SlideShare a Scribd company logo
Organizing Secretary
Dr.R.Gunavathi,
Head & Associate professor,
PG & Research Department of Computer
Applications
PG & Research Department of Computer Applications
organized
IoT – Applications and Machine Learning
-By Sushama
Assistant Professor (CSE)
JECRC University
“Learning is any process by which a system
improves performance from experience.”
- Herbert Simon
Definition by Tom Mitchell (1998):
Machine Learning is the study of algorithms that
• improve their performance P
• at some task T
• with experience E.
A well-defined learning task is given by <P, T,
E>.
3
Machine
Learning
Computer Output
Computer
Data
Output
Program
4
Data
Program
ML is used when:
• Human expertise does not exist (navigating on Mars)
• Humans can’t explain their expertise (speech
recognition)
• Models must be customized (personalized medicine)
• Models are based on huge amounts of data
(genomics)
Learning isn’t always useful:
• There is no need to “learn” to calculate payroll
5
6
Slide credit: Geoffrey
7
• Recognizing patterns:
– Facial identities or facial expressions
– Handwritten or spoken words
– Medical images
• Generating patterns:
– Generating images or motion sequences
• Recognizing anomalies:
– Unusual credit card transactions
– Unusual patterns of sensor readings in a nuclear
power plant
• Prediction:
– Future stock prices or currency exchange rates
8
• Web search
• Computational
biology
• Finance
• E-commerce
• Space exploration
• Robotics
• Information
extraction
• Social networks
• Debugging software
• [Your favorite area]
“Machine Learning: Field of study that gives
computers the ability to learn without being
explicitly programmed.” -Arthur Samuel
(1959)
9
10
Improve on task T, with respect to
performance metric P, based on experience E
T: Playing checkers
P: Percentage of games won against an arbitrary opponent
E: Playing practice games against itself
T: Recognizing hand-written words
P: Percentage of words correctly classified
E: Database of human-labeled images of handwritten words
T: Driving on four-lane highways using vision sensors
P: Average distance traveled before a human-judged error
E: A sequence of images and steering commands recorded while
observing a human driver.
T: Categorize email messages as spam or legitimate.
P: Percentage of email messages correctly classified.
E: Database of emails, some with human-given labels
11
• Nevada made it legal for
autonomous cars to drive
on roads in June 2011
• As of 2013, four states
(Nevada, Florida, California,
and Michigan) have
legalized autonomous cars
Penn’s Autonomous Car 
(Ben Franklin Racing Team)
12
13
Laser Terrain
Mapping
Stanley
Learning from Human
Drivers
Sebastian
Adaptive
Vision
Pat
h
Plannin
g
Images and movies taken from Sebastian Thrun’smultimedia
w1e4bsite.
15
pixels
edges
object parts
(combination
of edges)
object models
16
17
 Trained on 4 classes
(cars, faces,
motorbikes, airplanes).
 Second layer: Shared-
features and object-
specific features.
 Third layer: More
specific features.
18
[Farabet et al. ICML 2012, PAMI
2013]
19
Input
images
Samples
from
feedforward
Inference
(control)
Samples
from Full
posterior
inference
Generating posterior samples from faces by “filling in”experiments
(cf. Lee and Mumford, 2003). Combine bottom-up and top-down
inference.
Slide credit: Andrew
20
A Typical Speech Recognition
System
ML used to predict of phone states from the sound
spectrogram
Deep learning has state-of-the-art
results
# Hidden Layers 1 2 4 8 10 12
Word Error Rate % 16.0 12.8 11.4 10.9 11.0 11.1
Baseline GMM performance = 15.4%
[Zeiler et al. “On rectified linear units for
speech recognition” ICASSP 2013]
21
Slide credit: Li Deng, MS
22
23
• Supervised (inductive) learning
– Given: training data + desired outputs (labels)
• Unsupervised learning
– Given: training data (without desired outputs)
• Semi-supervised learning
– Given: training data + a few desired outputs
• Reinforcement learning
– Rewards from sequence of actions
24
• Given (x1, y1), (x2, y2), ..., (xn, yn)
• Learn a function f(x) to predict y givenx
– y is real-valued == regression
9
8
7
6
5
4
3
2
1
0
1970 1980 1990 2000 2010 2020
SeptemberArcticSeaIce
Extent(1,000,000sq
km)
26
• Given (x1, y1), (x2, y2), ..., (xn, yn)
• Learn a function f(x) to predict y givenx
– y is categorical == classification
Breast Cancer (Malignant / Benign)
1(Malignant)
0(Benign)
Tumor Size
27
28
• Given (x1, y1), (x2, y2), ..., (xn, yn)
• Learn a function f(x) to predict y givenx
– y is categorical == classification
Breast Cancer (Malignant / Benign)
1(Malignant)
0(Benign)
Tumor Size
Tumor Size
29
• Given (x1, y1), (x2, y2), ..., (xn, yn)
• Learn a function f(x) to predict y given
x
– y is categorical == classification
Breast Cancer (Malignant / Benign)
1(Malignant)
0(Benign)
Tumor Size
Predict Benign Predict Malignant
Tumor Size
Tumor
Size
Ag
e
- Clump Thickness
- Uniformity of Cell Size
- Uniformity of Cell
Shape
…
• x can be multi-dimensional
– Each dimension corresponds to an
attribute
30
• Given x1, x2, ..., xn (without labels)
• Output hidden structure behind the x’s
– E.g., clustering
31
Genes
Individuals
Genomics application: group individuals by genetic
similarity
32
Organize computing clusters Social network analysis
Image credit: NASA/JPL-Caltech/E. Churchwell (Univ. of Wisconsin, Madison)
Astronomical data analysisMarket segmentation
33
34
• Independent component analysis – separate a
combined signal into its original sources
35
• Independent component analysis – separate a
combined signal into its original sources
36
• Given a sequence of states and actions
with (delayed) rewards, output a policy
– Policy is a mapping from states  actions
that tells you what to do in a given state
• Examples:
– Credit assignment problem
– Game playing
– Robot in a maze
– Balance a pole on your hand
37
Agent and environment interact at discrete timesteps
Agent observes state at step t: st S
: t  0, 1, 2, K
produces action at step t : at  A(st )
gets resulting reward :
and resulting next state :
rt1 
st 1
. . . st at
rt +1 st +1
at +1
rt +2 st+2
at +2
rt +3 st +3
. . .
at +3
38
39
• Learn policy from user demonstrations
40
• Choose the training experience
• Choose exactly what is to be learned
– i.e. the target function
• Choose how to represent the target
function
• Choose a learning algorithm to infer the
target function from the experience
Environment/
Experience
Learner
Knowledge
Performance
Element
Training
data
Testing
data
41
• We generally assume that the training and test
examples are independently drawn from the
same overall distribution of data
– We call this “i.i.d” which stands for “independent and
identically distributed”
• If examples are not independent, requires
collective classification
• If test distribution is different, requires
transfer learning
42
• Tens of thousands of machine
learning algorithms
– Hundreds new every year
• Every ML algorithm has three
components:
– Representation
– Optimization
– Evaluation
43
44
• Numerical functions
– Linear regression
– Neural networks
– Support vector machines
• Symbolic functions
– Decision trees
– Rules in propositional logic
– Rules in first-order predicate logic
• Instance-based functions
– Nearest-neighbor
– Case-based
• Probabilistic Graphical Models
– Naïve Bayes
– Bayesian networks
– Hidden-Markov Models (HMMs)
– Probabilistic Context Free Grammars
(PCFGs)
– Markov networks
45
• Gradient descent
– Perceptron
– Backpropagation
• Dynamic Programming
– HMM Learning
– PCFG Learning
• Divide and Conquer
– Decision tree induction
– Rule learning
• Evolutionary Computation
– Genetic Algorithms (GAs)
– Genetic Programming (GP)
– Neuro-evolution
47
• Accuracy
• Precision and recall
• Squared error
• Likelihood
• Posterior probability
• Cost / Utility
• Margin
• Entropy
• K-L divergence etc.
• Understand domain, prior knowledge, and goals
• Data integration, selection, cleaning, pre-
processing, etc.
• Learn models
• Interpret results
• Consolidate and deploy discovered knowledge
Loop
48
49
• Learning can be viewed as using direct or
indirect experience to approximate a chosen
target function.
• Function approximation can be viewed as a
search through a space of hypotheses
(representations of functions) for one that best
fits a set of training data.
• Different learning methods assume different
hypothesis spaces (representation languages)
and/or employ different search techniques.
50
51
• 1950s
– Samuel’s checker player
– Selfridge’s Pandemonium
• 1960s:
– Neural networks: Perceptron
– Pattern recognition
– Learning in the limit theory
– Minsky and Papert prove limitations of Perceptron
• 1970s:
– Symbolic concept induction
– Winston’s arch learner
– Expert systems and the knowledge acquisition
bottleneck
– Quinlan’s ID3
– Michalski’s AQ and soybean diagnosis
– Scientific discovery with BACON
– Mathematical discovery with AM
52
• 1980s:
– Advanced decision tree and rule learning
– Explanation-based Learning (EBL)
– Learning and planning and problem solving
– Utility problem
– Analogy
– Cognitive architectures
– Resurgence of neural networks (connectionism,
backpropagation)
– Valiant’s PAC Learning Theory
– Focus on experimental methodology
• 1990s
– Data mining
– Adaptive software agents and web applications
– Text learning
– Reinforcement learning (RL)
– Inductive Logic Programming (ILP)
– Ensembles: Bagging, Boosting, and Stacking
– Bayes Net learning
53
• 2000s
– Support vector machines & kernel methods
– Graphical models
– Statistical relational learning
– Transfer learning
– Sequence labeling
– Collective classification and structured outputs
– Computer Systems Applications (Compilers, Debugging, Graphics, Security)
– E-mail management
– Personalized assistants that learn
– Learning in robotics and vision
• 2010s
– Deep learning systems
– Learning for big data
– Bayesian methods
– Multi-task & lifelong learning
– Applications to vision, speech, social networks, learning to read, etc.
– ???
54
• Supervised learning
– Decision tree induction
– Linear regression
– Logistic regression
– Support vector
machines & kernel
methods
– Model ensembles
– Bayesian learning
– Neural networks &
deep learning
– Learning theory
• Unsupervised
learning
– Clustering
– Dimensionality
reduction
• Reinforcement
learning
– Temporal
difference
learning
– Q learning
• Evaluation
• Applications
Launching into machine learning
Launching into machine learning

More Related Content

What's hot

Machine learning Introduction
Machine learning IntroductionMachine learning Introduction
Machine learning Introduction
Dong Guo
 
This is a heavily data-oriented
This is a heavily data-orientedThis is a heavily data-oriented
This is a heavily data-oriented
butest
 
introducción a Machine Learning
introducción a Machine Learningintroducción a Machine Learning
introducción a Machine Learning
butest
 
2.17Mb ppt
2.17Mb ppt2.17Mb ppt
2.17Mb ppt
butest
 
Lecture #1: Introduction to machine learning (ML)
Lecture #1: Introduction to machine learning (ML)Lecture #1: Introduction to machine learning (ML)
Lecture #1: Introduction to machine learning (ML)
butest
 
MultiC2: an Optimization Framework for Learning from Task and Worker Dual Het...
MultiC2: an Optimization Framework for Learning from Task and Worker Dual Het...MultiC2: an Optimization Framework for Learning from Task and Worker Dual Het...
MultiC2: an Optimization Framework for Learning from Task and Worker Dual Het...
collwe
 

What's hot (20)

Introduction to machine learning and model building using linear regression
Introduction to machine learning and model building using linear regressionIntroduction to machine learning and model building using linear regression
Introduction to machine learning and model building using linear regression
 
Machine learning Introduction
Machine learning IntroductionMachine learning Introduction
Machine learning Introduction
 
This is a heavily data-oriented
This is a heavily data-orientedThis is a heavily data-oriented
This is a heavily data-oriented
 
introducción a Machine Learning
introducción a Machine Learningintroducción a Machine Learning
introducción a Machine Learning
 
Machine Can Think
Machine Can ThinkMachine Can Think
Machine Can Think
 
Intro to machine learning(with animations)
Intro to machine learning(with animations)Intro to machine learning(with animations)
Intro to machine learning(with animations)
 
Machine learning
Machine learningMachine learning
Machine learning
 
2.17Mb ppt
2.17Mb ppt2.17Mb ppt
2.17Mb ppt
 
Interpretability of machine learning
Interpretability of machine learningInterpretability of machine learning
Interpretability of machine learning
 
Lecture #1: Introduction to machine learning (ML)
Lecture #1: Introduction to machine learning (ML)Lecture #1: Introduction to machine learning (ML)
Lecture #1: Introduction to machine learning (ML)
 
DEFENSE
DEFENSEDEFENSE
DEFENSE
 
Introduction into machine learning
Introduction into machine learningIntroduction into machine learning
Introduction into machine learning
 
Introduction to Machine Learning
Introduction to Machine LearningIntroduction to Machine Learning
Introduction to Machine Learning
 
Machine learning
Machine learningMachine learning
Machine learning
 
How machines can take decisions
How machines can take decisionsHow machines can take decisions
How machines can take decisions
 
Introduction to Machine Learning
Introduction to Machine LearningIntroduction to Machine Learning
Introduction to Machine Learning
 
Lecture 1.pptx
Lecture 1.pptxLecture 1.pptx
Lecture 1.pptx
 
MultiC2: an Optimization Framework for Learning from Task and Worker Dual Het...
MultiC2: an Optimization Framework for Learning from Task and Worker Dual Het...MultiC2: an Optimization Framework for Learning from Task and Worker Dual Het...
MultiC2: an Optimization Framework for Learning from Task and Worker Dual Het...
 
Machine Learning and its Applications
Machine Learning and its ApplicationsMachine Learning and its Applications
Machine Learning and its Applications
 
Introduction to machine learning
Introduction to machine learningIntroduction to machine learning
Introduction to machine learning
 

Similar to Launching into machine learning

01_introduction.pdfbnmelllleitrthnjjjkkk
01_introduction.pdfbnmelllleitrthnjjjkkk01_introduction.pdfbnmelllleitrthnjjjkkk
01_introduction.pdfbnmelllleitrthnjjjkkk
JesusTekonbo
 
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
 

Similar to Launching into machine learning (20)

ppt on introduction to Machine learning tools
ppt on introduction to Machine learning toolsppt on introduction to Machine learning tools
ppt on introduction to Machine learning tools
 
INTRO TO ML.pptx
INTRO TO ML.pptxINTRO TO ML.pptx
INTRO TO ML.pptx
 
Machine learning
Machine learningMachine learning
Machine learning
 
Machine Learning GDSC DCE Darbhanga.pptx
Machine Learning GDSC DCE Darbhanga.pptxMachine Learning GDSC DCE Darbhanga.pptx
Machine Learning GDSC DCE Darbhanga.pptx
 
01_introduction.pdfbnmelllleitrthnjjjkkk
01_introduction.pdfbnmelllleitrthnjjjkkk01_introduction.pdfbnmelllleitrthnjjjkkk
01_introduction.pdfbnmelllleitrthnjjjkkk
 
L 8 introduction to machine learning final kirti.pptx
L 8 introduction to machine learning final kirti.pptxL 8 introduction to machine learning final kirti.pptx
L 8 introduction to machine learning final kirti.pptx
 
01_introduction_ML.pdf
01_introduction_ML.pdf01_introduction_ML.pdf
01_introduction_ML.pdf
 
1_Introduction.pptx
1_Introduction.pptx1_Introduction.pptx
1_Introduction.pptx
 
know Machine Learning Basic Concepts.pdf
know Machine Learning Basic Concepts.pdfknow Machine Learning Basic Concepts.pdf
know Machine Learning Basic Concepts.pdf
 
Week 1.pdf
Week 1.pdfWeek 1.pdf
Week 1.pdf
 
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
 
ML
MLML
ML
 
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
 
module 6 (1).ppt
module 6 (1).pptmodule 6 (1).ppt
module 6 (1).ppt
 
Pattern recognition and Machine Learning.
Pattern recognition and Machine Learning.Pattern recognition and Machine Learning.
Pattern recognition and Machine Learning.
 
Fundementals of Machine Learning and Deep Learning
Fundementals of Machine Learning and Deep Learning Fundementals of Machine Learning and Deep Learning
Fundementals of Machine Learning and Deep Learning
 
Machine learning ppt unit one syllabuspptx
Machine learning ppt unit one syllabuspptxMachine learning ppt unit one syllabuspptx
Machine learning ppt unit one syllabuspptx
 
Intro to machine learning
Intro to machine learningIntro to machine learning
Intro to machine learning
 
Rahul_Kirtoniya_11800121032_CSE_Machine_Learning.pptx
Rahul_Kirtoniya_11800121032_CSE_Machine_Learning.pptxRahul_Kirtoniya_11800121032_CSE_Machine_Learning.pptx
Rahul_Kirtoniya_11800121032_CSE_Machine_Learning.pptx
 

More from Dr.R. Gunavathi Ramasamy (9)

Iot transforming the future of agriculture
Iot transforming the future of agricultureIot transforming the future of agriculture
Iot transforming the future of agriculture
 
Machine learningfor computervision_ashutoshupadhyay
Machine learningfor computervision_ashutoshupadhyayMachine learningfor computervision_ashutoshupadhyay
Machine learningfor computervision_ashutoshupadhyay
 
Iot
IotIot
Iot
 
Io t with biometrics
Io t with biometricsIo t with biometrics
Io t with biometrics
 
Iot trends and technologies development in terms of Machine Learning
Iot trends and technologies development in terms of Machine LearningIot trends and technologies development in terms of Machine Learning
Iot trends and technologies development in terms of Machine Learning
 
Blockchain overview
Blockchain overviewBlockchain overview
Blockchain overview
 
Artificial Intelligence and Expert System
Artificial Intelligence  and Expert SystemArtificial Intelligence  and Expert System
Artificial Intelligence and Expert System
 
The big 3
The big 3 The big 3
The big 3
 
The big 3
The big 3 The big 3
The big 3
 

Recently uploaded

678020731-Sumas-y-Restas-Para-Colorear.pdf
678020731-Sumas-y-Restas-Para-Colorear.pdf678020731-Sumas-y-Restas-Para-Colorear.pdf
678020731-Sumas-y-Restas-Para-Colorear.pdf
CarlosHernanMontoyab2
 
Additional Benefits for Employee Website.pdf
Additional Benefits for Employee Website.pdfAdditional Benefits for Employee Website.pdf
Additional Benefits for Employee Website.pdf
joachimlavalley1
 
Accounting and finance exit exam 2016 E.C.pdf
Accounting and finance exit exam 2016 E.C.pdfAccounting and finance exit exam 2016 E.C.pdf
Accounting and finance exit exam 2016 E.C.pdf
YibeltalNibretu
 

Recently uploaded (20)

Welcome to TechSoup New Member Orientation and Q&A (May 2024).pdf
Welcome to TechSoup   New Member Orientation and Q&A (May 2024).pdfWelcome to TechSoup   New Member Orientation and Q&A (May 2024).pdf
Welcome to TechSoup New Member Orientation and Q&A (May 2024).pdf
 
678020731-Sumas-y-Restas-Para-Colorear.pdf
678020731-Sumas-y-Restas-Para-Colorear.pdf678020731-Sumas-y-Restas-Para-Colorear.pdf
678020731-Sumas-y-Restas-Para-Colorear.pdf
 
Basic Civil Engineering Notes of Chapter-6, Topic- Ecosystem, Biodiversity G...
Basic Civil Engineering Notes of Chapter-6,  Topic- Ecosystem, Biodiversity G...Basic Civil Engineering Notes of Chapter-6,  Topic- Ecosystem, Biodiversity G...
Basic Civil Engineering Notes of Chapter-6, Topic- Ecosystem, Biodiversity G...
 
The approach at University of Liverpool.pptx
The approach at University of Liverpool.pptxThe approach at University of Liverpool.pptx
The approach at University of Liverpool.pptx
 
Sectors of the Indian Economy - Class 10 Study Notes pdf
Sectors of the Indian Economy - Class 10 Study Notes pdfSectors of the Indian Economy - Class 10 Study Notes pdf
Sectors of the Indian Economy - Class 10 Study Notes pdf
 
Additional Benefits for Employee Website.pdf
Additional Benefits for Employee Website.pdfAdditional Benefits for Employee Website.pdf
Additional Benefits for Employee Website.pdf
 
Chapter 3 - Islamic Banking Products and Services.pptx
Chapter 3 - Islamic Banking Products and Services.pptxChapter 3 - Islamic Banking Products and Services.pptx
Chapter 3 - Islamic Banking Products and Services.pptx
 
Accounting and finance exit exam 2016 E.C.pdf
Accounting and finance exit exam 2016 E.C.pdfAccounting and finance exit exam 2016 E.C.pdf
Accounting and finance exit exam 2016 E.C.pdf
 
Home assignment II on Spectroscopy 2024 Answers.pdf
Home assignment II on Spectroscopy 2024 Answers.pdfHome assignment II on Spectroscopy 2024 Answers.pdf
Home assignment II on Spectroscopy 2024 Answers.pdf
 
1.4 modern child centered education - mahatma gandhi-2.pptx
1.4 modern child centered education - mahatma gandhi-2.pptx1.4 modern child centered education - mahatma gandhi-2.pptx
1.4 modern child centered education - mahatma gandhi-2.pptx
 
Students, digital devices and success - Andreas Schleicher - 27 May 2024..pptx
Students, digital devices and success - Andreas Schleicher - 27 May 2024..pptxStudents, digital devices and success - Andreas Schleicher - 27 May 2024..pptx
Students, digital devices and success - Andreas Schleicher - 27 May 2024..pptx
 
UNIT – IV_PCI Complaints: Complaints and evaluation of complaints, Handling o...
UNIT – IV_PCI Complaints: Complaints and evaluation of complaints, Handling o...UNIT – IV_PCI Complaints: Complaints and evaluation of complaints, Handling o...
UNIT – IV_PCI Complaints: Complaints and evaluation of complaints, Handling o...
 
Embracing GenAI - A Strategic Imperative
Embracing GenAI - A Strategic ImperativeEmbracing GenAI - A Strategic Imperative
Embracing GenAI - A Strategic Imperative
 
How to Break the cycle of negative Thoughts
How to Break the cycle of negative ThoughtsHow to Break the cycle of negative Thoughts
How to Break the cycle of negative Thoughts
 
NLC-2024-Orientation-for-RO-SDO (1).pptx
NLC-2024-Orientation-for-RO-SDO (1).pptxNLC-2024-Orientation-for-RO-SDO (1).pptx
NLC-2024-Orientation-for-RO-SDO (1).pptx
 
Basic_QTL_Marker-assisted_Selection_Sourabh.ppt
Basic_QTL_Marker-assisted_Selection_Sourabh.pptBasic_QTL_Marker-assisted_Selection_Sourabh.ppt
Basic_QTL_Marker-assisted_Selection_Sourabh.ppt
 
Sha'Carri Richardson Presentation 202345
Sha'Carri Richardson Presentation 202345Sha'Carri Richardson Presentation 202345
Sha'Carri Richardson Presentation 202345
 
Matatag-Curriculum and the 21st Century Skills Presentation.pptx
Matatag-Curriculum and the 21st Century Skills Presentation.pptxMatatag-Curriculum and the 21st Century Skills Presentation.pptx
Matatag-Curriculum and the 21st Century Skills Presentation.pptx
 
Palestine last event orientationfvgnh .pptx
Palestine last event orientationfvgnh .pptxPalestine last event orientationfvgnh .pptx
Palestine last event orientationfvgnh .pptx
 
Instructions for Submissions thorugh G- Classroom.pptx
Instructions for Submissions thorugh G- Classroom.pptxInstructions for Submissions thorugh G- Classroom.pptx
Instructions for Submissions thorugh G- Classroom.pptx
 

Launching into machine learning

  • 1. Organizing Secretary Dr.R.Gunavathi, Head & Associate professor, PG & Research Department of Computer Applications PG & Research Department of Computer Applications organized IoT – Applications and Machine Learning
  • 2. -By Sushama Assistant Professor (CSE) JECRC University
  • 3. “Learning is any process by which a system improves performance from experience.” - Herbert Simon Definition by Tom Mitchell (1998): Machine Learning is the study of algorithms that • improve their performance P • at some task T • with experience E. A well-defined learning task is given by <P, T, E>. 3
  • 5. ML is used when: • Human expertise does not exist (navigating on Mars) • Humans can’t explain their expertise (speech recognition) • Models must be customized (personalized medicine) • Models are based on huge amounts of data (genomics) Learning isn’t always useful: • There is no need to “learn” to calculate payroll 5
  • 7. 7 • Recognizing patterns: – Facial identities or facial expressions – Handwritten or spoken words – Medical images • Generating patterns: – Generating images or motion sequences • Recognizing anomalies: – Unusual credit card transactions – Unusual patterns of sensor readings in a nuclear power plant • Prediction: – Future stock prices or currency exchange rates
  • 8. 8 • Web search • Computational biology • Finance • E-commerce • Space exploration • Robotics • Information extraction • Social networks • Debugging software • [Your favorite area]
  • 9. “Machine Learning: Field of study that gives computers the ability to learn without being explicitly programmed.” -Arthur Samuel (1959) 9
  • 10. 10 Improve on task T, with respect to performance metric P, based on experience E T: Playing checkers P: Percentage of games won against an arbitrary opponent E: Playing practice games against itself T: Recognizing hand-written words P: Percentage of words correctly classified E: Database of human-labeled images of handwritten words T: Driving on four-lane highways using vision sensors P: Average distance traveled before a human-judged error E: A sequence of images and steering commands recorded while observing a human driver. T: Categorize email messages as spam or legitimate. P: Percentage of email messages correctly classified. E: Database of emails, some with human-given labels
  • 11. 11
  • 12. • Nevada made it legal for autonomous cars to drive on roads in June 2011 • As of 2013, four states (Nevada, Florida, California, and Michigan) have legalized autonomous cars Penn’s Autonomous Car  (Ben Franklin Racing Team) 12
  • 13. 13
  • 14. Laser Terrain Mapping Stanley Learning from Human Drivers Sebastian Adaptive Vision Pat h Plannin g Images and movies taken from Sebastian Thrun’smultimedia w1e4bsite.
  • 15. 15
  • 17. 17
  • 18.  Trained on 4 classes (cars, faces, motorbikes, airplanes).  Second layer: Shared- features and object- specific features.  Third layer: More specific features. 18
  • 19. [Farabet et al. ICML 2012, PAMI 2013] 19
  • 20. Input images Samples from feedforward Inference (control) Samples from Full posterior inference Generating posterior samples from faces by “filling in”experiments (cf. Lee and Mumford, 2003). Combine bottom-up and top-down inference. Slide credit: Andrew 20
  • 21. A Typical Speech Recognition System ML used to predict of phone states from the sound spectrogram Deep learning has state-of-the-art results # Hidden Layers 1 2 4 8 10 12 Word Error Rate % 16.0 12.8 11.4 10.9 11.0 11.1 Baseline GMM performance = 15.4% [Zeiler et al. “On rectified linear units for speech recognition” ICASSP 2013] 21
  • 22. Slide credit: Li Deng, MS 22
  • 23. 23
  • 24. • Supervised (inductive) learning – Given: training data + desired outputs (labels) • Unsupervised learning – Given: training data (without desired outputs) • Semi-supervised learning – Given: training data + a few desired outputs • Reinforcement learning – Rewards from sequence of actions 24
  • 25. • Given (x1, y1), (x2, y2), ..., (xn, yn) • Learn a function f(x) to predict y givenx – y is real-valued == regression 9 8 7 6 5 4 3 2 1 0 1970 1980 1990 2000 2010 2020 SeptemberArcticSeaIce Extent(1,000,000sq km) 26
  • 26. • Given (x1, y1), (x2, y2), ..., (xn, yn) • Learn a function f(x) to predict y givenx – y is categorical == classification Breast Cancer (Malignant / Benign) 1(Malignant) 0(Benign) Tumor Size 27
  • 27. 28 • Given (x1, y1), (x2, y2), ..., (xn, yn) • Learn a function f(x) to predict y givenx – y is categorical == classification Breast Cancer (Malignant / Benign) 1(Malignant) 0(Benign) Tumor Size Tumor Size
  • 28. 29 • Given (x1, y1), (x2, y2), ..., (xn, yn) • Learn a function f(x) to predict y given x – y is categorical == classification Breast Cancer (Malignant / Benign) 1(Malignant) 0(Benign) Tumor Size Predict Benign Predict Malignant Tumor Size
  • 29. Tumor Size Ag e - Clump Thickness - Uniformity of Cell Size - Uniformity of Cell Shape … • x can be multi-dimensional – Each dimension corresponds to an attribute 30
  • 30. • Given x1, x2, ..., xn (without labels) • Output hidden structure behind the x’s – E.g., clustering 31
  • 31. Genes Individuals Genomics application: group individuals by genetic similarity 32
  • 32. Organize computing clusters Social network analysis Image credit: NASA/JPL-Caltech/E. Churchwell (Univ. of Wisconsin, Madison) Astronomical data analysisMarket segmentation 33
  • 33. 34 • Independent component analysis – separate a combined signal into its original sources
  • 34. 35 • Independent component analysis – separate a combined signal into its original sources
  • 35. 36 • Given a sequence of states and actions with (delayed) rewards, output a policy – Policy is a mapping from states  actions that tells you what to do in a given state • Examples: – Credit assignment problem – Game playing – Robot in a maze – Balance a pole on your hand
  • 36. 37 Agent and environment interact at discrete timesteps Agent observes state at step t: st S : t  0, 1, 2, K produces action at step t : at  A(st ) gets resulting reward : and resulting next state : rt1  st 1 . . . st at rt +1 st +1 at +1 rt +2 st+2 at +2 rt +3 st +3 . . . at +3
  • 37. 38
  • 38. 39 • Learn policy from user demonstrations
  • 39. 40
  • 40. • Choose the training experience • Choose exactly what is to be learned – i.e. the target function • Choose how to represent the target function • Choose a learning algorithm to infer the target function from the experience Environment/ Experience Learner Knowledge Performance Element Training data Testing data 41
  • 41. • We generally assume that the training and test examples are independently drawn from the same overall distribution of data – We call this “i.i.d” which stands for “independent and identically distributed” • If examples are not independent, requires collective classification • If test distribution is different, requires transfer learning 42
  • 42. • Tens of thousands of machine learning algorithms – Hundreds new every year • Every ML algorithm has three components: – Representation – Optimization – Evaluation 43
  • 43. 44 • Numerical functions – Linear regression – Neural networks – Support vector machines • Symbolic functions – Decision trees – Rules in propositional logic – Rules in first-order predicate logic • Instance-based functions – Nearest-neighbor – Case-based • Probabilistic Graphical Models – Naïve Bayes – Bayesian networks – Hidden-Markov Models (HMMs) – Probabilistic Context Free Grammars (PCFGs) – Markov networks
  • 44. 45 • Gradient descent – Perceptron – Backpropagation • Dynamic Programming – HMM Learning – PCFG Learning • Divide and Conquer – Decision tree induction – Rule learning • Evolutionary Computation – Genetic Algorithms (GAs) – Genetic Programming (GP) – Neuro-evolution
  • 45. 47 • Accuracy • Precision and recall • Squared error • Likelihood • Posterior probability • Cost / Utility • Margin • Entropy • K-L divergence etc.
  • 46. • Understand domain, prior knowledge, and goals • Data integration, selection, cleaning, pre- processing, etc. • Learn models • Interpret results • Consolidate and deploy discovered knowledge Loop 48
  • 47. 49 • Learning can be viewed as using direct or indirect experience to approximate a chosen target function. • Function approximation can be viewed as a search through a space of hypotheses (representations of functions) for one that best fits a set of training data. • Different learning methods assume different hypothesis spaces (representation languages) and/or employ different search techniques.
  • 48. 50
  • 49. 51 • 1950s – Samuel’s checker player – Selfridge’s Pandemonium • 1960s: – Neural networks: Perceptron – Pattern recognition – Learning in the limit theory – Minsky and Papert prove limitations of Perceptron • 1970s: – Symbolic concept induction – Winston’s arch learner – Expert systems and the knowledge acquisition bottleneck – Quinlan’s ID3 – Michalski’s AQ and soybean diagnosis – Scientific discovery with BACON – Mathematical discovery with AM
  • 50. 52 • 1980s: – Advanced decision tree and rule learning – Explanation-based Learning (EBL) – Learning and planning and problem solving – Utility problem – Analogy – Cognitive architectures – Resurgence of neural networks (connectionism, backpropagation) – Valiant’s PAC Learning Theory – Focus on experimental methodology • 1990s – Data mining – Adaptive software agents and web applications – Text learning – Reinforcement learning (RL) – Inductive Logic Programming (ILP) – Ensembles: Bagging, Boosting, and Stacking – Bayes Net learning
  • 51. 53 • 2000s – Support vector machines & kernel methods – Graphical models – Statistical relational learning – Transfer learning – Sequence labeling – Collective classification and structured outputs – Computer Systems Applications (Compilers, Debugging, Graphics, Security) – E-mail management – Personalized assistants that learn – Learning in robotics and vision • 2010s – Deep learning systems – Learning for big data – Bayesian methods – Multi-task & lifelong learning – Applications to vision, speech, social networks, learning to read, etc. – ???
  • 52. 54 • Supervised learning – Decision tree induction – Linear regression – Logistic regression – Support vector machines & kernel methods – Model ensembles – Bayesian learning – Neural networks & deep learning – Learning theory • Unsupervised learning – Clustering – Dimensionality reduction • Reinforcement learning – Temporal difference learning – Q learning • Evaluation • Applications