yes Yes No No 4 F No Yes Yes No 3 B No No No Yes 2 B Yes No No Yes 1 Class a 4 a 3 a 2 a 1 Instance
  • 14.
  • 15. Error of h with respect to c Instance space X + + + c h - - - -
  • 16.
  • 17.
  • 18.
  • 19.
  • 20.
  • 21. Block Diagram of PAC Learning Model Learning algorithm L Training sample Control Parameters  ,  Hypothesis h
  • 22.
  • 23.
  • 24.
  • 25.
  • 26.
  • 27.
  • 28. Exhausting the version space VS H,D error = 0.1 r=0.2 error = 0.3 r=0.2 error = 0.2 r=0 error = 0.1 r=0 error = 0.3 r=0.4 error = 0.2 r=0.3 Hypothesis Space H
  • 29.
  • 30.
  • 31.
  • 32. Number of Training Examples (Eq. 7.2)
  • 33.
  • 34.
  • 35.
  • 36.
  • 37.
  • 38.
  • 39.
  • 40.
  • 41.
  • 42.
  • 43.
  • 44.
  • 45.
  • 46.
  • 47.
  • 48.
  • 50.
  • 51. Shattering the real number line -1.2 3.4 6.7 What is VC(H)? What is |H|? -1.2 3.4
  • 52.
  • 53. Shattering the x-y plane 2 instances 3 instances VC(H) = ? |H| = ?
  • 54.
  • 55.
  • 56.
  • 57.
  • 58.
  • 60.