The document discusses machine learning and provides definitions and examples. It covers the following key points: - Machine learning is a subfield of artificial intelligence concerned with developing algorithms that allow computers to learn from data without being explicitly programmed. - Well-posed learning problems have a defined task, performance measure, and training experience. Examples given include learning to play checkers and recognize handwritten words. - Designing a machine learning system involves choosing a training experience, target function, representation of the target function, and learning algorithm to approximate the function. A checkers-playing example is used to illustrate these design decisions.

1. MACHINE LEARNING
SWAPNA.C
by swapna.c

2. Machine Learning
• Learning ↔ Intelligence
• Def: (Learning): Acquisition of knowledge or skills through
study , experience, or being taught.
• Def: Intelligence is the ability to learn and use concepts to
solve problems.
• Machine Learning ↔ Artificial Intelligence –
• Def: AI is the science of making machines do things that
require intelligence if done by human. (Minsky 1986).
• Def: Machine Learning is an area of AI concerned with
development of techniques which allow machines to learn.
by swapna.c

3. Why Machine Learning
• Why Machine Learning? ↔ Why Artificial Intelligence? ≡ To
build machines exhibiting intelligent behaviour (i.e., able to
reason, predict, and adapt) while helping humans work, study,
and entertain themselves.
• Recent programs in algorithm and theory.
• Growing flood of online data.
• More Computational power is available than human.
• Budding industry.
by swapna.c

4. Relevant disciplines and examples of
their influence on machine learning.
• Artificial intelligence
Bayesian methods
Computational complexity theory
• Control theory
Information theory
• Philosophy
Psychology and neurobiology
Statistics
by swapna.c

5. Well-posed Learning Problems
• Def: 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.
• Def 2 (Hadamard 1902): A (machine learning) problem is
well-posed if a solution to it exists, if that solution is unique,
and if that solution depends on the data / experience but it is
not sensitive to (reasonably small) changes in the data /
experience.
• For example, 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.
by swapna.c

6. Successful Applications
• Learning to recognize spoken words.
All of the most successful speech recognition systems employ
machine learning in some form. For example the SPHINX
system .
. Learning to drive an autonomous vehicle.
Machine learning methods have been used to train computer-
controlled vehicles to steer correctly when driving on a variety
of road types. For example, the ALVINN system.
by swapna.c

7. • Learning to classify new astronomical structures.
Machine learning methods have been applied to a variety of
large databases to learn general regularities implicit in the data.
For example, decision tree learning algorithms have been used
by NASA to learn how to classify celestial objects from the
second Palomar Observatory SkySurvey (Fayyad et al. 1995).
• Learning to play world-class backgammon.
The most successful computer programs for playing games
such as backgammon are based on machine learning
algorithms. For example, the world's top computer program for
backgammon, TD-GAMMO
by swapna.c

8. To have a well-defined learning
problem
Identify 3 Features: the class of tasks, the measure of
performance to be improved, and the source of experience.
• checkers learning problem:
• Task T: playing checkers
• Performance measure P: percent of games won against
opponents.
• Training experience E: playing practice games against itself.
• Some other learning problems:
by swapna.c

9. A handwriting recognition learning
problem:
• Task T: recognizing and classifying handwritten words
within images
• Performance measure P: percent of words correctly
classified.
Training experience E: a database of handwritten words
with given classifications
by swapna.c

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

11. Designing a learning system
1. Choosing the training experience
– Examples of best moves, games outcome …
2. Choosing the target function
– board-move, board-value, …
3. Choosing a representation for the target function
– linear function with weights (hypothesis space)
4. Choosing a learning algorithm for approximating the
target function
– A method for parameter estimation

12. Designing A Learning System
1.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.
• A second important attribute of the training experience is
the degree to which the learner controls the sequence of
training.
• A third important attribute of the training experience is
how well it represents the distribution of examples over
which the final system performance P must be measured.
by swapna.c

13. Checkers Game
by swapna.c

14. 2.Choosing the Target Function
• The next design choice is to determine exactly what type of
knowledge will be learned and how this will be used by the
performance program. B-M(Priori) (Evaluation Target
function) V:BR
• Let us therefore define the target value V(b) for an arbitrary
board state b in B, as follows:
• 1. if b is a final board state that is won, then V(b) = 100
• 2. if b is a final board state that is lost, then V(b) = -100
• 3. if b is a final board state that is drawn, then V(b) = 0
• 4. if b is a not a final state in the game, then V(b) = V(b’)
where b' is the best final board state that can be achieved
starting from b and playing optimally until the end of the game
(assuming the opponent plays optimally, as well).
by swapna.c

15. 3.Choosing a Representation for the
Target Function
• let us choose a simple representation: for any given board
state, the function c will be calculated as a linear combination
of the following board features:
• xl: the number of black pieces on the board
• x2: the number of red pieces on the board
• x3: the number of black kings on the board
• x4: the number of red kings on the board
• x5: the number of black pieces threatened by red (i.e., which
can be captured
• on red's next turn)
• X6: the number of red pieces threatened by black
by swapna.c

16. • Thus, our learning program will represent c(b) as a linear
function of the form
V^(b)=w0+w1x1+w2x2+w3x3+w4x4+w5x5+w6x6
• where wo through W6 are numerical coefficients, or weights,
to be chosen by the learning algorithm. . Learned values for
the weights w l through W6 will determine the relative
importance of the various board features in determining the
value of the board, whereas the weight w0 will provide an
additive constant to the board value.
by swapna.c

17. • Partial design of a checkers learning program:
• Task T: playing checkers
• Performance measure P: percent of games won in the world
tournament.
• Training experience E: games played against itself
• Targetfunction: V:Board ->R
• Targetfunction representation
• V^(b)=w0+w1x1+w2x2+w3x3+w4x4+w5x5+w6x6
by swapna.c

18. 4.Choosing a function Approximation
Algorithm
• In order to learn the target function f we require a set of
training examples, each describing a specific board state b and
the training value Vtrain(b)for b. In other words, each training
example is an ordered pair of the form (b, V',,,i,(b)). For
instance, the following training example describes a board
state b in which black has won the game (note x2 = 0 indicates
that red has no remaining pieces) and for which the target
function value Vtrain(b)is therefore +100.
• b=(x1=3,x2=0,x3=1x4=0,x5=0x6=0)
• <<x1=3,x2=0,x3=1,x4=0,x5=0,x6=0),+100>>.
• Estimating training values, Adjusting the Weights
by swapna.c

19. 4.1Estimating Training Values
• ESTIMATING TRAINING VALUES:
• In ex. Training information only available is about game was
won or not.
• An approach is made to assign the training value of Vtrain(b)
for intermediate board state b to be V^(successor(b)). Where
v(b) the learners current approximation to V.(Successor(b)
denotes the next board state of b.
• V,,,i.(b)c c(~successor(b)) Each training example is an ordered
pair of the form k for estimating training values< b,Vtrain (b)>
• Recall that according to our formulation of the learning
problem, the only training information available to our learner
is whether the game was eventually won or lost.
• Rule for estimating training values.
Vtrain(b)V^(Successor(b))
by swapna.c

20. by swapna.c

21. Adjusting The Weights
• Several algorithms are known for finding weights of a linear
function that minimize E defined in this way.
• In our case, we require an algorithm that will incrementally
refine the weights as new training examples become available
and that will be robust to errors in these estimated training
values. One such algorithm is called the Least Mean Squares,
or LMS training rule.
• For each observed training example it adjusts the weights a
small amount in the direction that reduces the error on this
training example.
by swapna.c

22. by swapna.c

23. 4.3Final Design
• The Final design of our checkers learning system can
be naturally described by four distinct program
modules that represent the central components in
many learning systems.
• Performance System : It is the module that must
solve the given performance task, in this case playing
checkers, by using the learned target functions(s).
by swapna.c

24. by swapna.c

25. • The Critic takes as input the history or trace of the game
and produces as output a set of training examples of the
target function
• The Generalizer takes as input the training examples and
produces an output hypothesis that is its estimate of the
target function.
• The Experiment Generator takes as input the current
hypothesis (currently learned function) and outputs a new
problem (i.e., initial board state) for the Performance
System to explore. Its role is to pick new practice
problems that will maximize the learning rate of the
overall system. In our example, the Experiment Generator
follows a very simple strategy: It always proposes the
same initial game board to begin a new game.
by swapna.c

26. by swapna.c

27. Perspective & Issues in Machine Learning
Perspective:
• It involves searching a very large space of possible hypothesis
to determine the one that best fits the observed data.
Issues:
• Which algorithm performs best for which types of problems &
representation?
• How much training data is sufficient?
• Can prior knowledge be helpful even when it is only
approximately correct?
• The best strategy for choosing a useful next training
experience.
• What specific function should the system attempt to learn?
• How can learner automatically alter it’s representation to
improve it’s ability to represent and learn the target function?
by swapna.c