Download Bayesian Decision Theory

Survey
yes no Was this document useful for you?
   Thank you for your participation!

* Your assessment is very important for improving the workof artificial intelligence, which forms the content of this project

Document related concepts
no text concepts found
Transcript
Introduction to Machine Learning
Yazd University, Electrical and Computer Engineering
Department
Course Title: Advanced Software Engineering
By: Mohammad Ali Zare Chahooki
1
Why “Learn” ?
 Machine learning is programming computers to …
optimize a performance criterion using …
example data or past experience.
 There is no
need to “learn” to calculate payroll
 Learning is used when:
 Human expertise does not exist (navigating on Mars),
 Humans are unable to explain their expertise (speech
recognition)
 Solution changes in time (routing on a computer network)
 Solution needs to be adapted to particular cases (user
biometrics)
2
In “Learning” …
 Learning
general models from a data of
particular examples
 Data is cheap and abundant (data warehouses); knowledge is
expensive and scarce.
 Example in retail …
People who bought “DaVinci Code” also bought “The Five PeopleYou Meet
in Heaven” (www.amazon.com)
 Build a model that is a good and useful approximation
to the data.
3
What is Machine Learning?
 Optimize a performance criterion using example data or past
experience.
 Role of Statistics: Inference from a sample
 Role of Computer science: Efficient algorithms to
 Solve the optimization problem
 Representing and evaluating the model for inference
4
Applications
 Learning Associations
 Supervised Learning
 Classification
 Regression
 Unsupervised Learning
 Reinforcement Learning
5
Learning Associations
 Basket analysis:
P (Y | X ) probability that somebody who buys X also buys Y
where X and Y are products/services.
Example: P ( chips | delester) = 0.7
6
Classification
 Example: Credit
scoring
 Differentiating between
low-risk and high-risk
customers from their
income and savings
7
Discriminant: IF income > θ1 AND savings > θ2
THEN low-risk ELSE high-risk
Classification: Applications
 Face recognition: Pose, lighting, occlusion (glasses, beard),
make-up, hair style
 Character recognition: Different handwriting styles.
 Speech recognition: Temporal dependency.
 Use of a dictionary or the syntax of the language.
 Sensor fusion: Combine multiple modalities; eg, visual (lip
image) and acoustic for speech
 Medical diagnosis: From symptoms to illnesses
 ...
8
Face Recognition
Training examples of a person
Test images
AT&T Laboratories, Cambridge UK
http://www.uk.research.att.com/facedatabase.html
9
Regression
 Example: Price of a used car
 x : car attributes
y : price
y = g (x | θ )
g ( ) model,
θ parameters
10
y = wx+w0
Regression Applications
 Navigating a car: Angle of the steering wheel (CMU NavLab)
 Kinematics of a robot arm
(x,y)
α2
α1
11
α1= g1(x,y)
α2= g2(x,y)
Supervised Learning: Uses
 Prediction of future cases: Use the rule to predict the output
for future inputs
 Knowledge extraction: The rule is easy to understand
 Compression: The rule is simpler than the data it explains
 Outlier detection: Exceptions that are not covered by the
rule, e.g., fraud
12
Unsupervised Learning
 In supervised
learning, the aim is to …
learn a mapping from the input to an output whose
…
correct values are provided by a supervisor.
 In unsupervised learning, there is no such supervisor
and …
we only have input data.
The aim is to find the regularities in the input.
 One method is clustering where the aim is to find clusters
or groupings of input.
 Other methods like feature reduction and finding
association rules
13
Reinforcement Learning
 In some applications, the output of the system is a
sequence of actions.
 In such a case, a single action is not important; what is
important is the policy that is the sequence of correct
actions to reach the goal.
 There is no such thing as the best action in any
intermediate state; …
an action is good if it is part of a good policy.
14
Reinforcement Learning
 In such a case, the machine learning program should be
able to …
assess the goodness of policies and …
learn from past good action sequences to be able to
generate a policy.
 Such learning methods are called reinforcement learning
algorithms.
 A good example is game playing where …
a single move by itself is not that important;
it is the sequence of right moves that is good
15
Reference
 E. Alpaydın, "Introduction to Machine Learning 2nd edition
Ed.“, MIT Press, (2010)
 E. Alpaydın, "Introduction to Machine Learning 3nd edition
Ed.“, MIT Press, (2014)
16