- The document discusses a lecture on machine learning given by Ravi Gupta and G. Bharadwaja Kumar. - Machine learning allows computers to automatically improve at tasks through experience. It is used for problems where the output is unknown and computation is expensive. - Machine learning involves training a decision function or hypothesis on examples to perform tasks like classification, regression, and clustering. The training experience and representation impact whether learning succeeds. - Choosing how to represent the target function, select training examples, and update weights to improve performance are issues in machine learning systems.

1. Lecture Series on Machine
Learning
Ravi Gupta and G. Bharadwaja Kumar
AU-KBC Research Centre,
MIT Campus, Anna University

2. Books
Machine Learning by Tom M. Mitchell

3. Lecture No. 1
Ravi Gupta
AU-KBC Research Centre,
MIT Campus, Anna University
Date: 5.03.2008

4. What is Machine Learning ???
Machine Learning (ML) is concerned with
the question of how to construct computer
programs that automatically improves with
experience.

5. When Machine Learning ???
• Computers applied for solving a complex problem
• No known method for computing output is present
• When computation is expensive

6. When Machine Learning ???
• Classification of protein types based amino acid sequences
• Screening of credit applicants (who will default and who will
not)
• Modeling a complex chemical reaction, when the precise
interaction of the different reactants is unknown

7. What Machine Learning does???
Decision Function
/ Hypothesis

8. What Machine Learning does???
Training Decision Function
Examples / Hypothesis

9. Supervised Learning
Apple
Decision Function
/ Hypothesis
Orange
Supervised Classification

10. Unsupervised Learning
Decision Function
/ Hypothesis
Unsupervised Classification

11. Binary Classification
Decision Function
/ Hypothesis

12. Multiclass Classification
Decision Function
/ Hypothesis

13. Application of Machine Learning
• Speech and Hand Writing Recognition)
• Robotics (Robot locomotion)
• Search Engines (Information Retrieval)
• Learning to Classify new astronomical structures
• Medical Diagnosis
• Learning to drive an autonomous vehicle
• Computational Biology/Bioinformatics
• Computer Vision (Object Detection algorithms)
• Detecting credit card fraud
• Stock Market analysis
• Game playing
• ………………..
• ………………….

14. Search Engines

15. Sky Image Cataloging and Analysis Tool (SKI
CAT) to Classify new astronomical structures

16. ALVINN (Autonomous Land Vehicle
In a Neural Network)

17. SPHINX - A speech recognizer

18. Disciplines that contribute to
development ML Field

19. Definition (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. (Tom Mitchell, 1998)

20. Checker Learning Problem
A computer program that learns to play checkers might
improve its performance as measured by its ability to win at the
class of tasks involving playing checkers games, through
experience obtained by playing games against itself
• Task T : playing checkers
• Performance measure P: % of game won against opponents
• Training experience E : playing practice game against itself

21. A Handwritten Recognition
Problem
• Task T : recognizing and classifying handwritten words
within images
• Performance measure P: % of words correctly classified
• Training experience E : a database of handwritten
words with given classifications

22. A Robot Driving Learning Problem
• Task T : driving on public four-lane highways using
vision sensors
Performance measure P: average distance traveled
before an error (as judged by human overseer)
• Training experience E : a sequence of images and
steering commands recorded while observing a human
driver

23. Designing a Learning System

24. Checker Learning Problem
• Task T : playing checkers
• Performance measure P: % of game won against
opponents
• Training experience E : playing practice game
against itself

25. Checker

26. Choosing the Training Experience
The type of training experience E available to a system
can have significant impact on success or failure of the
learning system.

27. Choosing the Training Experience
One key attribute is whether the training experience
provides direct or indirect feedback regarding the
choices made by the performance system

28. Direct Learning

29. Indirect Learning
Next Move
Win / Loss

30. Second attribute is the degree to which the learner
controls the sequence of training examples.
Next
Move

31. Another attribute is the degree to which the learner
controls the sequence of training examples.
Teacher / Expert
Player Next Move
Player Next Move

32. How well the training experience represents the
distribution of examples over which the final system
performance P must be measured.
(Learning will be most reliable when the training
example follow a distribution similar to that of future
test examples)

33. V. Anand
G. Kasparov

34. Garry Kasparov playing chess with IBM's Deep Blue.
Photo courtesy of IBM.

35. Kasparov Monkey

36. Geri’s Game by Pixar in which an elderly man enjoys a game of chess
with himself (available at http://www.pixar.com/shorts/gg/theater/index.html)
Won an Academy Award for best animated short film.

37. Assumptions
• Let us assume that our system will train by
playing games against itself.
• And it is allowed to generate as much training
data as time permits.

38. Issues Related to Experience
What type of
knowledge/experience
should one learn??
How to represent the
experience ? (some
mathematical
representation for
experience)
What should be the
learning mechanism???

39. Main objective of the checker
playing
Best Next Move

40. Target Function
Choose Move: B → M
Choose Move is a function
where input B is the set of legal board states
and produces M which is the set of legal moves

41. Input: Board State
Output: M (Moves)

42. Target Function
Choose Move: B → M
M = Choose Move (B)

43. Alternative Target Function
F:B→R
F is the target function,
Input B is the board state and
Output R denotes a set of real number

44. Input: Board State
Output: M (Moves)
F = 10 F = 7.7 F = 14.3 F = 10
F = 10.8 F = 6.3 F = 9.4

45. Representation of Target Function
• xl: the number of white pieces on the board
• x2: the number of red pieces on the board
• x3: the number of white kings on the board
• x4: the number of red kings on the board
• x5: the number of white pieces threatened by red (i.e.,
which can be captured on red's next turn)
• X6: the number of red pieces threatened by white
F'(b) = w0 + w1x1+ w2x2 + w3x3 + w4x4 + w5x5 + w6x6

46. • Task T: playing checkers
• Performance measure P: % of games won in the world
tournament
• Training experience E: games played against itself
• Target function: F : Board → R
• Target function representation
F'(b) = w0 + w1x1+ w2x2 + w3x3 + w4x4 + w5x5 + w6x6
The problem of learning a checkers strategy reduces to the
problem of learning values for the coefficients w0 through w6 in
the target function representation

47. Adjustment of Weights
E(Error) ≡ ∑
< b , Ftrain ( b ) >∈ training examples
(Ftrain (b) − F '(b))
2

48. Generic issues of Machine Learning
• What algorithms exist for learning general target functions from
specific training examples?
• In what settings will particular algorithms converge to the desired
function, given sufficient training data?
• Which algorithms perform best for which types of problems and
representations?
• How much training data is sufficient?
• What is the best way to reduce the learning task to one or more
function approximation problems?

49. Generic issues of Machine Learning
• When and how can prior knowledge held by the learner guide the
process of generalizing from examples?
• Can prior knowledge be helpful even when it is only approximately
correct?
• What is the best strategy for choosing a useful next training
experience, and how does the choice of this strategy alter the
complexity of the learning problem?
• How can the learner automatically alter its representation to
improve its ability to represent and learn the target function?

50. Concept Learning

51. Concept Learning
A task of acquiring a potential hypothesis (solution) that
best fits the training examples

52. Concept Learning Task
Objective is to learn EnjoySport
{Sky, AirTemp, Humidity, Wind, Water, Forecast} → EnjoySport
Tom enjoys his favorite water sports

53. Concept Learning Task
Objective is to learn EnjoySport
{Sky, AirTemp, Humidity, Wind, Water, Forecast} → EnjoySport
Input variables Output
<x1, x2, x3, x4, x5, x6> → <y>

54. Notations

55. Notations
Instances (X) Target Concept (C)
Training examples (D)

56. Concept Learning
Acquiring the definition of a general category from a given set of
positive and negative training examples of the category.
instance
A hypothesis h in H such that h(x) = c(x) for all x in X
hypothesis Target Instance
concept

57. Instance Space
Suppose that the target hypothesis that we want to
learn for the current problem is represented as a
conjunction of all the attributes
Sky = .... AND AirTemp = …. AND Humidity= …. AND Wind = …. AND
Water= …. AND Forecast= …. THEN EnjoySport= ….

58. Instance Space
Suppose the attribute Sky has three possible values,
and that AirTemp, Humidity, Wind, Water, and
Forecast each have two possible values
Instance
Space
Possible distinct instances = 3 * 2 * 2 * 2 * 2 * 2 = 96

59. Hypothesis Space
Hypothesis Space: A set of all possible hypotheses
Possible syntactically distinct Hypotheses for EnjoySport
= 5 * 4 * 4 * 4 * 4 * 4 = 5120
• Sky has three possible values
• Fourth value don’t care (?)
• Fifth value is empty set Ø

60. Hypothesis Space
h = <Sunny, Warm, ?, Strong, Warm, Same>
Normal / High

61. Hypothesis Space
h = <Ø, Warm, ?, Strong, Warm, Same>

62. Concept Learning as Search
Concept learning can be viewed as the task of searching through
a large space of hypothesis implicitly defined by the hypothesis
representation.
The goal of the concept learning search is to find the hypothesis
that best fits the training examples.

63. General-to-Specific Learning
Every day Tom his
enjoy i.e., Only
positive examples.
Most General Hypothesis: h = <?, ?, ?, ?, ?, ?>
Most Specific Hypothesis: h = < Ø, Ø, Ø, Ø, Ø, Ø>

64. General-to-Specific Learning
Consider the sets of instances that are classified positive by hl and by h2. h2 imposes
fewer constraints on the instance, thus it classifies more instances as positive.
Any instance classified positive by hl will also be classified positive by
h2. Therefore, we say that h2 is more general than hl.

65. Definition
Given hypotheses hj and hk, hj is more_general_than_or_equal_to
hk if and only if any instance that satisfies hk also satisfies hj.
We can also say that hj is more_specific_than hk when hk is
more_general_than hj.

66. More_general_than relation

67. FIND-S: Finding a Maximally
Specific Hypothesis

68. Step 1: FIND-S
h0 = <Ø, Ø, Ø, Ø, Ø, Ø>

69. Step 2: FIND-S
h0 = <Ø, Ø, Ø, Ø, Ø, Ø>
a1 a2 a3 a4 a5 a6
x1 = <Sunny, Warm, Normal, Strong, Warm, Same>
Iteration 1
h1 = <Sunny, Warm, Normal, Strong, Warm, Same>

70. h1 = <Sunny, Warm, Normal, Strong, Warm, Same>
Iteration 2
x2 = <Sunny, Warm, High, Strong, Warm, Same>
h2 = <Sunny, Warm, ?, Strong, Warm, Same>

71. Iteration 3 Ignore h3 = <Sunny, Warm, ?, Strong, Warm, Same>

72. h3 = < Sunny, Warm, ?, Strong, Warm, Same >
Iteration 4
x4 = < Sunny, Warm, High, Strong, Cool, Change >
Step 3
Output h4 = <Sunny, Warm, ?, Strong, ?, ?>

74. Key Properties of FIND-S Algorithm
• Guaranteed to output the most specific hypothesis within H
that is consistent with the positive training examples.
• Final hypothesis will also be consistent with the negative
examples provided the correct target concept is contained in
H, and provided the training examples are correct.

75. Unanswered Questions by FIND-S
• Has the learner converged to the correct
target concept?
Although FIND-S will find a hypothesis consistent with the training data, it
has no way to determine whether it has found the only hypothesis in H
consistent with the data (i.e., the correct target concept
• Why prefer the most specific hypothesis?
In case there are multiple hypotheses consistent with the training examples,
FIND-S will find the most specific. It is unclear whether we should prefer this
hypothesis over, say, the most general, or some other hypothesis of
intermediate generality.

76. Unanswered Questions by FIND-S
• Are the training examples consistent?
In most practical learning problems there is some chance that the training
examples will contain at least some errors or noise. Such inconsistent sets
of training examples can severely mislead FIND-S, given the fact that it
ignores negative examples. We would prefer an algorithm that could at least
detect when the training data is inconsistent and, preferably, accommodate
such errors.

77. Unanswered Questions by FIND-S
• What if there are several maximally specific
consistent hypotheses?
In the hypothesis language H for the EnjoySport task, there is always a
unique, most specific hypothesis consistent with any set of positive
examples. However, for other hypothesis spaces (which will be discussed
later) there can be several maximally specific hypotheses consistent with
the data.