LEARNING IN ARTIFICIAL INTELLIGENCE
LEARNING IN ARTIFICIAL INTELLIGENCE
LEARNING DEFINITION
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
WHAT IS LEARNING? Machines cannot be called intelligent until they are able to learn to do new
things and adapt to new situations, rather than simply doing as they are told
to do.
Adapting to new surroundings and to solve new problems is an important
characteristics of intelligent entities
Learning covers a wide range of phenomenon:
-Skill refinement : Practice makes skills improve. More you play Cricket,
better you get
-Knowledge acquisition: Knowledge is generally acquired through
experience
VARIOUS LEARNING MECHANISMS
Simple storing of computed information or rote learning, is the most basic
learning activity
Many computer programs i.e. database systems can be said to learn in this
sense
Advice Taking
Own problem-solving experience Learning from examples : we often learn to classify things in the world
without being given explicit rules
Learning from examples usually involves a teacher who helps us classify things by correcting us when we are wrong
ROTE LEARNING
ROTE LEARNING Rote learning is the basic learning activity. It is also called
memorization because the knowledge, without any modification is,
simply coped into the knowledge base
In case of data caching, we store computed values so that we do not
have to recomputed them later
When computation is more expensive than recall, this strategy can
save a significant amount of time
Caching in AI programs can be used to produce some surprising
performance improvements
Such Caching is known as rote learning
LEARNING BY TAKING ADVICE
LEARNING BY TAKING ADVICE This is a simple form of learning
A programmer writes a set of instructions to instruct the computer
what to do, the programmer is a teacher and the computer is a
student. Once learned (i.e. programmed), the system will be in a
position to do new things
In chess, the advice “fight for control of the center of the board” is
useless unless the player can translate the advice into concrete
moves and plans. A computer program might make use of the
advice by adjusting its static evaluation function to include a factor
based on the number of center squares attacked by its own pieces
LEARNING BY TAKING ADVICE( CONTD…)
FOO (First Operational Operationaliser), for example, is
a learning system which is used to learn the game of
Hearts. It converts the advice which is in the form of
principles, problems, and methods into effective
executable (LISP) procedures (or knowledge). Now this
knowledge is ready to use.
LEARNING IN PROBLEM SOLVING
LEARNING IN PROBLEM SOLVING
Can program get better without the aid of a teacher?
It can be by generalizing from its own experiences
Learning in problem solving we have:
-Learning by parameter adjustment
-Learning by Macro-Operators
-Learning by Chunking
-The Utility Program
-Learning from Example : INDUCTION
LEARNING BY PARAMETER ADJUSTMENT
Many programs rely on an evaluation procedure that combines information from
several sources into a single summary statistic
For Example: Game Playing reflecting the desirability of a particular board
position and Pattern classification programs to determine the correct category into
which a given stimulus should be placed
In designing such programs, it is often difficult to know a priori how much weight
should be attached to each feature being used
One way of finding the correct weights is to begin with some estimate of the correct
settings and then to let the program modify the settings on the basis of its experience
LEARNING BY MACRO-OPERATORS Sequences of actions that can be treated as a whole are called macro-operators
Example: suppose you are faced with the problem of getting to the downtown post
office. Your solution may involve getting in your car, starting it, and driving along a
certain route. Substantial planning may go into choosing the appropriate route, but
you need not plan about how to about starting the car. You are free to treat START-
CAR as an atomic action, even though it really consists of several actions: sitting
down, adjusting the mirror, inserting the key, and turning the key
After each problem solving episode, the learning component takes the computed
plan and stores it away as a macro-operator, or MACROP
MACROP is just like a regular operator
LEARNING BY CHUNKING Chunking is similar to learning with macro-operators
it is used by problem solver systems that make use of production systems
When a system detects useful sequence of production firings, it creates chunk,
which is essentially a large production that does the work of an entire sequence of
smaller ones
SOAR is an example production system which uses chunking
Chunks learned during the initial stages of solving a problem are applicable in the
later stages of the same problem-solving episode
After a solution is found, the chunks remain in memory, ready for use in the next
problem
THE UTILITY PROBLEM While new search control knowledge can be of great benefit in
solving future problems efficiently, there are also some drawbacks:
large amounts of memory Required Time Consuming If we only want to minimize the number of node expansions in
the search space, then the more control rules we learn, the better
If we want to minimize the total CPU time required to solve a problem, we must consider this trade off
LEARNING FROM EXAMPLES: INDUCTION
The idea of producing a classification program that can evolve its own class
definitions is called concept learning or induction
Classification is the process of assigning, to a particular input, the name of a
class to which it belongs
The classes from which the classification procedure can choose can be
described in a variety of ways
Classification is an important component of many problem solving tasks
Before classification can be done, the classes it will use must be defined:
-Isolate a set of features that are relevant to the task domain
-Isolate a set of features that are relevant to the task domain
DISCOVERY
DISCOVERYo Learning is the process by which one entity acquires knowledge.
Usually that knowledge is already possessed by some number of
other entities who may serve as teachers
o Discovery is a restricted form of learning in which one entity
acquires knowledge without the help of a teacher
- Theory-Driven Discovery
- Data Driven Discovery
- Clustering
AM : THEORY-DRIVEN DISCOVERY
o AM is a program that discovers concepts in elementary mathematics
and set theory
oAM is written by Lenat and it worked from a few basic concepts of set
theory to discover a good deal of standard number theoryoAM has 2 inputs: - A description of some concepts of set theory (in LISP form),E.g. set union
-Information on how to perform mathematics. E.g. functions
oAM exploited a variety of general-purpose AI techniques. It used a
frame system to represent mathematical concepts. One of the major
activities of AM is to create new concepts and fill in their slots
HOW DOES AM WORKS?
BACON: DATA DRIVEN DISCOVERY
o Many discoveries are made from observing data obtained from the
world and making sense of it -- E.g. Astrophysics - discovery of planets,
Quantum mechanics , discovery of sub-atomic particles
o BACON is an attempt at provided such an AI system
o BACON begins with a set of variables for a problem
For example in the study of the behavior of gases, some
variables are p, the pressure on the gas, V, the volume of the gas, n, the
amount of gas in moles, and T the temperature of the gas
o Physicists have long known a law, called ideal gas law, that relates these
variables
HOW DOES BACON WORKS?o First, BACON holds the variables n and T constant, performing
experiments at different pressures p1, p2 and p3
o BACON notices that as the pressure increases, the volume V decreases
o For all values, n, p, V and T, pV/nT = 8.32 which is ideal gas law as
shown by BACON
o BACON has been used to discover wide variety of scientifc laws such
as Kepler’s third law, Ohm’s law, the conservation of momentum and
Joule’s law
o BACON’s discovery procedure is state-space search
CLUSTERINGo A cluster is a collection of objects which are similar in some way. Clustering
groups data items into similarity classes. The properties of these classes can then
be used to understand problem characteristics or to find similar groups of data
items. Clustering can be defined as the process of reducing a large set of unlabeled
data to manageable piles consisting of similar items. The similarity measures
depend on the assumptions and desired usage one brings to the data
oClustering begins by doing feature extraction on data items and measure the
values of the chosen feature set. Then the clustering model selects and compares
two sets of data items and outputs the similarity measure between them
ANY QUESTION