Matakuliah
Tahun
Versi
: T0264/Intelijensia Semu
: Juli 2006
: 2/1
Pertemuan 25
Learning
1
Learning Outcomes
Pada akhir pertemuan ini, diharapkan mahasiswa
akan mampu :
• << TIK-99 >>
• << TIK-99>>
2
Outline Materi
•
•
•
•
•
Materi 1
Materi 2
Materi 3
Materi 4
Materi 5
3
17.1. What Is Learning ?
• The machine cannot be called intelligent
until they are able to learn to do new thing
and adapt to new situations, rather than
simply doing as they are told to do.
• “... changes in the system that are adaptive
in the sense that they enable the system to
do the same task or tasks drawn from the
same population more efficiently and more
effectively the next time.“ [Simon, 1983]
4
Rote-Learning Techniques
•
•
•
•
•
Skill refinement vs knowledge acquisition
Rote learning
Taking advice
Learning through problem solving
Learning from examples
5
17.2. Rote Learning
• Rote learning is basic learning activity
• Caching has been used in AI programs to produce
some surprising
• It exploited two kinds of learning :
- rote learning, which we look at now, and
parameter (or coefficient) adjustment.
- rote learning of this sort is very simple,
involve sophisticated problem solving
capabilities,
include :
organized storage of information and generalization.
6
Rote Learning
• Storing Backed-Up Values
7
17.3. Learning by Taking Advice
•
•
•
•
•
•
(avoid (take points me) (trick))
(achieve (not(during (trick) (take-points me))))
(achieve (not during
(scenario
(each p1(players) (play-card p1))
(take-trick (trick-winner)))
(take-points me))))
(achieve (not (there-exists c1 (cards-played)
(there-exists c2 (point-cards)
(during (take (trick-winner) c1)
(take me c2))))))
(achieve (not (and (have-points (cards-played))
(=(trick-winner) me))))
(achieve (>= (and (in-suit-led (card-of me))
(possible (trick-has-points)))
(low (card-of me)))
8
17.4. Learning in Problem Solving
Can a program get better without the aid of
a teacher? It can, by generalizing from its
own experiences!
•Learning by parameter adjustment
•Learning with macro-operators
•Learning by chunking
•The utility problem
9
Parameter Adjustment
• Many programs rely on an evaluation
procedure that combines information from
several sources into a single summary
statistic
• How much weight should be attached to
each component
• Credit assignment problem
10
Macro Operators and Chunking
• Sequences of actions that can be treated
as a whole
• Avoid expensive recomputation
• A chunk is essentially a large production
that does the work of an entire sequence
of smaller ones
• Several chunks may encode a single
macro operator, and one chunk may
participate in a number of macro
sequences.
11
Learning with Macro Operators
A
E
D
C
B
Start : ON(E,C)
ON(D,B)
E
A
D
C
B
Goal : ON(A,C)
ON(D,B)
[Korf 1985b]
• It turns out that the set of problems for which
macro-operators are critical are exactly those
problems with nonserializable subgoals.
• Nonserializability means that working on one
subgoal will necessarily interfere with the previous
12
solution to another subgoal,
Learning by Chunking
• Chunking is process similar in flavor to
macro-operator.
• The idea of chunking comes from the
psychological literature on memory and
problem solving.
• Its computational basis is in production
system.
• Chunking is a universal learning method.
• SOAR system solves problems by firing
productions, which are store in long-term
memory.
13
Utility Problem
• While new search control knowledge can be of
great benefit in solving new problem efficiently,
there can be also some drawbacks.
• PRODIGY maintains a utility measure for each
control rule:
• Average savings provided by the rule
• Frequency of its application
• Cost of matching
• If a proposed rule has a negative utility, it is
discarded
14
<< Closing >>
End of Pertemuan 25
Good Luck
15