SlideShare a Scribd company logo
Big Data & Analytical Unit (BDAU)
Workshop On Machine Learning
Introduction to Machine Learning
Dr. Mian Asbat Ahmad – 3 March 2016
Goals of the presentation
• What is Machine Learning
• Types of Machine Learning
• Supervised Learning
• Linear Regression
• Logistic Regression
• Unsupervised Learning
• K-Nearest neighbour
• Applications of Machine Learning
• Practical
What is Machine Learning
Machine Learning
Definition 1
“Field of study that gives computers the ability to learn without being
explicitly programmed”. Arthur Samuel (1959)
Machine Learning
Definition 2
“A computer program is said to learn from Experience E with respect to
some Task T and some Performance measure P, if its performance on T, as
measured by P, improves with experience E”. Tom Mitchell (1998)
Example of Spam Filter
1. Classifying email as spam or ham (Task T)
2. Watching email for spam or ham (Experience E)
3. The number of emails correctly classified as spam or ham (Performance P)
In Machine Learning programs, the Performance P of the program will
improve on Task T with Experience E.
Terms of Machine Learning
• Dataset = Training set
• Rows = Training examples (m), m = 14
• Columns = features (n), n = 2
• Input variables/features/predictors/independant (x), x = 1
• Output variable/target variable/Response/dependant (y), y = 1
• (x(i), y(i)) to denote ith training example
• (x(14), y(14)) = (44.99, 996)
• (xj
(i), yj
(i)) to denote ith training example of jth feature
• (x1
(14), y1
(14)) = (44.99, 996)
Training
Set
Learning
Algorithm
Hypothesis
h
Output YInput X
Main types of Machine Learning
Supervised Learning
• Labelled data
• For example (x1, y1), (x2, y2), (x3, y3), (x4, y4), (x5, y5)
• Develop predictive model based on input and output data
• Regression is type of Supervised Learning which deals with continuous data
• Classification is type of Unsupervised Learning which deals with discrete data
Supervised
Learning
Regression
Problem
Classification
Problem
Supervised Learning
Linear Prediction or
Linear Regression
Linear function
ŷ = mx + b (simple linear regression)
From the figure put the value of m and b
ŷ = 3(x) + 2
Predict y when the value of x is 0
ŷ = 3(0) + 2
ŷ = 0 + 2
ŷ = 2
[http://philschatz.com/precalculus-book/contents/m49324.html]
Example of Supervised Learning 1 ( Regression problem)
To predict the average walking
distance of a person per day
with BMI 50 (kg/m2)
from the given data
BMI
Average Distance
Walked Per Day
42.82 1175
30.11 1600
43.24 905
36.44 1229
52.98 650
37.72 1009
48.44 792
46.44 1015
44.99 996
50.98 594
48.2 1022
63.37 196
55.86 429
52.62 522
32.83 1524
53.41 600
51.19 897
44.19 1058
51.73 479
47.34 936
33.57 1203
39.41 987
46.06 1043
42.42 971
43.94 1157
43.83 844
35.43 1165
61.66 351
Example of Supervised Learning 2 ( Regression problem)
100
300
500
700
900
1100
1300
1500
1700
25 35 45 55 65 75
AverageDistanceWalkedPerDay
BMI
Example of Supervised Learning 3 ( Regression problem)
100
300
500
700
900
1100
1300
1500
1700
25 35 45 55 65 75
AverageDistanceWalkedPerDay
BMI
Example of Supervised Learning 4 ( Regression problem)
100
300
500
700
900
1100
1300
1500
1700
25 35 45 55 65 75
AverageDistanceWalkedPerDay
BMI
The answer
is 730 m
Supervised Learning
Logistic Regression
Example of Supervised Learning 1 (Classification Problem)
Predict if a cancer
of a person with tumour
size 4 and age 40 is
Benign (B) or Malignant (M)
from the given data
Tumor Size Age Cancer
4 52 B
9 62 M
2 31 B
6 60 M
3 38 B
8 72 M
5 20 B
4 35 B
6 47 B
8 49 M
7 50 M
5 32 B
8 65 M
5 42 M
3 27 B
4 21 B
3 20 B
7 67 M
6 50 M
9 57 M
7 60 M
Example of Supervised Learning 2 (Classification Problem)
0
10
20
30
40
50
60
70
0 1 2 3 4 5 6 7 8 9 10
Age
Tumour size
Example of Supervised Learning 3 (Classification Problem)
0
10
20
30
40
50
60
70
0 1 2 3 4 5 6 7 8 9 10
Age
Tumour size
Example of Supervised Learning 4 (Classification Problem)
0
10
20
30
40
50
60
70
0 1 2 3 4 5 6 7 8 9 10
Age
Tumour size
The answer is
Benign
Unsupervised Learning
Clustering
Unsupervised Learning
• Unlabelled data
• For example (x1, x2, x3, x4, x5)
• Group and interpret data based only on input data
• Find interesting structures in the data
Unsupervised
Learning
Cluterring
Problem
Example of Unsupervised Learning 1 (Cluster Problem)
Predict if a cancer
of a person with tumour
size 4 and age 40 is
Benign (B) or Malignant (M)
from the given data.
Tumor Size Age
4 52
9 62
2 31
6 60
3 38
8 72
5 20
4 35
6 47
8 49
7 50
5 32
8 65
5 42
3 27
4 21
3 20
7 67
6 50
9 57
7 60
Non labelled data
0
10
20
30
40
50
60
70
0 1 2 3 4 5 6 7 8 9 10
Age
Tumor size
Split in to clusters
0
10
20
30
40
50
60
70
0 1 2 3 4 5 6 7 8 9 10
Age
Tumour size
Split in to clusters
0
10
20
30
40
50
60
70
0 1 2 3 4 5 6 7 8 9 10
Age
Tumour size
The
answer is
Benign
K-Means Algorithm Unsupervised Learning 1
[Prof. Andrew NG]
K-Means Algorithm Unsupervised Learning 2
• Take two random points on the data when k = 2
[Prof. Andrew NG]
K-Means Algorithm Unsupervised Learning 3
• Find distance of each value from the points
[Prof. Andrew NG]
K-Means Algorithm Unsupervised Learning 4
• Take mean of the distance and move the points there
[Prof. Andrew NG]
K-Means Algorithm Unsupervised Learning 5
• Find distance of each value from the points
[Prof. Andrew NG]
K-Means Algorithm Unsupervised Learning 6
• Take mean of the distance and move the points there
• The data is divided into two clusters
[Prof. Andrew NG]
K-Nearest Neighbour (Clustering problem)
0
10
20
30
40
50
60
70
0 1 2 3 4 5 6 7 8 9 10
Age
Tumor size
K-Nearest Neighbour (Clustering problem)
0
10
20
30
40
50
60
70
0 1 2 3 4 5 6 7 8 9 10
Age
Tumor size
K-Nearest Neighbour (Clustering problem)
0
10
20
30
40
50
60
70
0 1 2 3 4 5 6 7 8 9 10
Age
Tumor size
The answer is
Malignant
Applications of Machine Learning
Training Machine for detecting faces
[Thomas Serre 2012]
Training Machine to identify pedestrians
[Thomas Serre 2012]
Click to play the video
Search Engines (Ranking)
https://news.google.com/ (Clustering)
https://news.google.com/
Genes Clusters
[Su-In Lee, Dana Peer, Aimee Dudley, George Church, Daphne koller]
Recommender systems
Other applications of Machine Learning
• Data Mining / Data Analysis
• Hand writing recognition
• E.g. Automatic transfer of mail
• Natural language processing
• Analysis of social media (Twitter, Facebook, LinkedIn etc.)
• Credit card legitimate/fraud transaction detection
• Speech Recognition
• Google Now, Siri, Cortana voice recognition
• Recommender System
• Movie recommendations (Netflix)
Questions / Comments / Feedback
bdau@imperial.ac.uk
mian.ahmad@imperial.ac.uk

More Related Content

What's hot

Image Similarity Test Using Eigenface Calculation
Image Similarity Test Using Eigenface CalculationImage Similarity Test Using Eigenface Calculation
Image Similarity Test Using Eigenface Calculation
Universitas Pembangunan Panca Budi
 
08 classbasic
08 classbasic08 classbasic
08 classbasic
ritumysterious1
 
08 classbasic
08 classbasic08 classbasic
08 classbasic
engrasi
 
Learning strategy with groups on page based students' profiles
Learning strategy with groups on page based students' profilesLearning strategy with groups on page based students' profiles
Learning strategy with groups on page based students' profiles
aciijournal
 
Lecture 3: Basic Concepts of Machine Learning - Induction & Evaluation
Lecture 3: Basic Concepts of Machine Learning - Induction & EvaluationLecture 3: Basic Concepts of Machine Learning - Induction & Evaluation
Lecture 3: Basic Concepts of Machine Learning - Induction & Evaluation
Marina Santini
 
When Classifier Selection meets Information Theory: A Unifying View
When Classifier Selection meets Information Theory: A Unifying ViewWhen Classifier Selection meets Information Theory: A Unifying View
When Classifier Selection meets Information Theory: A Unifying View
Mohamed Farouk
 
Active learning
Active learningActive learning
CASP14 Data Assisted Modeling (KIharalab)
CASP14 Data Assisted Modeling (KIharalab)CASP14 Data Assisted Modeling (KIharalab)
CASP14 Data Assisted Modeling (KIharalab)
Purdue University
 
Comparison on PCA ICA and LDA in Face Recognition
Comparison on PCA ICA and LDA in Face RecognitionComparison on PCA ICA and LDA in Face Recognition
Comparison on PCA ICA and LDA in Face Recognition
ijdmtaiir
 
Educational Data Mining to Analyze Students Performance – Concept Plan
Educational Data Mining to Analyze Students Performance – Concept PlanEducational Data Mining to Analyze Students Performance – Concept Plan
Educational Data Mining to Analyze Students Performance – Concept Plan
IRJET Journal
 
Genetic Algorithm
Genetic AlgorithmGenetic Algorithm
Genetic Algorithm
Ankit Chaudhary
 
Lecture 2 Basic Concepts in Machine Learning for Language Technology
Lecture 2 Basic Concepts in Machine Learning for Language TechnologyLecture 2 Basic Concepts in Machine Learning for Language Technology
Lecture 2 Basic Concepts in Machine Learning for Language Technology
Marina Santini
 
Stellar simulation
Stellar simulationStellar simulation
Stellar simulation
TiongEve
 
Important questions for class 10 maths chapter 14 statistics with solutions
Important questions for class 10 maths chapter 14 statistics with solutionsImportant questions for class 10 maths chapter 14 statistics with solutions
Important questions for class 10 maths chapter 14 statistics with solutions
ExpertClass
 
Active learning lecture
Active learning lectureActive learning lecture
Active learning lecture
azuring
 
PhD Defense
PhD DefensePhD Defense
Classification and Prediction
Classification and PredictionClassification and Prediction
Classification and Prediction
SahilKumar542
 

What's hot (17)

Image Similarity Test Using Eigenface Calculation
Image Similarity Test Using Eigenface CalculationImage Similarity Test Using Eigenface Calculation
Image Similarity Test Using Eigenface Calculation
 
08 classbasic
08 classbasic08 classbasic
08 classbasic
 
08 classbasic
08 classbasic08 classbasic
08 classbasic
 
Learning strategy with groups on page based students' profiles
Learning strategy with groups on page based students' profilesLearning strategy with groups on page based students' profiles
Learning strategy with groups on page based students' profiles
 
Lecture 3: Basic Concepts of Machine Learning - Induction & Evaluation
Lecture 3: Basic Concepts of Machine Learning - Induction & EvaluationLecture 3: Basic Concepts of Machine Learning - Induction & Evaluation
Lecture 3: Basic Concepts of Machine Learning - Induction & Evaluation
 
When Classifier Selection meets Information Theory: A Unifying View
When Classifier Selection meets Information Theory: A Unifying ViewWhen Classifier Selection meets Information Theory: A Unifying View
When Classifier Selection meets Information Theory: A Unifying View
 
Active learning
Active learningActive learning
Active learning
 
CASP14 Data Assisted Modeling (KIharalab)
CASP14 Data Assisted Modeling (KIharalab)CASP14 Data Assisted Modeling (KIharalab)
CASP14 Data Assisted Modeling (KIharalab)
 
Comparison on PCA ICA and LDA in Face Recognition
Comparison on PCA ICA and LDA in Face RecognitionComparison on PCA ICA and LDA in Face Recognition
Comparison on PCA ICA and LDA in Face Recognition
 
Educational Data Mining to Analyze Students Performance – Concept Plan
Educational Data Mining to Analyze Students Performance – Concept PlanEducational Data Mining to Analyze Students Performance – Concept Plan
Educational Data Mining to Analyze Students Performance – Concept Plan
 
Genetic Algorithm
Genetic AlgorithmGenetic Algorithm
Genetic Algorithm
 
Lecture 2 Basic Concepts in Machine Learning for Language Technology
Lecture 2 Basic Concepts in Machine Learning for Language TechnologyLecture 2 Basic Concepts in Machine Learning for Language Technology
Lecture 2 Basic Concepts in Machine Learning for Language Technology
 
Stellar simulation
Stellar simulationStellar simulation
Stellar simulation
 
Important questions for class 10 maths chapter 14 statistics with solutions
Important questions for class 10 maths chapter 14 statistics with solutionsImportant questions for class 10 maths chapter 14 statistics with solutions
Important questions for class 10 maths chapter 14 statistics with solutions
 
Active learning lecture
Active learning lectureActive learning lecture
Active learning lecture
 
PhD Defense
PhD DefensePhD Defense
PhD Defense
 
Classification and Prediction
Classification and PredictionClassification and Prediction
Classification and Prediction
 

Similar to Introduction to Machine Learning

Lecture 09(introduction to machine learning)
Lecture 09(introduction to machine learning)Lecture 09(introduction to machine learning)
Lecture 09(introduction to machine learning)
Jeet Das
 
Introduction to data mining and machine learning
Introduction to data mining and machine learningIntroduction to data mining and machine learning
Introduction to data mining and machine learning
Tilani Gunawardena PhD(UNIBAS), BSc(Pera), FHEA(UK), CEng, MIESL
 
Machine Learning for Aerospace Training
Machine Learning for Aerospace TrainingMachine Learning for Aerospace Training
Machine Learning for Aerospace Training
Mikhail Klassen
 
Lecture 31
Lecture 31Lecture 31
Lecture 31
Shani729
 
Introduction to machine learning-2023-IT-AI and DS.pdf
Introduction to machine learning-2023-IT-AI and DS.pdfIntroduction to machine learning-2023-IT-AI and DS.pdf
Introduction to machine learning-2023-IT-AI and DS.pdf
SisayNegash4
 
Machine Learning ebook.pdf
Machine Learning ebook.pdfMachine Learning ebook.pdf
Machine Learning ebook.pdf
HODIT12
 
1_5_AI_edx_ml_51intro_240204_104838machine learning lecture 1
1_5_AI_edx_ml_51intro_240204_104838machine learning lecture 11_5_AI_edx_ml_51intro_240204_104838machine learning lecture 1
1_5_AI_edx_ml_51intro_240204_104838machine learning lecture 1
MostafaHazemMostafaa
 
Launching into machine learning
Launching into machine learningLaunching into machine learning
Launching into machine learning
Dr.R. Gunavathi Ramasamy
 
know Machine Learning Basic Concepts.pdf
know Machine Learning Basic Concepts.pdfknow Machine Learning Basic Concepts.pdf
know Machine Learning Basic Concepts.pdf
hemangppatel
 
Unit-1.ppt
Unit-1.pptUnit-1.ppt
Unit-1.ppt
ASrinivasReddy3
 
3.pdf
3.pdf3.pdf
Measures of Central tendency
Measures of Central tendencyMeasures of Central tendency
Measures of Central tendency
Edrin Jay Morta
 
Central Tendancy.pdf
Central Tendancy.pdfCentral Tendancy.pdf
Central Tendancy.pdf
MuhammadFaizan389
 
1_Introduction.pptx
1_Introduction.pptx1_Introduction.pptx
1_Introduction.pptx
ranapoonam1
 
Topic_6
Topic_6Topic_6
Topic_6
butest
 
Machine learning ppt unit one syllabuspptx
Machine learning ppt unit one syllabuspptxMachine learning ppt unit one syllabuspptx
Machine learning ppt unit one syllabuspptx
VenkateswaraBabuRavi
 
Data Science and Machine Learning with Tensorflow
 Data Science and Machine Learning with Tensorflow Data Science and Machine Learning with Tensorflow
Data Science and Machine Learning with Tensorflow
Shubham Sharma
 
Intro to machine learning
Intro to machine learningIntro to machine learning
Intro to machine learning
Akshay Kanchan
 
Joseph Jay Williams - WESST - Bridging Research and Practice via MOOClets & C...
Joseph Jay Williams - WESST - Bridging Research and Practice via MOOClets & C...Joseph Jay Williams - WESST - Bridging Research and Practice via MOOClets & C...
Joseph Jay Williams - WESST - Bridging Research and Practice via MOOClets & C...
NUS Institute of Applied Learning Sciences and Educational Technology
 
Characterization
CharacterizationCharacterization
Characterization
Aiswaryadevi Jaganmohan
 

Similar to Introduction to Machine Learning (20)

Lecture 09(introduction to machine learning)
Lecture 09(introduction to machine learning)Lecture 09(introduction to machine learning)
Lecture 09(introduction to machine learning)
 
Introduction to data mining and machine learning
Introduction to data mining and machine learningIntroduction to data mining and machine learning
Introduction to data mining and machine learning
 
Machine Learning for Aerospace Training
Machine Learning for Aerospace TrainingMachine Learning for Aerospace Training
Machine Learning for Aerospace Training
 
Lecture 31
Lecture 31Lecture 31
Lecture 31
 
Introduction to machine learning-2023-IT-AI and DS.pdf
Introduction to machine learning-2023-IT-AI and DS.pdfIntroduction to machine learning-2023-IT-AI and DS.pdf
Introduction to machine learning-2023-IT-AI and DS.pdf
 
Machine Learning ebook.pdf
Machine Learning ebook.pdfMachine Learning ebook.pdf
Machine Learning ebook.pdf
 
1_5_AI_edx_ml_51intro_240204_104838machine learning lecture 1
1_5_AI_edx_ml_51intro_240204_104838machine learning lecture 11_5_AI_edx_ml_51intro_240204_104838machine learning lecture 1
1_5_AI_edx_ml_51intro_240204_104838machine learning lecture 1
 
Launching into machine learning
Launching into machine learningLaunching into machine learning
Launching into machine learning
 
know Machine Learning Basic Concepts.pdf
know Machine Learning Basic Concepts.pdfknow Machine Learning Basic Concepts.pdf
know Machine Learning Basic Concepts.pdf
 
Unit-1.ppt
Unit-1.pptUnit-1.ppt
Unit-1.ppt
 
3.pdf
3.pdf3.pdf
3.pdf
 
Measures of Central tendency
Measures of Central tendencyMeasures of Central tendency
Measures of Central tendency
 
Central Tendancy.pdf
Central Tendancy.pdfCentral Tendancy.pdf
Central Tendancy.pdf
 
1_Introduction.pptx
1_Introduction.pptx1_Introduction.pptx
1_Introduction.pptx
 
Topic_6
Topic_6Topic_6
Topic_6
 
Machine learning ppt unit one syllabuspptx
Machine learning ppt unit one syllabuspptxMachine learning ppt unit one syllabuspptx
Machine learning ppt unit one syllabuspptx
 
Data Science and Machine Learning with Tensorflow
 Data Science and Machine Learning with Tensorflow Data Science and Machine Learning with Tensorflow
Data Science and Machine Learning with Tensorflow
 
Intro to machine learning
Intro to machine learningIntro to machine learning
Intro to machine learning
 
Joseph Jay Williams - WESST - Bridging Research and Practice via MOOClets & C...
Joseph Jay Williams - WESST - Bridging Research and Practice via MOOClets & C...Joseph Jay Williams - WESST - Bridging Research and Practice via MOOClets & C...
Joseph Jay Williams - WESST - Bridging Research and Practice via MOOClets & C...
 
Characterization
CharacterizationCharacterization
Characterization
 

Recently uploaded

一比一原版南十字星大学毕业证(SCU毕业证书)学历如何办理
一比一原版南十字星大学毕业证(SCU毕业证书)学历如何办理一比一原版南十字星大学毕业证(SCU毕业证书)学历如何办理
一比一原版南十字星大学毕业证(SCU毕业证书)学历如何办理
slg6lamcq
 
Experts live - Improving user adoption with AI
Experts live - Improving user adoption with AIExperts live - Improving user adoption with AI
Experts live - Improving user adoption with AI
jitskeb
 
原版一比一爱尔兰都柏林大学毕业证(UCD毕业证书)如何办理
原版一比一爱尔兰都柏林大学毕业证(UCD毕业证书)如何办理 原版一比一爱尔兰都柏林大学毕业证(UCD毕业证书)如何办理
原版一比一爱尔兰都柏林大学毕业证(UCD毕业证书)如何办理
tzu5xla
 
Build applications with generative AI on Google Cloud
Build applications with generative AI on Google CloudBuild applications with generative AI on Google Cloud
Build applications with generative AI on Google Cloud
Márton Kodok
 
一比一原版卡尔加里大学毕业证(uc毕业证)如何办理
一比一原版卡尔加里大学毕业证(uc毕业证)如何办理一比一原版卡尔加里大学毕业证(uc毕业证)如何办理
一比一原版卡尔加里大学毕业证(uc毕业证)如何办理
oaxefes
 
一比一原版(UofT毕业证)多伦多大学毕业证如何办理
一比一原版(UofT毕业证)多伦多大学毕业证如何办理一比一原版(UofT毕业证)多伦多大学毕业证如何办理
一比一原版(UofT毕业证)多伦多大学毕业证如何办理
exukyp
 
Econ3060_Screen Time and Success_ final_GroupProject.pdf
Econ3060_Screen Time and Success_ final_GroupProject.pdfEcon3060_Screen Time and Success_ final_GroupProject.pdf
Econ3060_Screen Time and Success_ final_GroupProject.pdf
blueshagoo1
 
一比一原版澳洲西澳大学毕业证(uwa毕业证书)如何办理
一比一原版澳洲西澳大学毕业证(uwa毕业证书)如何办理一比一原版澳洲西澳大学毕业证(uwa毕业证书)如何办理
一比一原版澳洲西澳大学毕业证(uwa毕业证书)如何办理
aguty
 
一比一原版(uob毕业证书)伯明翰大学毕业证如何办理
一比一原版(uob毕业证书)伯明翰大学毕业证如何办理一比一原版(uob毕业证书)伯明翰大学毕业证如何办理
一比一原版(uob毕业证书)伯明翰大学毕业证如何办理
9gr6pty
 
REUSE-SCHOOL-DATA-INTEGRATED-SYSTEMS.pptx
REUSE-SCHOOL-DATA-INTEGRATED-SYSTEMS.pptxREUSE-SCHOOL-DATA-INTEGRATED-SYSTEMS.pptx
REUSE-SCHOOL-DATA-INTEGRATED-SYSTEMS.pptx
KiriakiENikolaidou
 
Sample Devops SRE Product Companies .pdf
Sample Devops SRE  Product Companies .pdfSample Devops SRE  Product Companies .pdf
Sample Devops SRE Product Companies .pdf
Vineet
 
DATA COMMS-NETWORKS YR2 lecture 08 NAT & CLOUD.docx
DATA COMMS-NETWORKS YR2 lecture 08 NAT & CLOUD.docxDATA COMMS-NETWORKS YR2 lecture 08 NAT & CLOUD.docx
DATA COMMS-NETWORKS YR2 lecture 08 NAT & CLOUD.docx
SaffaIbrahim1
 
一比一原版(UO毕业证)渥太华大学毕业证如何办理
一比一原版(UO毕业证)渥太华大学毕业证如何办理一比一原版(UO毕业证)渥太华大学毕业证如何办理
一比一原版(UO毕业证)渥太华大学毕业证如何办理
bmucuha
 
一比一原版马来西亚博特拉大学毕业证(upm毕业证)如何办理
一比一原版马来西亚博特拉大学毕业证(upm毕业证)如何办理一比一原版马来西亚博特拉大学毕业证(upm毕业证)如何办理
一比一原版马来西亚博特拉大学毕业证(upm毕业证)如何办理
eudsoh
 
Drownings spike from May to August in children
Drownings spike from May to August in childrenDrownings spike from May to August in children
Drownings spike from May to August in children
Bisnar Chase Personal Injury Attorneys
 
一比一原版爱尔兰都柏林大学毕业证(本硕)ucd学位证书如何办理
一比一原版爱尔兰都柏林大学毕业证(本硕)ucd学位证书如何办理一比一原版爱尔兰都柏林大学毕业证(本硕)ucd学位证书如何办理
一比一原版爱尔兰都柏林大学毕业证(本硕)ucd学位证书如何办理
hqfek
 
ML-PPT-UNIT-2 Generative Classifiers Discriminative Classifiers
ML-PPT-UNIT-2 Generative Classifiers Discriminative ClassifiersML-PPT-UNIT-2 Generative Classifiers Discriminative Classifiers
ML-PPT-UNIT-2 Generative Classifiers Discriminative Classifiers
MastanaihnaiduYasam
 
Module 1 ppt BIG DATA ANALYTICS_NOTES FOR MCA
Module 1 ppt BIG DATA ANALYTICS_NOTES FOR MCAModule 1 ppt BIG DATA ANALYTICS_NOTES FOR MCA
Module 1 ppt BIG DATA ANALYTICS_NOTES FOR MCA
yuvarajkumar334
 
How To Control IO Usage using Resource Manager
How To Control IO Usage using Resource ManagerHow To Control IO Usage using Resource Manager
How To Control IO Usage using Resource Manager
Alireza Kamrani
 
一比一原版加拿大麦吉尔大学毕业证(mcgill毕业证书)如何办理
一比一原版加拿大麦吉尔大学毕业证(mcgill毕业证书)如何办理一比一原版加拿大麦吉尔大学毕业证(mcgill毕业证书)如何办理
一比一原版加拿大麦吉尔大学毕业证(mcgill毕业证书)如何办理
agdhot
 

Recently uploaded (20)

一比一原版南十字星大学毕业证(SCU毕业证书)学历如何办理
一比一原版南十字星大学毕业证(SCU毕业证书)学历如何办理一比一原版南十字星大学毕业证(SCU毕业证书)学历如何办理
一比一原版南十字星大学毕业证(SCU毕业证书)学历如何办理
 
Experts live - Improving user adoption with AI
Experts live - Improving user adoption with AIExperts live - Improving user adoption with AI
Experts live - Improving user adoption with AI
 
原版一比一爱尔兰都柏林大学毕业证(UCD毕业证书)如何办理
原版一比一爱尔兰都柏林大学毕业证(UCD毕业证书)如何办理 原版一比一爱尔兰都柏林大学毕业证(UCD毕业证书)如何办理
原版一比一爱尔兰都柏林大学毕业证(UCD毕业证书)如何办理
 
Build applications with generative AI on Google Cloud
Build applications with generative AI on Google CloudBuild applications with generative AI on Google Cloud
Build applications with generative AI on Google Cloud
 
一比一原版卡尔加里大学毕业证(uc毕业证)如何办理
一比一原版卡尔加里大学毕业证(uc毕业证)如何办理一比一原版卡尔加里大学毕业证(uc毕业证)如何办理
一比一原版卡尔加里大学毕业证(uc毕业证)如何办理
 
一比一原版(UofT毕业证)多伦多大学毕业证如何办理
一比一原版(UofT毕业证)多伦多大学毕业证如何办理一比一原版(UofT毕业证)多伦多大学毕业证如何办理
一比一原版(UofT毕业证)多伦多大学毕业证如何办理
 
Econ3060_Screen Time and Success_ final_GroupProject.pdf
Econ3060_Screen Time and Success_ final_GroupProject.pdfEcon3060_Screen Time and Success_ final_GroupProject.pdf
Econ3060_Screen Time and Success_ final_GroupProject.pdf
 
一比一原版澳洲西澳大学毕业证(uwa毕业证书)如何办理
一比一原版澳洲西澳大学毕业证(uwa毕业证书)如何办理一比一原版澳洲西澳大学毕业证(uwa毕业证书)如何办理
一比一原版澳洲西澳大学毕业证(uwa毕业证书)如何办理
 
一比一原版(uob毕业证书)伯明翰大学毕业证如何办理
一比一原版(uob毕业证书)伯明翰大学毕业证如何办理一比一原版(uob毕业证书)伯明翰大学毕业证如何办理
一比一原版(uob毕业证书)伯明翰大学毕业证如何办理
 
REUSE-SCHOOL-DATA-INTEGRATED-SYSTEMS.pptx
REUSE-SCHOOL-DATA-INTEGRATED-SYSTEMS.pptxREUSE-SCHOOL-DATA-INTEGRATED-SYSTEMS.pptx
REUSE-SCHOOL-DATA-INTEGRATED-SYSTEMS.pptx
 
Sample Devops SRE Product Companies .pdf
Sample Devops SRE  Product Companies .pdfSample Devops SRE  Product Companies .pdf
Sample Devops SRE Product Companies .pdf
 
DATA COMMS-NETWORKS YR2 lecture 08 NAT & CLOUD.docx
DATA COMMS-NETWORKS YR2 lecture 08 NAT & CLOUD.docxDATA COMMS-NETWORKS YR2 lecture 08 NAT & CLOUD.docx
DATA COMMS-NETWORKS YR2 lecture 08 NAT & CLOUD.docx
 
一比一原版(UO毕业证)渥太华大学毕业证如何办理
一比一原版(UO毕业证)渥太华大学毕业证如何办理一比一原版(UO毕业证)渥太华大学毕业证如何办理
一比一原版(UO毕业证)渥太华大学毕业证如何办理
 
一比一原版马来西亚博特拉大学毕业证(upm毕业证)如何办理
一比一原版马来西亚博特拉大学毕业证(upm毕业证)如何办理一比一原版马来西亚博特拉大学毕业证(upm毕业证)如何办理
一比一原版马来西亚博特拉大学毕业证(upm毕业证)如何办理
 
Drownings spike from May to August in children
Drownings spike from May to August in childrenDrownings spike from May to August in children
Drownings spike from May to August in children
 
一比一原版爱尔兰都柏林大学毕业证(本硕)ucd学位证书如何办理
一比一原版爱尔兰都柏林大学毕业证(本硕)ucd学位证书如何办理一比一原版爱尔兰都柏林大学毕业证(本硕)ucd学位证书如何办理
一比一原版爱尔兰都柏林大学毕业证(本硕)ucd学位证书如何办理
 
ML-PPT-UNIT-2 Generative Classifiers Discriminative Classifiers
ML-PPT-UNIT-2 Generative Classifiers Discriminative ClassifiersML-PPT-UNIT-2 Generative Classifiers Discriminative Classifiers
ML-PPT-UNIT-2 Generative Classifiers Discriminative Classifiers
 
Module 1 ppt BIG DATA ANALYTICS_NOTES FOR MCA
Module 1 ppt BIG DATA ANALYTICS_NOTES FOR MCAModule 1 ppt BIG DATA ANALYTICS_NOTES FOR MCA
Module 1 ppt BIG DATA ANALYTICS_NOTES FOR MCA
 
How To Control IO Usage using Resource Manager
How To Control IO Usage using Resource ManagerHow To Control IO Usage using Resource Manager
How To Control IO Usage using Resource Manager
 
一比一原版加拿大麦吉尔大学毕业证(mcgill毕业证书)如何办理
一比一原版加拿大麦吉尔大学毕业证(mcgill毕业证书)如何办理一比一原版加拿大麦吉尔大学毕业证(mcgill毕业证书)如何办理
一比一原版加拿大麦吉尔大学毕业证(mcgill毕业证书)如何办理
 

Introduction to Machine Learning

  • 1. Big Data & Analytical Unit (BDAU) Workshop On Machine Learning Introduction to Machine Learning Dr. Mian Asbat Ahmad – 3 March 2016
  • 2. Goals of the presentation • What is Machine Learning • Types of Machine Learning • Supervised Learning • Linear Regression • Logistic Regression • Unsupervised Learning • K-Nearest neighbour • Applications of Machine Learning • Practical
  • 3. What is Machine Learning
  • 4. Machine Learning Definition 1 “Field of study that gives computers the ability to learn without being explicitly programmed”. Arthur Samuel (1959)
  • 5. Machine Learning Definition 2 “A computer program is said to learn from Experience E with respect to some Task T and some Performance measure P, if its performance on T, as measured by P, improves with experience E”. Tom Mitchell (1998) Example of Spam Filter 1. Classifying email as spam or ham (Task T) 2. Watching email for spam or ham (Experience E) 3. The number of emails correctly classified as spam or ham (Performance P) In Machine Learning programs, the Performance P of the program will improve on Task T with Experience E.
  • 6. Terms of Machine Learning • Dataset = Training set • Rows = Training examples (m), m = 14 • Columns = features (n), n = 2 • Input variables/features/predictors/independant (x), x = 1 • Output variable/target variable/Response/dependant (y), y = 1 • (x(i), y(i)) to denote ith training example • (x(14), y(14)) = (44.99, 996) • (xj (i), yj (i)) to denote ith training example of jth feature • (x1 (14), y1 (14)) = (44.99, 996)
  • 8. Main types of Machine Learning
  • 9.
  • 10. Supervised Learning • Labelled data • For example (x1, y1), (x2, y2), (x3, y3), (x4, y4), (x5, y5) • Develop predictive model based on input and output data • Regression is type of Supervised Learning which deals with continuous data • Classification is type of Unsupervised Learning which deals with discrete data Supervised Learning Regression Problem Classification Problem
  • 12. Linear function ŷ = mx + b (simple linear regression) From the figure put the value of m and b ŷ = 3(x) + 2 Predict y when the value of x is 0 ŷ = 3(0) + 2 ŷ = 0 + 2 ŷ = 2 [http://philschatz.com/precalculus-book/contents/m49324.html]
  • 13. Example of Supervised Learning 1 ( Regression problem) To predict the average walking distance of a person per day with BMI 50 (kg/m2) from the given data BMI Average Distance Walked Per Day 42.82 1175 30.11 1600 43.24 905 36.44 1229 52.98 650 37.72 1009 48.44 792 46.44 1015 44.99 996 50.98 594 48.2 1022 63.37 196 55.86 429 52.62 522 32.83 1524 53.41 600 51.19 897 44.19 1058 51.73 479 47.34 936 33.57 1203 39.41 987 46.06 1043 42.42 971 43.94 1157 43.83 844 35.43 1165 61.66 351
  • 14. Example of Supervised Learning 2 ( Regression problem) 100 300 500 700 900 1100 1300 1500 1700 25 35 45 55 65 75 AverageDistanceWalkedPerDay BMI
  • 15. Example of Supervised Learning 3 ( Regression problem) 100 300 500 700 900 1100 1300 1500 1700 25 35 45 55 65 75 AverageDistanceWalkedPerDay BMI
  • 16. Example of Supervised Learning 4 ( Regression problem) 100 300 500 700 900 1100 1300 1500 1700 25 35 45 55 65 75 AverageDistanceWalkedPerDay BMI The answer is 730 m
  • 18. Example of Supervised Learning 1 (Classification Problem) Predict if a cancer of a person with tumour size 4 and age 40 is Benign (B) or Malignant (M) from the given data Tumor Size Age Cancer 4 52 B 9 62 M 2 31 B 6 60 M 3 38 B 8 72 M 5 20 B 4 35 B 6 47 B 8 49 M 7 50 M 5 32 B 8 65 M 5 42 M 3 27 B 4 21 B 3 20 B 7 67 M 6 50 M 9 57 M 7 60 M
  • 19. Example of Supervised Learning 2 (Classification Problem) 0 10 20 30 40 50 60 70 0 1 2 3 4 5 6 7 8 9 10 Age Tumour size
  • 20. Example of Supervised Learning 3 (Classification Problem) 0 10 20 30 40 50 60 70 0 1 2 3 4 5 6 7 8 9 10 Age Tumour size
  • 21. Example of Supervised Learning 4 (Classification Problem) 0 10 20 30 40 50 60 70 0 1 2 3 4 5 6 7 8 9 10 Age Tumour size The answer is Benign
  • 23. Unsupervised Learning • Unlabelled data • For example (x1, x2, x3, x4, x5) • Group and interpret data based only on input data • Find interesting structures in the data Unsupervised Learning Cluterring Problem
  • 24. Example of Unsupervised Learning 1 (Cluster Problem) Predict if a cancer of a person with tumour size 4 and age 40 is Benign (B) or Malignant (M) from the given data. Tumor Size Age 4 52 9 62 2 31 6 60 3 38 8 72 5 20 4 35 6 47 8 49 7 50 5 32 8 65 5 42 3 27 4 21 3 20 7 67 6 50 9 57 7 60
  • 25. Non labelled data 0 10 20 30 40 50 60 70 0 1 2 3 4 5 6 7 8 9 10 Age Tumor size
  • 26. Split in to clusters 0 10 20 30 40 50 60 70 0 1 2 3 4 5 6 7 8 9 10 Age Tumour size
  • 27. Split in to clusters 0 10 20 30 40 50 60 70 0 1 2 3 4 5 6 7 8 9 10 Age Tumour size The answer is Benign
  • 28. K-Means Algorithm Unsupervised Learning 1 [Prof. Andrew NG]
  • 29. K-Means Algorithm Unsupervised Learning 2 • Take two random points on the data when k = 2 [Prof. Andrew NG]
  • 30. K-Means Algorithm Unsupervised Learning 3 • Find distance of each value from the points [Prof. Andrew NG]
  • 31. K-Means Algorithm Unsupervised Learning 4 • Take mean of the distance and move the points there [Prof. Andrew NG]
  • 32. K-Means Algorithm Unsupervised Learning 5 • Find distance of each value from the points [Prof. Andrew NG]
  • 33. K-Means Algorithm Unsupervised Learning 6 • Take mean of the distance and move the points there • The data is divided into two clusters [Prof. Andrew NG]
  • 34. K-Nearest Neighbour (Clustering problem) 0 10 20 30 40 50 60 70 0 1 2 3 4 5 6 7 8 9 10 Age Tumor size
  • 35. K-Nearest Neighbour (Clustering problem) 0 10 20 30 40 50 60 70 0 1 2 3 4 5 6 7 8 9 10 Age Tumor size
  • 36. K-Nearest Neighbour (Clustering problem) 0 10 20 30 40 50 60 70 0 1 2 3 4 5 6 7 8 9 10 Age Tumor size The answer is Malignant
  • 38. Training Machine for detecting faces
  • 40. Training Machine to identify pedestrians [Thomas Serre 2012]
  • 41. Click to play the video
  • 45. Genes Clusters [Su-In Lee, Dana Peer, Aimee Dudley, George Church, Daphne koller]
  • 47. Other applications of Machine Learning • Data Mining / Data Analysis • Hand writing recognition • E.g. Automatic transfer of mail • Natural language processing • Analysis of social media (Twitter, Facebook, LinkedIn etc.) • Credit card legitimate/fraud transaction detection • Speech Recognition • Google Now, Siri, Cortana voice recognition • Recommender System • Movie recommendations (Netflix)
  • 48. Questions / Comments / Feedback bdau@imperial.ac.uk mian.ahmad@imperial.ac.uk