Introduction to

Machine Learning
Instructor:
Da Budz

1
Robot Image Credit: Viktoriya Sukhanova © 123RF.com
 What is Machine Learning?
“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>.
 Traditional Programming

Data
Computer Output
Program

Machine Learning

Data
Computer Program
Output

4
Slide credit: Pedro Domingos
 When Do We Use Machine Learning?
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
Based on slide by E. Alpaydin
 A classic example of a task that requires machine learning:
It is very hard to say what makes a 2

6
Slide credit: Geoffrey Hinton
 Some more examples of tasks that are best
solved by using a learning algorithm
• 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
7
Slide credit: Geoffrey Hinton
 Sample Applications
• Web search
• Computational biology
• Finance
• E-commerce
• Space exploration
• Robotics
• Information extraction
• Social networks
• Debugging software
• [Your favorite area]

8
Slide credit: Pedro Domingos
 Samuel’s Checkers-Player
“Machine Learning: Field of study that gives
computers the ability to learn without being
explicitly programmed.” -Arthur Samuel (1959)

9
 Defining the Learning Task
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. 10

Slide credit: RayP:Mooney
Percentage of email messages correctly classified.
State of the Art Applications of
Machine Learning

11
 Autonomous Cars

• 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
12
Car 
Autonomous Car Sensors

13
 Autonomous Car Technology
Path
Planning

Laser Terrain Mapping

Learning from Human Drivers

Adaptive Vision

Sebastian

Stanle
y

Images and movies taken from Sebastian Thrun’s multimedia w1e4bsite.

Deep Learning in the Headlines

15
 Deep Belief Net on Face Images
object
models

object
parts
(combinati
on of
edges)

edge
s

pixel
Based on materials s 16
by Andrew Ng
 Learning of Object Parts

17
Slide credit: Andrew Ng
 Training on Multiple Objects

Trained on 4 classes (cars, faces,

motorbikes, airplanes).
Second layer: Shared-features
and object-specific features.
Third layer: More specific
features.

18
Slide credit: Andrew Ng
 Scene Labeling via Deep Learning

[Farabet et al. ICML 2012, PAMI 2013] 19

 Inference from Deep Learned Models
Generating posterior samples from faces by “filling in” experiments
(cf. Lee and Mumford, 2003). Combine bottom-up and top-down inference.

Input images

Samples from
feedforward
Inference
(control)

Samples from
Full posterior
inference

20
Slide credit: Andrew Ng
 Machine Learning in
Automatic Speech Recognition
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]
2
1
 Impact of Deep Learning in Speech Technology

22
Slide credit: Li Deng, MS Research
Types of Learning

23
 Types of Learning

• 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
Based on slide by Pedro Domingos
 Supervised Learning: Regression
• Given (x1, y1), (x2, y2), ..., (xn, yn)
• Learn a function f(x) to predict y given
x
– y is real-valued
9 == regression
8
September Arctic Sea Ice Extent

7
(1,000,000 sq km)

6
5
4
3
2
1
0
1970 1990 2000 2010 2020
1980 Year
26
Data from G. Witt. Journal of Statistics Education, Volume 21,
 Supervised Learning: Classification
• 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

27
Based on example by Andrew Ng
 Supervised Learning: Classification
• 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

Based on example by Andrew Ng

Tumor Size 28
 Supervised Learning: Classification
• 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
(
M
a Tumor Size
l
i Predict Benign Predict Malignant

g
Based on example by Andrew Ng
n Tumor Size 29
 Supervised Learning
• x can be multi-dimensional
– Each dimension corresponds to an attribute

- Clump Thickness
- Uniformity of Cell Size
Age - Uniformity of Cell Shape
…

Tumor Size

30
Based on example by Andrew Ng
 Unsupervised Learning
• Given x1 , x2 , ..., xn (without labels)
• Output hidden structure behind the x’s
– E.g., clustering

31
 Unsupervised Learning
Genomics application: group individuals by genetic similarity
Genes

Individuals 32
[Source: Daphne Koller]
 Unsupervised Learning

Organize computing clusters Social network analysis

Image credit: NASA/JPL-Caltech/E. Churchwell (Univ. of Wisconsin, Madison)

Market segmentation Astronomical data analysis 33

Slide credit: Andrew Ng
 Unsupervised Learning
• Independent component analysis – separate a
combined signal into its original sources

34
Image credit: statsoft.com Audio from http://www.ism.ac.jp/~shiro/research/blindsep.html
 Unsupervised Learning
• Independent component analysis – separate a
combined signal into its original sources

35
Image credit: statsoft.com Audio from http://www.ism.ac.jp/~shiro/research/blindsep.html
 Reinforcement Learning
• 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
 The Agent-Environment Interface

Agent and environment interact at discrete time : t  0, 1, 2,

steps Agent observes state at step t: K
t S
sproduces action at step t : at 
A(st )resulting reward : rt 1 
gets
and resulting next
st 1
state :
... st rt +1 rt +2 s rt +3 ...
at st +1 t +2 st +3
at +1 at +2 at +3
37
Slide credit: Sutton & Barto
 Reinforcement Learning

https://www.youtube.com/watch?v=4cgWya-wjgY 38
 Inverse Reinforcement Learning
• Learn policy from user demonstrations

Stanford Autonomous Helicopter

http://heli.stanford.edu/ https://
www.youtube.com/watch?v=VCdxqn0fcnE
39
Framing a Learning Problem

40
 Designing a Learning System
• 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

Training data Learner

Environment/
Experience Knowledge

Testing data
Performance
Element 41
Based on slide by Ray Mooney
 Training vs. Test Distribution
• 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
Slide credit: Ray Mooney
 ML in a Nutshell
• Tens of thousands of machine learning
algorithms
– Hundreds new every year

• Every ML algorithm has three

components:
– Representation
– Optimization
– Evaluation

43
Slide credit: Pedro Domingos
 Various Function Representations
• 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
Slide credit: Ray Mooney
 Various Search/Optimization
Algorithms
• 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
Slide credit: Ray Mooney
 Evaluation
• Accuracy
• Precision and recall
• Squared error
• Likelihood
• Posterior probability
• Cost / Utility
• Margin
• Entropy
• K-L divergence
• etc.

47
Slide credit: Pedro Domingos
 ML in Practice
• Understand domain, prior knowledge, and goals
• Data integration, selection, cleaning, pre-processing, etc.
Loop • Learn models
• Interpret results
• Consolidate and deploy discovered knowledge

48
Based on a slide by Pedro Domingos
 Lessons Learned about Learning
• 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.

49
Slide credit: Ray Mooney
A Brief History of
Machine Learning

50
 History of Machine Learning
• 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

51
Slide credit: Ray Mooney
 History of Machine Learning (cont.)
• 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
52
Slide credit: Ray Mooney
 History of Machine Learning (cont.)
• 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.
– ???
53
Based on slide by Ray Mooney
 What We’ll Cover in this Course
• Supervised learning • Unsupervised learning
– Decision tree induction – Clustering
– Linear regression – Dimensionality reduction
– Logistic regression • Reinforcement learning
– Support vector machines – Temporal difference
& kernel methods learning
– Model ensembles – Q learning
– Bayesian learning • Evaluation
– Neural networks & deep
learning • Applications
– Learning theory

Our focus will be on applying machine learning to real applications

54