Nyhetsflöde

Fältövöreläsning

Teacher: Atsuto Maki¶

FöreläsningLecture 6, Classification Introduction

FR4

Fältövöreläsning

[{u'user_idname': u'u12rf6rnAtsuto Maki', u'user_nameid': u'Giampiero Salviu1elx760'}]

Lecture 6, ClassificatRegression Introduction

Teacher: Atsuto Maki¶

Topics:¶


* Function approximation
* Linear regression
* RANSAC
* Nearest Neighbours regression
* Linear regression + regularization
* Ridge regression
* Lasso
Slides from this lecture: Slides for Lecture 6¶

Topics:

* Function approximation
* Linear regression
* RANSAC
* Nearest Neighbours regression
* Linear regression + regularization
* Ridge regression
* Lasso
Slides from this lecture: Slides for Lecture 6

Topics:

* Function approximation
* Linear regression
* RANSAC
* Nearest Neighbours regression
* Linear regression + regularization
* Ridge regression
* Lasso
Slides from this lecture: Slides for Lecture 6or Lecture 6¶

Related reading:¶

Chapter 3 and 6.2 from An Introduction to Statistical Learning (Springer, 2013)¶

Gareth James, Daniela Witten, Trevor Hastie and Robert TibshiraniAvailable online: http://www-bcf.usc.edu/~gareth/ISL/¶

Topics:

* Function approximation
* Linear regression
* RANSAC
* Nearest Neighbours regression
* Linear regression + regularization
* Ridge regression
* Lasso
Slides for Lecture 6

Related reading:

Chapter 3 and 6.2 from An Introduction to Statistical Learning (Springer, 2013)

Gareth James, Daniela Witten, Trevor Hastie and Robert TibshiraniAvailable online: http://www-bcf.usc.edu/~gareth/ISL/

Topics:

* Function approximation
* Linear regression
* RANSAC
* Nearest Neighbours regression
* Linear regression + regularization
* Ridge regression
* Lasso
Slides for Lecture 6

Related reading:

Chapter 3 and 6.2 from An Introduction to Statistical Learning (Springer, 2013)

Gareth James, Daniela Witten, Trevor Hastie and Robert TibshiraniAvailable online: http://www-bcf.usc.edu/~gareth/ISL/

FöreläsningLecture 10, Ensemble Methods

Topics:¶


* Wisdom of Crowd
* Why combine classifiers?
* Bagging
* Decision Forests
* Boosting
Slides for Lecture 10¶

Topics:

* Wisdom of Crowd
* Why combine classifiers?
* Bagging
* Decision Forests
* Boosting
Slides for Lecture 10

¶

Topics:

* Wisdom of Crowd
* Why combine classifiers?
* Bagging
* Decision Forests
* Boosting
Slides for Lecture 10

Topics:

* Wisdom of Crowd
* Why combine classifiers?
* Bagging
* Decision Forests
* Boosting
Slides for Lecture 10

Related reading:¶

Chapter 8.2 from An Introduction to Statistical Learning (Springer, 2013)¶

Gareth James, Daniela Witten, Trevor Hastie and Robert TibshiraniAvailable online: http://www-bcf.usc.edu/~gareth/ISL/

Topics:

* Wisdom of Crowd
* Why combine classifiers?
* Bagging
* Decision Forests
* Boosting
Slides for Lecture 10

Related reading:

Chapter 8.2 from An Introduction to Statistical Learning (Springer, 2013)

Gareth James, Daniela Witten, Trevor Hastie and Robert TibshiraniAvailable online: http://www-bcf.usc.edu/~gareth/ISL/

FöreläsningLecture 9, Learning Theory

Topics:¶


* Concepts and Hypotheses
* PAC-Learning
* VC-Dimension
Slides from lecture 9¶

Topics:

* Concepts and Hypotheses
* PAC-Learning
* VC-Dimension
Slides from lecture 9

FöreläsningLecture 8, Classification with Separating Hyperplanes

Topics:¶


* Linear separation
* Structural risk minimization
* Support vector machines
* Kernels
* Non-separable Classes
Slides from lecture 8¶

Topics:

* Linear separation
* Structural risk minimization
* Support vector machines
* Kernels
* Non-separable Classes
Slides from lecture 8

Teacher: Atsuto Maki¶

FöreläsningLecture 7, Regression Introduction

[{u'user_idname': u'u12rf6rnAtsuto Maki', u'user_nameid': u'Giampiero Salviu1elx760'}]

Lecture 7, RegressClassification Introduction

Teacher: Atsuto Maki¶

Topics:¶


* Logistic regression
* Inference and decision
* Discriminative function
* Discriminative vs Generative model
* Naive Bayes
Slides from this lecture: Slides for Lecture 7 ¶

                                       Slides for Lecture 7 (part II)¶

Topics:

* Logistic regression
* Inference and decision
* Discriminative function
* Discriminative vs Generative model
* Naive Bayes
Slides from this lecture:  Slides for Lecture 7 ¶                                       (part I) , Slides for Lecture 7 (part II)

¶

Topics:

* Naive Bayes
* Logistic regression
* Inference and decision
* Discriminative function
* Discriminative vs Generative model
* Naive Bayes
Slides from this lecture: Slides for Lecture 7 (part I) , Slides for Lecture 7 (part II)

Topics:

* Naive Bayes
* Logistic regression
* Inference and decision
* Discriminative function
* Discriminative vs Generative model
Slides from this lecture: Slides for Lecture 7 (part I) , Slides for Lecture 7 (part II)

Topics:

* Naive Bayes
* Logistic regression
* Inference and decision
* Discriminative function
* Discriminative vs Generative model
Slides from this lecture: or Lecture 7 (part I) , Slides for Lecture 7 (part I) , Slides for Lecture 7 (part II)¶ I)¶

Related reading:¶

Chapter 4 from An Introduction to Statistical Learning (Springer, 2013)¶

Gareth James, Daniela Witten, Trevor Hastie and Robert TibshiraniAvailable online: http://www-bcf.usc.edu/~gareth/ISL/

Topics:

* Naive Bayes
* Logistic regression
* Inference and decision
* Discriminative function
* Discriminative vs Generative model
Slides for Lecture 7 (part I) , Slides for Lecture 7 (part II)

Related reading:

Chapter 4 from An Introduction to Statistical Learning (Springer, 2013)

Gareth James, Daniela Witten, Trevor Hastie and Robert TibshiraniAvailable online: http://www-bcf.usc.edu/~gareth/ISL/

FöreläsLecture 5, Challenges to machine learning

Topics:¶


* Challenges to machine learning
* Model complexity and overfitting
* The curse of dimentionality
* Concepts of prediction errors
* The bias-variance trade-off
Slides from this lecture: Slides for Lecture 5¶

Related reading: Chapter 2 from An Introduction to Statistical Learning James et al.¶

available online at: http://www-bcf.usc.edu/~gareth/ISL/data.html¶

Topics:

* Challenges to machine learning
* Model complexity and overfitting
* The curse of dimentionality
* Concepts of prediction errors
* The bias-variance trade-off
Slides from this lecture: Slides for Lecture 5

Related reading: Chapter 2 from An Introduction to Statistical Learning James et al.¶ available online at: http://www-bcf.usc.edu/~gareth/ISL/data.html

Topics:

* Challenges to machine learning
* Model complexity and overfitting
* The curse of dimentionality
* Concepts of prediction errors
* The bias-variance trade-off
Slides from this lecture: Slides for Lecture 5

Topics:

* Challenges to machine learning
* Model complexity and overfitting
* The curse of dimentionality
* Concepts of prediction errors
* The bias-variance trade-off
Slides from this lecture: Slides for Lecture 5

Topics:

* Challenges to machine learning
* Model complexity and overfitting
* The curse of dimentionality
* Concepts of prediction errors
* The bias-variance trade-off
Slides from this lecture: Slides for Lecture 5

¶

Topics:

* Challenges to machine learning
* Model complexity and overfitting
* The curse of dimentionality
* Concepts of prediction errors
* The bias-variance trade-off
Slides from this lecture: Slides for Lecture 5

¶

Topics:

* Challenges to machine learning
* Model complexity and overfitting
* The curse of dimentionality
* Concepts of prediction errors
* The bias-variance trade-off
Slides from this lecture: Slides for Lecture 5

Topics:

* Challenges to machine learning
* Model complexity and overfitting
* The curse of dimentionality
* Concepts of prediction errors
* The bias-variance trade-off
Slides from this lecture: Slides for Lecture 5¶ or Lecture 5¶

Related reading:¶

Chapter 2 and 6.4 from An Introduction to Statistical Learning (Springer, 2013)¶

Gareth James, Daniela Witten, Trevor Hastie and Robert TibshiraniAvailable online: http://www-bcf.usc.edu/~gareth/ISL/

Topics:

* Challenges to machine learning
* Model complexity and overfitting
* The curse of dimentsionality
* Concepts of prediction errors
* The bias-variance trade-off
Slides for Lecture 5

Related reading:

Chapter 2 and 6.4 from An Introduction to Statistical Learning (Springer, 2013)

Gareth James, Daniela Witten, Trevor Hastie and Robert TibshiraniAvailable online: http://www-bcf.usc.edu/~gareth/ISL/

Teacher: Giampiero Salvi¶

FöreläsningLecture 4, Probability II

Teacher: Giampiero Salvi

Topics:¶


* Fitting probability models (continued)
* Model selection (Occam's Razor)
* Unsupervised learning and Expectation Maximization
Selected reading:¶

Chapters 4 and 7 from Computer Vision: Models, Learning, and Inference Simon J.D. Princeavailable online at: http://www.computervisionmodels.com/¶

[{u'user_idname': u'u1oppompGiampiero Salvi', u'user_nameid': u'\xd6rjan Ekebergu12rf6rn'}]

Teacher: Giampiero Salvi

Topics:

* Fitting probability models (continued)
* Model selection (Occam's Razor)
* Unsupervised learning and Expectation Maximization
Selected reading:

Chapters 4 and 7 from Computer Vision: Models, Learning, and Inference Simon J.D. Princeavailable online at: http://www.computervisionmodels.com/

Handouts: Handouts for Lecture 04¶

¶

Teacher: Giampiero Salvi

Topics:

* Fitting probability models (continued)
* Model selection (Occam's Razor)
* Unsupervised learning and Expectation Maximization
Selected reading:

Chapters 4 and 7 from Computer Vision: Models, Learning, and Inference Simon J.D. Princeavailable online at: http://www.computervisionmodels.com/

Handouts: Handouts for Lecture 04

Teacher: Giampiero Salvi

Topics:

* Fitting probability models (continued)
* Model selection (Occam's Razor)
* Unsupervised learning and Expectation Maximization
Selected reading:

Chapters 4 and 7 from Computer Vision: Models, Learning, and Inference Simon J.D. Princeavailable online at: http://www.computervisionmodels.com/

Handouts: Handouts for Lecture 04

Teacher: Giampiero Salvi

Topics:

* Fitting probability models (continued)
* Model selection (Occam's Razor)
* Unsupervised learning and Expectation Maximization
Selected reading:

Chapters 4 and 7 from Computer Vision: Models, Learning, and Inference Simon J.D. Princeavailable online at: http://www.computervisionmodels.com/

Handouts: Handouts for Lecture 04

FöreläsningLecture 3, Probability I

Topics:¶


* Probability theory
* Common probability distributions
* Bayes rule and machine learning
Selected reading:¶

Chapters 2, 3, 5 from Computer Vision: Models, Learning, and Inference Simon J.D. Princeavailable online at: http://www.computervisionmodels.com/¶

¶

Topics:

* Probability theory
* Common probability distributions
* Bayes rule and machine learning
* Fitting probability models
Selected reading:

Chapters 2, 3, -5 from Computer Vision: Models, Learning, and Inference Simon J.D. Princeavailable online at: http://www.computervisionmodels.com/

Topics:

* Probability theory
* Common probability distributions
* Bayes rule and machine learning
* Fitting probability models
Handouts: 03-probtheory-2x2.pdf¶

Selected reading:

Chapters 2-5 from Computer Vision: Models, Learning, and Inference Simon J.D. Princeavailable online at: http://www.computervisionmodels.com/

Topics:

* Probability theory
* Common probability distributions
* Bayes rule and machine learning
* Fitting probability models
Handouts: 03-probtheory-2x2.pdf

Selected reading:

Chapters 2-5 from Computer Vision: Models, Learning, and Inference Simon J.D. Princeavailable online at: http://www.computervisionmodels.com/

FöreläsningLecture 1, Introduction

Structure of the Course¶


* What will the course cover?
* How are labs and examination handled?
Learning Machines¶


* What do we mean by a "Learning Machine"?
* Supervised vs Unsupervised learning?   
* What can learning algorithms be used for?
* How can a simple learning program be constructured?
* What is a Nearest neighbour classifier?

Structure of the Course

* What will the course cover?
* How are labs and examination handled?
Learning Machines

* What do we mean by a "Learning Machine"?
* Supervised vs Unsupervised learning?   
* What can learning algorithms be used for?
* How can a simple learning program be constructured?
* What is a Nearest neighbour classifier?
Slides from this lecture: Slides for Lecture 1¶

Slides from this lecture: Slides for Lecture 1 (part II)¶

Structure of the Course

* What will the course cover?
* How are labs and examination handled?
Learning Machines

* What do we mean by a "Learning Machine"?
* Supervised vs Unsupervised learning?   
* What can learning algorithms be used for?
* How can a simple learning program be constructured?
* What is a Nearest neighbour classifier?
Slides from this lecture: Slides for Lecture 1

Slides from this lecture: Slides for Lecture 1 (part II)

Structure of the Course

* What will the course cover?
* How are labs and examination handled?
Learning Machines

* What do we mean by a "Learning Machine"?
* Supervised vs Unsupervised learning?   
* What can learning algorithms be used for?
* How can a simple learning program be constructured?
* What is a Nearest neighbour classifier?
Slides from this lecture: Slides for Lecture 1¶ Slides from this lecture:or Lecture 1¶

Slides for Lecture 1 (part II)

Structure of the Course

* What will the course cover?
* How are labs and examination handled?
Learning Machines

* What do we mean by a "Learning Machine"?
* Supervised vs Unsupervised learning?   
* What can learning algorithms be used for?
* How can a simple learning program be constructured?
* What is a Nearest neighbour classifier?
Slides for Lecture 1

Slides for Lecture 1 (part II)

FöreläsningLecture 2, Decision Trees

* What is a Decision Tree?
* When are decision trees useful?
* How can one select what questions to ask?
* What do we mean by Entropy for a data set?
* What do we mean by the Information Gain of a question?
* What is the problem of overfitting? Minimizing training error?
* Bias - Variance trade-off

* What is a Decision Tree?
* When are decision trees useful?
* How can one select what questions to ask?
* What do we mean by Entropy for a data set?
* What do we mean by the Information Gain of a question?
* What is the problem of overfitting? Minimizing training error?
* Bias - Variance trade-off
What extensions will be possible for improvement?
Slides from this lecture: Slides for Lecture 2   ¶

* What is a Decision Tree?
* When are decision trees useful?
* How can one select what questions to ask?
* What do we mean by Entropy for a data set?
* What do we mean by the Information Gain of a question?
* What is the problem of overfitting? Minimizing training error?
* What extensions will be possible for improvement?
Slides from this lecture: Slides for Lecture 2  

* What is a Decision Tree?
* When are decision trees useful?
* How can one select what questions to ask?
* What do we mean by Entropy for a data set?
* What do we mean by the Information Gain of a question?
* What is the problem of overfitting? Minimizing training error?
* What extensions will be possible for improvement?
Slides from this lecture: Slides for Lecture 2

* What is a Decision Tree?
* When are decision trees useful?
* How can one select what questions to ask?
* What do we mean by Entropy for a data set?
* What do we mean by the Information Gain of a question?
* What is the problem of overfitting? Minimizing training error?
* What extensions will be possible for improvement?
Slides from this lecture: Slides for Lecture 2or Lecture 2¶

Related reading:¶

An Introduction to Statistical Learning with Applications in R (Springer, 2013)Gareth James, Daniela Witten, Trevor Hastie and Robert TibshiraniAvailable online: http://www-bcf.usc.edu/~gareth/ISL/¶

Chapter 8.1¶

* What is a Decision Tree?
* When are decision trees useful?
* How can one select what questions to ask?
* What do we mean by Entropy for a data set?
* What do we mean by the Information Gain of a question?
* What is the problem of overfitting? Minimizing training error?
* What extensions will be possible for improvement?
Slides for Lecture 2

Related reading:

Chapter 8.1 from An Introduction to Statistical Learning with Applications in R (Springer, 2013)¶

Gareth James, Daniela Witten, Trevor Hastie and Robert TibshiraniAvailable online: http://www-bcf.usc.edu/~gareth/ISL/

Chapter 8.1¶ ¶

* What is a Decision Tree?
* When are decision trees useful?
* How can one select what questions to ask?
* What do we mean by Entropy for a data set?
* What do we mean by the Information Gain of a question?
* What is the problem of overfitting? Minimizing training error?
* What extensions will be possible for improvement?
Slides for Lecture 2

Related reading:

Chapter 8.1 from An Introduction to Statistical Learning (Springer, 2013)

Gareth James, Daniela Witten, Trevor Hastie and Robert TibshiraniAvailable online: http://www-bcf.usc.edu/~gareth/ISL/

* What is a Decision Tree?
* When are decision trees useful?
* How can one select what questions to ask?
* What do we mean by Entropy for a data set?
* What do we mean by the Information Gain of a question?
* What is the problem of overfitting? Minimizing training error?
* What extensions will be possible for improvement?
Slides for Lecture 2

Related reading:

Chapter 8.1 from An Introduction to Statistical Learning (Springer, 2013)

Gareth James, Daniela Witten, Trevor Hastie and Robert TibshiraniAvailable online: http://www-bcf.usc.edu/~gareth/ISL/

FöreläsningLecture 11, Learning Representation

Lecture 11, Learning RepresentaDimensionality Reduction

Topics:¶


* Concept of subspace
* Similarity measure
* Subspace method
* Unsupervised Learning
* Principal Component Analysis (PCA)
Slides from lecture 11¶

Related reading:¶

Chapter 10.2 from An Introduction to Statistical Learning (Springer, 2013)¶

Gareth James, Daniela Witten, Trevor Hastie and Robert TibshiraniAvailable online: http://www-bcf.usc.edu/~gareth/ISL/¶

¶

Topics:

* Concept of subspace
* Similarity measure
* Subspace method
* Unsupervised Learning
* Principal Component Analysis (PCA)
Slides from lecture 11

Related reading:

Chapter 10.2 from An Introduction to Statistical Learning (Springer, 2013)

Gareth James, Daniela Witten, Trevor Hastie and Robert TibshiraniAvailable online: http://www-bcf.usc.edu/~gareth/ISL/

Topics:

* Concept of subspace
* Similarity measure
* Subspace method
* Unsupervised Learning
* Principal Component Analysis (PCA)
Slides from lor Lecture 11

Related reading:

Chapter 10.2 from An Introduction to Statistical Learning (Springer, 2013)

Gareth James, Daniela Witten, Trevor Hastie and Robert TibshiraniAvailable online: http://www-bcf.usc.edu/~gareth/ISL/

Topics:

* Concept of subspace
* Similarity measure
* Subspace method
* Unsupervised Learning
* Principal Component Analysis (PCA)
Slides for Lecture 11

Related reading:

Chapter 10.2 from An Introduction to Statistical Learning (Springer, 2013)

Gareth James, Daniela Witten, Trevor Hastie and Robert TibshiraniAvailable online: http://www-bcf.usc.edu/~gareth/ISL/

TorsMåndag 913 oktober 2014 kl 107:00 - 129:00

FR4D1

FöreläsningLecture 12, Summary

Slides for Lecture 12¶

Slides for Lecture 12