SlideShare a Scribd company logo
1 of 22
Terry Taewoong Um (terry.t.um@gmail.com)
University of Waterloo
Department of Electrical & Computer Engineering
Terry Taewoong Um
INTRODUCTION TO
MACHINE LEARNING
AND DEEP LEARNING
1
T-robotics.blogspot.com
Facebook.com/TRobotics
Terry Taewoong Um (terry.t.um@gmail.com)
CAUTION
• I cannot explain everything
• You cannot get every details
2
• Try to get a big picture
• Get some useful keywords
• Connect with your research
Terry Taewoong Um (terry.t.um@gmail.com)
CONTENTS
1. What is Machine Learning?
2. What is Deep Learning?
3
Terry Taewoong Um (terry.t.um@gmail.com)
CONTENTS
4
1. What is Machine Learning?
Terry Taewoong Um (terry.t.um@gmail.com)
WHAT IS MACHINE LEARNING?
"A computer program is said to learn from experience E
with respect to some class of tasks T and performance
measure P, if its performance at tasks in T, as measured
by P, improves with experience E“ – T. Michell (1997)
Example: A program for soccer tactics
5
T : Win the game
P : Goals
E : (x) Players’ movements
(y) Evaluation
Terry Taewoong Um (terry.t.um@gmail.com)
WHAT IS MACHINE LEARNING?
6
“Toward learning robot table tennis”, J. Peters et al. (2012)
https://youtu.be/SH3bADiB7uQ
"A computer program is said to learn from experience E
with respect to some class of tasks T and performance
measure P, if its performance at tasks in T, as measured
by P, improves with experience E“ – T. Michell (1997)
Terry Taewoong Um (terry.t.um@gmail.com)
TASKS
7
classification
discrete target values
x : pixels (28*28)
y : 0,1, 2,3,…,9
regression
real target values
x ∈ (0,100)
y : 0,1, 2,3,…,9
clustering
no target values
x ∈ (-3,3)×(-3,3)
"A computer program is said to learn from experience E
with respect to some class of tasks T and performance
measure P, if its performance at tasks in T, as measured
by P, improves with experience E“ – T. Michell (1997)
Terry Taewoong Um (terry.t.um@gmail.com)
PERFORMANCE
8
"A computer program is said to learn from experience E
with respect to some class of tasks T and performance
measure P, if its performance at tasks in T, as measured
by P, improves with experience E“ – T. Michell (1997)
classification
0-1 loss function
regression
L2 loss function
clustering
Terry Taewoong Um (terry.t.um@gmail.com)
EXPERIENCE
9
"A computer program is said to learn from experience E
with respect to some class of tasks T and performance
measure P, if its performance at tasks in T, as measured
by P, improves with experience E“ – T. Michell (1997)
classification
labeled data
(pixels)→(number)
regression
labeled data
(x) → (y)
clustering
unlabeled data
(x1,x2)
Terry Taewoong Um (terry.t.um@gmail.com)
A TOY EXAMPLE
10
? Height(cm)
Weight
(kg)
[Input X]
[Output Y]
Terry Taewoong Um (terry.t.um@gmail.com)
11
180 Height(cm)
Weight
(kg)
80
Y = aX+b
Model : Y = aX+b Parameter : (a, b)
[Goal] Find (a,b) which best fits the given data
A TOY EXAMPLE
Terry Taewoong Um (terry.t.um@gmail.com)
12
[Analytic Solution]
Least square problem
(from AX = b, X=A#b where
A# is A’s pseudo inverse)
Not always available
[Numerical Solution]
1. Set a cost function
2. Apply an optimization method
(e.g. Gradient Descent (GD) Method)
L
(a,b)
http://www.yaldex.com/game-
development/1592730043_ch18lev1sec4.html
Local minima problem
http://mnemstudio.org/neural-networks-
multilayer-perceptron-design.htm
A TOY EXAMPLE
Terry Taewoong Um (terry.t.um@gmail.com)
13
32 Age(year)
Running
Record
(min)
140
WHAT WOULD BE THE CORRECT MODEL?
Select a model → Set a cost function → Optimization
Terry Taewoong Um (terry.t.um@gmail.com)
14
? X
Y
WHAT WOULD BE THE CORRECT MODEL?
1. Regularization 2. Nonparametric model
“overfitting”
Terry Taewoong Um (terry.t.um@gmail.com)
15
L2 REGULARIZATION
(e.g. w=(a,b) where Y=aX+b)
Avoid a complicated model!
• Another interpretation :
: Maximum a Posteriori (MAP)
http://goo.gl/6GE2ix
http://goo.gl/6GE2ix
Terry Taewoong Um (terry.t.um@gmail.com)
16
WHAT WOULD BE THE CORRECT MODEL?
1. Regularization 2. Nonparametric model
training time
error
training error
test error
we should
stop here
training
set
validation
set
test
set
for training
(parameter
optimization)
for early
stopping
(avoid
overfitting)
for evaluation
(measure the
performance)
keep watching the validation error
Terry Taewoong Um (terry.t.um@gmail.com)
17
NONPARAMETRIC MODEL
• It does not assume any parametric models (e.g. Y = aX+b, Y=aX2+bX+c, etc.)
• It often requires much more samples
• Kernel methods are frequently applied for modeling the data
• Gaussian Process Regression (GPR), a sort of kernel method, is a widely-used
nonparametric regression method
• Support Vector Machine (SVM), also a sort of kernel method, is a widely-used
nonparametric classification method
kernel function
[Input space] [Feature space]
Terry Taewoong Um (terry.t.um@gmail.com)
18
SUPPORT VECTOR MACHINE (SVM)
“Myo”, Thalmic Labs (2013)
https://youtu.be/oWu9TFJjHaM
[Linear classifiers] [Maximum margin]
Support vector Machine Tutorial, J. Weston, http://goo.gl/19ywcj
[Dual formulation] ( )
kernel function
kernel function
Terry Taewoong Um (terry.t.um@gmail.com)
19
GAUSSIAN PROCESS REGRESSION (GPR)
https://youtu.be/YqhLnCm0KXY
https://youtu.be/kvPmArtVoFE
• Gaussian Distribution
• Multivariate regression likelihood
posterior
prior
likelihood
prediction conditioning the joint distribution of the observed & predicted values
https://goo.gl/EO54WN
http://goo.gl/XvOOmf
Terry Taewoong Um (terry.t.um@gmail.com)
20
DIMENSION REDUCTION
[Original space] [Feature space]
low dim. high dim.
high dim. low dim.
𝑋 → ∅(𝑋)
• Principal Component Analysis
: Find the best orthogonal axes
(=principal components) which
maximize the variance of the data
Y = P X
* The rows in P are m largest eigenvectors
of
1
𝑁
𝑋𝑋 𝑇
(covariance matrix)
Terry Taewoong Um (terry.t.um@gmail.com)
21
DIMENSION REDUCTION
http://jbhuang0604.blogspot.kr/2013/04/miss-korea-2013-contestants-face.html
Terry Taewoong Um (terry.t.um@gmail.com)
22
SUMMARY - PART 1
• Machine Learning
- Tasks : Classification, Regression, Clustering, etc.
- Performance : 0-1 loss, L2 loss, etc.
- Experience : labeled data, unlabelled data
• Machine Learning Process
(1) Select a parametric / nonparametric model
(2) Set a performance measurement including regularization term
(3) Training data (optimizing parameters) until validation error increases
(4) Evaluate the final performance using test set
• Nonparametric model : Support Vector Machine, Gaussian Process Regression
• Dimension reduction : used as pre-processing data

More Related Content

What's hot

ReComment: Towards Critiquing-based Recommendation with Speech Interaction
ReComment: Towards Critiquing-based Recommendation with Speech InteractionReComment: Towards Critiquing-based Recommendation with Speech Interaction
ReComment: Towards Critiquing-based Recommendation with Speech Interaction
Peter Grasch
 

What's hot (14)

Introduction to Deep Learning with TensorFlow
Introduction to Deep Learning with TensorFlowIntroduction to Deep Learning with TensorFlow
Introduction to Deep Learning with TensorFlow
 
Deep Variational Bayes Filters (2017)
Deep Variational Bayes Filters (2017)Deep Variational Bayes Filters (2017)
Deep Variational Bayes Filters (2017)
 
Deep Learning: A Critical Appraisal (2018)
Deep Learning: A Critical Appraisal (2018)Deep Learning: A Critical Appraisal (2018)
Deep Learning: A Critical Appraisal (2018)
 
On Calibration of Modern Neural Networks (2017)
On Calibration of Modern Neural Networks (2017)On Calibration of Modern Neural Networks (2017)
On Calibration of Modern Neural Networks (2017)
 
Novel Machine Learning Methods for Extraction of Features Characterizing Data...
Novel Machine Learning Methods for Extraction of Features Characterizing Data...Novel Machine Learning Methods for Extraction of Features Characterizing Data...
Novel Machine Learning Methods for Extraction of Features Characterizing Data...
 
Network analysis lecture
Network analysis lectureNetwork analysis lecture
Network analysis lecture
 
Tabu search
Tabu searchTabu search
Tabu search
 
Could a Data Science Program use Data Science Insights?
Could a Data Science Program use Data Science Insights?Could a Data Science Program use Data Science Insights?
Could a Data Science Program use Data Science Insights?
 
BDACA - Tutorial5
BDACA - Tutorial5BDACA - Tutorial5
BDACA - Tutorial5
 
A Network-Aware Approach for Searching As-You-Type in Social Media
A Network-Aware Approach for Searching As-You-Type in Social MediaA Network-Aware Approach for Searching As-You-Type in Social Media
A Network-Aware Approach for Searching As-You-Type in Social Media
 
String matching algorithms
String matching algorithmsString matching algorithms
String matching algorithms
 
Joint contrastive learning with infinite possibilities
Joint contrastive learning with infinite possibilitiesJoint contrastive learning with infinite possibilities
Joint contrastive learning with infinite possibilities
 
metaheuristic tabu pso
metaheuristic tabu psometaheuristic tabu pso
metaheuristic tabu pso
 
ReComment: Towards Critiquing-based Recommendation with Speech Interaction
ReComment: Towards Critiquing-based Recommendation with Speech InteractionReComment: Towards Critiquing-based Recommendation with Speech Interaction
ReComment: Towards Critiquing-based Recommendation with Speech Interaction
 

Viewers also liked

Deview deep learning-김정희
Deview deep learning-김정희Deview deep learning-김정희
Deview deep learning-김정희
NAVER D2
 

Viewers also liked (17)

기계학습 / 딥러닝이란 무엇인가
기계학습 / 딥러닝이란 무엇인가기계학습 / 딥러닝이란 무엇인가
기계학습 / 딥러닝이란 무엇인가
 
Lie Group Formulation for Robot Mechanics
Lie Group Formulation for Robot MechanicsLie Group Formulation for Robot Mechanics
Lie Group Formulation for Robot Mechanics
 
쫄지말자딥러닝2 - CNN RNN 포함버전
쫄지말자딥러닝2 - CNN RNN 포함버전쫄지말자딥러닝2 - CNN RNN 포함버전
쫄지말자딥러닝2 - CNN RNN 포함버전
 
인공지능, 기계학습 그리고 딥러닝
인공지능, 기계학습 그리고 딥러닝인공지능, 기계학습 그리고 딥러닝
인공지능, 기계학습 그리고 딥러닝
 
알파고 (바둑 인공지능)의 작동 원리
알파고 (바둑 인공지능)의 작동 원리알파고 (바둑 인공지능)의 작동 원리
알파고 (바둑 인공지능)의 작동 원리
 
알파고 해부하기 1부
알파고 해부하기 1부알파고 해부하기 1부
알파고 해부하기 1부
 
[2A4]DeepLearningAtNAVER
[2A4]DeepLearningAtNAVER[2A4]DeepLearningAtNAVER
[2A4]DeepLearningAtNAVER
 
[모두의연구소] 쫄지말자딥러닝
[모두의연구소] 쫄지말자딥러닝[모두의연구소] 쫄지말자딥러닝
[모두의연구소] 쫄지말자딥러닝
 
인공 신경망 구현에 관한 간단한 설명
인공 신경망 구현에 관한 간단한 설명인공 신경망 구현에 관한 간단한 설명
인공 신경망 구현에 관한 간단한 설명
 
R 프로그래밍 기본 문법
R 프로그래밍 기본 문법R 프로그래밍 기본 문법
R 프로그래밍 기본 문법
 
머신 러닝 입문 #1-머신러닝 소개와 kNN 소개
머신 러닝 입문 #1-머신러닝 소개와 kNN 소개머신 러닝 입문 #1-머신러닝 소개와 kNN 소개
머신 러닝 입문 #1-머신러닝 소개와 kNN 소개
 
Large Scale Deep Learning with TensorFlow
Large Scale Deep Learning with TensorFlow Large Scale Deep Learning with TensorFlow
Large Scale Deep Learning with TensorFlow
 
Deview deep learning-김정희
Deview deep learning-김정희Deview deep learning-김정희
Deview deep learning-김정희
 
자습해도 모르겠던 딥러닝, 머리속에 인스톨 시켜드립니다.
자습해도 모르겠던 딥러닝, 머리속에 인스톨 시켜드립니다.자습해도 모르겠던 딥러닝, 머리속에 인스톨 시켜드립니다.
자습해도 모르겠던 딥러닝, 머리속에 인스톨 시켜드립니다.
 
Ai 그까이거
Ai 그까이거Ai 그까이거
Ai 그까이거
 
텐서플로우 설치도 했고 튜토리얼도 봤고 기초 예제도 짜봤다면 TensorFlow KR Meetup 2016
텐서플로우 설치도 했고 튜토리얼도 봤고 기초 예제도 짜봤다면 TensorFlow KR Meetup 2016텐서플로우 설치도 했고 튜토리얼도 봤고 기초 예제도 짜봤다면 TensorFlow KR Meetup 2016
텐서플로우 설치도 했고 튜토리얼도 봤고 기초 예제도 짜봤다면 TensorFlow KR Meetup 2016
 
딥러닝과 강화 학습으로 나보다 잘하는 쿠키런 AI 구현하기 DEVIEW 2016
딥러닝과 강화 학습으로 나보다 잘하는 쿠키런 AI 구현하기 DEVIEW 2016딥러닝과 강화 학습으로 나보다 잘하는 쿠키런 AI 구현하기 DEVIEW 2016
딥러닝과 강화 학습으로 나보다 잘하는 쿠키런 AI 구현하기 DEVIEW 2016
 

Similar to 기계학습(Machine learning) 입문하기

Week 1 Lec 1-5 with watermarking.pdf
Week 1 Lec 1-5 with watermarking.pdfWeek 1 Lec 1-5 with watermarking.pdf
Week 1 Lec 1-5 with watermarking.pdf
meghana092
 
Week_1_Lec_1-5_with_watermarking_(1).pdf
Week_1_Lec_1-5_with_watermarking_(1).pdfWeek_1_Lec_1-5_with_watermarking_(1).pdf
Week_1_Lec_1-5_with_watermarking_(1).pdf
PrabhaK22
 
Lec 1 Ds
Lec 1 DsLec 1 Ds
Lec 1 Ds
Qundeel
 
Data Structure
Data StructureData Structure
Data Structure
sheraz1
 
Lec 1 Ds
Lec 1 DsLec 1 Ds
Lec 1 Ds
Qundeel
 

Similar to 기계학습(Machine learning) 입문하기 (20)

Deep learning (Machine learning) tutorial for beginners
Deep learning (Machine learning) tutorial for beginnersDeep learning (Machine learning) tutorial for beginners
Deep learning (Machine learning) tutorial for beginners
 
Machine Learning Lecture Series Lecture 1
Machine Learning Lecture Series Lecture 1Machine Learning Lecture Series Lecture 1
Machine Learning Lecture Series Lecture 1
 
Week 2 - ML models and Linear Regression.pptx
Week 2 - ML models and Linear Regression.pptxWeek 2 - ML models and Linear Regression.pptx
Week 2 - ML models and Linear Regression.pptx
 
Chapter two
Chapter twoChapter two
Chapter two
 
01_introduction_ML.pdf
01_introduction_ML.pdf01_introduction_ML.pdf
01_introduction_ML.pdf
 
Data Structure and Algorithms
Data Structure and AlgorithmsData Structure and Algorithms
Data Structure and Algorithms
 
Introducción a TDD
Introducción a TDDIntroducción a TDD
Introducción a TDD
 
See12.ppt
See12.pptSee12.ppt
See12.ppt
 
Machine Learning, Financial Engineering and Quantitative Investing
Machine Learning, Financial Engineering and Quantitative InvestingMachine Learning, Financial Engineering and Quantitative Investing
Machine Learning, Financial Engineering and Quantitative Investing
 
Introduction to computing Processing and performance.pdf
Introduction to computing Processing and performance.pdfIntroduction to computing Processing and performance.pdf
Introduction to computing Processing and performance.pdf
 
Analysis and Algorithms: basic Introduction
Analysis and Algorithms: basic IntroductionAnalysis and Algorithms: basic Introduction
Analysis and Algorithms: basic Introduction
 
Experiments with Machine Learning - GDG Lviv
Experiments with Machine Learning - GDG LvivExperiments with Machine Learning - GDG Lviv
Experiments with Machine Learning - GDG Lviv
 
Week 1 Lec 1-5 with watermarking.pdf
Week 1 Lec 1-5 with watermarking.pdfWeek 1 Lec 1-5 with watermarking.pdf
Week 1 Lec 1-5 with watermarking.pdf
 
Week_1_Lec_1-5_with_watermarking_(1).pdf
Week_1_Lec_1-5_with_watermarking_(1).pdfWeek_1_Lec_1-5_with_watermarking_(1).pdf
Week_1_Lec_1-5_with_watermarking_(1).pdf
 
Java™ (OOP) - Chapter 5: "Methods"
Java™ (OOP) - Chapter 5: "Methods"Java™ (OOP) - Chapter 5: "Methods"
Java™ (OOP) - Chapter 5: "Methods"
 
Data Structure: Algorithm and analysis
Data Structure: Algorithm and analysisData Structure: Algorithm and analysis
Data Structure: Algorithm and analysis
 
ML_Lecture_1.ppt
ML_Lecture_1.pptML_Lecture_1.ppt
ML_Lecture_1.ppt
 
Lec 1 Ds
Lec 1 DsLec 1 Ds
Lec 1 Ds
 
Data Structure
Data StructureData Structure
Data Structure
 
Lec 1 Ds
Lec 1 DsLec 1 Ds
Lec 1 Ds
 

Recently uploaded

1_Introduction + EAM Vocabulary + how to navigate in EAM.pdf
1_Introduction + EAM Vocabulary + how to navigate in EAM.pdf1_Introduction + EAM Vocabulary + how to navigate in EAM.pdf
1_Introduction + EAM Vocabulary + how to navigate in EAM.pdf
AldoGarca30
 
XXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXX
XXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXX
XXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXX
ssuser89054b
 
Hospital management system project report.pdf
Hospital management system project report.pdfHospital management system project report.pdf
Hospital management system project report.pdf
Kamal Acharya
 
Standard vs Custom Battery Packs - Decoding the Power Play
Standard vs Custom Battery Packs - Decoding the Power PlayStandard vs Custom Battery Packs - Decoding the Power Play
Standard vs Custom Battery Packs - Decoding the Power Play
Epec Engineered Technologies
 

Recently uploaded (20)

1_Introduction + EAM Vocabulary + how to navigate in EAM.pdf
1_Introduction + EAM Vocabulary + how to navigate in EAM.pdf1_Introduction + EAM Vocabulary + how to navigate in EAM.pdf
1_Introduction + EAM Vocabulary + how to navigate in EAM.pdf
 
DC MACHINE-Motoring and generation, Armature circuit equation
DC MACHINE-Motoring and generation, Armature circuit equationDC MACHINE-Motoring and generation, Armature circuit equation
DC MACHINE-Motoring and generation, Armature circuit equation
 
XXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXX
XXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXX
XXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXX
 
Orlando’s Arnold Palmer Hospital Layout Strategy-1.pptx
Orlando’s Arnold Palmer Hospital Layout Strategy-1.pptxOrlando’s Arnold Palmer Hospital Layout Strategy-1.pptx
Orlando’s Arnold Palmer Hospital Layout Strategy-1.pptx
 
FEA Based Level 3 Assessment of Deformed Tanks with Fluid Induced Loads
FEA Based Level 3 Assessment of Deformed Tanks with Fluid Induced LoadsFEA Based Level 3 Assessment of Deformed Tanks with Fluid Induced Loads
FEA Based Level 3 Assessment of Deformed Tanks with Fluid Induced Loads
 
AIRCANVAS[1].pdf mini project for btech students
AIRCANVAS[1].pdf mini project for btech studentsAIRCANVAS[1].pdf mini project for btech students
AIRCANVAS[1].pdf mini project for btech students
 
kiln thermal load.pptx kiln tgermal load
kiln thermal load.pptx kiln tgermal loadkiln thermal load.pptx kiln tgermal load
kiln thermal load.pptx kiln tgermal load
 
Wadi Rum luxhotel lodge Analysis case study.pptx
Wadi Rum luxhotel lodge Analysis case study.pptxWadi Rum luxhotel lodge Analysis case study.pptx
Wadi Rum luxhotel lodge Analysis case study.pptx
 
PE 459 LECTURE 2- natural gas basic concepts and properties
PE 459 LECTURE 2- natural gas basic concepts and propertiesPE 459 LECTURE 2- natural gas basic concepts and properties
PE 459 LECTURE 2- natural gas basic concepts and properties
 
Hospital management system project report.pdf
Hospital management system project report.pdfHospital management system project report.pdf
Hospital management system project report.pdf
 
Bhubaneswar🌹Call Girls Bhubaneswar ❤Komal 9777949614 💟 Full Trusted CALL GIRL...
Bhubaneswar🌹Call Girls Bhubaneswar ❤Komal 9777949614 💟 Full Trusted CALL GIRL...Bhubaneswar🌹Call Girls Bhubaneswar ❤Komal 9777949614 💟 Full Trusted CALL GIRL...
Bhubaneswar🌹Call Girls Bhubaneswar ❤Komal 9777949614 💟 Full Trusted CALL GIRL...
 
Standard vs Custom Battery Packs - Decoding the Power Play
Standard vs Custom Battery Packs - Decoding the Power PlayStandard vs Custom Battery Packs - Decoding the Power Play
Standard vs Custom Battery Packs - Decoding the Power Play
 
Thermal Engineering Unit - I & II . ppt
Thermal Engineering  Unit - I & II . pptThermal Engineering  Unit - I & II . ppt
Thermal Engineering Unit - I & II . ppt
 
A CASE STUDY ON CERAMIC INDUSTRY OF BANGLADESH.pptx
A CASE STUDY ON CERAMIC INDUSTRY OF BANGLADESH.pptxA CASE STUDY ON CERAMIC INDUSTRY OF BANGLADESH.pptx
A CASE STUDY ON CERAMIC INDUSTRY OF BANGLADESH.pptx
 
COST-EFFETIVE and Energy Efficient BUILDINGS ptx
COST-EFFETIVE  and Energy Efficient BUILDINGS ptxCOST-EFFETIVE  and Energy Efficient BUILDINGS ptx
COST-EFFETIVE and Energy Efficient BUILDINGS ptx
 
GEAR TRAIN- BASIC CONCEPTS AND WORKING PRINCIPLE
GEAR TRAIN- BASIC CONCEPTS AND WORKING PRINCIPLEGEAR TRAIN- BASIC CONCEPTS AND WORKING PRINCIPLE
GEAR TRAIN- BASIC CONCEPTS AND WORKING PRINCIPLE
 
Tamil Call Girls Bhayandar WhatsApp +91-9930687706, Best Service
Tamil Call Girls Bhayandar WhatsApp +91-9930687706, Best ServiceTamil Call Girls Bhayandar WhatsApp +91-9930687706, Best Service
Tamil Call Girls Bhayandar WhatsApp +91-9930687706, Best Service
 
Engineering Drawing focus on projection of planes
Engineering Drawing focus on projection of planesEngineering Drawing focus on projection of planes
Engineering Drawing focus on projection of planes
 
Moment Distribution Method For Btech Civil
Moment Distribution Method For Btech CivilMoment Distribution Method For Btech Civil
Moment Distribution Method For Btech Civil
 
Double Revolving field theory-how the rotor develops torque
Double Revolving field theory-how the rotor develops torqueDouble Revolving field theory-how the rotor develops torque
Double Revolving field theory-how the rotor develops torque
 

기계학습(Machine learning) 입문하기

  • 1. Terry Taewoong Um (terry.t.um@gmail.com) University of Waterloo Department of Electrical & Computer Engineering Terry Taewoong Um INTRODUCTION TO MACHINE LEARNING AND DEEP LEARNING 1 T-robotics.blogspot.com Facebook.com/TRobotics
  • 2. Terry Taewoong Um (terry.t.um@gmail.com) CAUTION • I cannot explain everything • You cannot get every details 2 • Try to get a big picture • Get some useful keywords • Connect with your research
  • 3. Terry Taewoong Um (terry.t.um@gmail.com) CONTENTS 1. What is Machine Learning? 2. What is Deep Learning? 3
  • 4. Terry Taewoong Um (terry.t.um@gmail.com) CONTENTS 4 1. What is Machine Learning?
  • 5. Terry Taewoong Um (terry.t.um@gmail.com) WHAT IS MACHINE LEARNING? "A computer program is said to learn from experience E with respect to some class of tasks T and performance measure P, if its performance at tasks in T, as measured by P, improves with experience E“ – T. Michell (1997) Example: A program for soccer tactics 5 T : Win the game P : Goals E : (x) Players’ movements (y) Evaluation
  • 6. Terry Taewoong Um (terry.t.um@gmail.com) WHAT IS MACHINE LEARNING? 6 “Toward learning robot table tennis”, J. Peters et al. (2012) https://youtu.be/SH3bADiB7uQ "A computer program is said to learn from experience E with respect to some class of tasks T and performance measure P, if its performance at tasks in T, as measured by P, improves with experience E“ – T. Michell (1997)
  • 7. Terry Taewoong Um (terry.t.um@gmail.com) TASKS 7 classification discrete target values x : pixels (28*28) y : 0,1, 2,3,…,9 regression real target values x ∈ (0,100) y : 0,1, 2,3,…,9 clustering no target values x ∈ (-3,3)×(-3,3) "A computer program is said to learn from experience E with respect to some class of tasks T and performance measure P, if its performance at tasks in T, as measured by P, improves with experience E“ – T. Michell (1997)
  • 8. Terry Taewoong Um (terry.t.um@gmail.com) PERFORMANCE 8 "A computer program is said to learn from experience E with respect to some class of tasks T and performance measure P, if its performance at tasks in T, as measured by P, improves with experience E“ – T. Michell (1997) classification 0-1 loss function regression L2 loss function clustering
  • 9. Terry Taewoong Um (terry.t.um@gmail.com) EXPERIENCE 9 "A computer program is said to learn from experience E with respect to some class of tasks T and performance measure P, if its performance at tasks in T, as measured by P, improves with experience E“ – T. Michell (1997) classification labeled data (pixels)→(number) regression labeled data (x) → (y) clustering unlabeled data (x1,x2)
  • 10. Terry Taewoong Um (terry.t.um@gmail.com) A TOY EXAMPLE 10 ? Height(cm) Weight (kg) [Input X] [Output Y]
  • 11. Terry Taewoong Um (terry.t.um@gmail.com) 11 180 Height(cm) Weight (kg) 80 Y = aX+b Model : Y = aX+b Parameter : (a, b) [Goal] Find (a,b) which best fits the given data A TOY EXAMPLE
  • 12. Terry Taewoong Um (terry.t.um@gmail.com) 12 [Analytic Solution] Least square problem (from AX = b, X=A#b where A# is A’s pseudo inverse) Not always available [Numerical Solution] 1. Set a cost function 2. Apply an optimization method (e.g. Gradient Descent (GD) Method) L (a,b) http://www.yaldex.com/game- development/1592730043_ch18lev1sec4.html Local minima problem http://mnemstudio.org/neural-networks- multilayer-perceptron-design.htm A TOY EXAMPLE
  • 13. Terry Taewoong Um (terry.t.um@gmail.com) 13 32 Age(year) Running Record (min) 140 WHAT WOULD BE THE CORRECT MODEL? Select a model → Set a cost function → Optimization
  • 14. Terry Taewoong Um (terry.t.um@gmail.com) 14 ? X Y WHAT WOULD BE THE CORRECT MODEL? 1. Regularization 2. Nonparametric model “overfitting”
  • 15. Terry Taewoong Um (terry.t.um@gmail.com) 15 L2 REGULARIZATION (e.g. w=(a,b) where Y=aX+b) Avoid a complicated model! • Another interpretation : : Maximum a Posteriori (MAP) http://goo.gl/6GE2ix http://goo.gl/6GE2ix
  • 16. Terry Taewoong Um (terry.t.um@gmail.com) 16 WHAT WOULD BE THE CORRECT MODEL? 1. Regularization 2. Nonparametric model training time error training error test error we should stop here training set validation set test set for training (parameter optimization) for early stopping (avoid overfitting) for evaluation (measure the performance) keep watching the validation error
  • 17. Terry Taewoong Um (terry.t.um@gmail.com) 17 NONPARAMETRIC MODEL • It does not assume any parametric models (e.g. Y = aX+b, Y=aX2+bX+c, etc.) • It often requires much more samples • Kernel methods are frequently applied for modeling the data • Gaussian Process Regression (GPR), a sort of kernel method, is a widely-used nonparametric regression method • Support Vector Machine (SVM), also a sort of kernel method, is a widely-used nonparametric classification method kernel function [Input space] [Feature space]
  • 18. Terry Taewoong Um (terry.t.um@gmail.com) 18 SUPPORT VECTOR MACHINE (SVM) “Myo”, Thalmic Labs (2013) https://youtu.be/oWu9TFJjHaM [Linear classifiers] [Maximum margin] Support vector Machine Tutorial, J. Weston, http://goo.gl/19ywcj [Dual formulation] ( ) kernel function kernel function
  • 19. Terry Taewoong Um (terry.t.um@gmail.com) 19 GAUSSIAN PROCESS REGRESSION (GPR) https://youtu.be/YqhLnCm0KXY https://youtu.be/kvPmArtVoFE • Gaussian Distribution • Multivariate regression likelihood posterior prior likelihood prediction conditioning the joint distribution of the observed & predicted values https://goo.gl/EO54WN http://goo.gl/XvOOmf
  • 20. Terry Taewoong Um (terry.t.um@gmail.com) 20 DIMENSION REDUCTION [Original space] [Feature space] low dim. high dim. high dim. low dim. 𝑋 → ∅(𝑋) • Principal Component Analysis : Find the best orthogonal axes (=principal components) which maximize the variance of the data Y = P X * The rows in P are m largest eigenvectors of 1 𝑁 𝑋𝑋 𝑇 (covariance matrix)
  • 21. Terry Taewoong Um (terry.t.um@gmail.com) 21 DIMENSION REDUCTION http://jbhuang0604.blogspot.kr/2013/04/miss-korea-2013-contestants-face.html
  • 22. Terry Taewoong Um (terry.t.um@gmail.com) 22 SUMMARY - PART 1 • Machine Learning - Tasks : Classification, Regression, Clustering, etc. - Performance : 0-1 loss, L2 loss, etc. - Experience : labeled data, unlabelled data • Machine Learning Process (1) Select a parametric / nonparametric model (2) Set a performance measurement including regularization term (3) Training data (optimizing parameters) until validation error increases (4) Evaluate the final performance using test set • Nonparametric model : Support Vector Machine, Gaussian Process Regression • Dimension reduction : used as pre-processing data