Learning AI
Learning AI
What is 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. (Mitchell 1997)
This means :
Given : A task T
A performance measure P
Some experience E with the task
Goal : Generalize the experience in a way that allows to improve your performance
on the task.
Why do you require Machine Learning ?
Understand and improve efficiency of human learning.
Discover new things or structure that is unknown to humans.
Fill in skeletal or incomplete specifications about a domain.
Learning Agents:
An agent is an entity that is capable of perceiving and do action.
Critic Percepts
Sensors
EN
V R
ON
feed back ME
NT
Learning Element changes Performance Element
Effectors
Actions
Problem Generator
Learning Agent
Components of a Learning System
■ Performance Element: The Performance Element is the agent itself that acts in
the world. It takes in percepts and decides on external actions.
■ Learning Element: It responsible for making improvements, takes knowledge
about performance element and some feedback, determines how to modify
performance element.
■ Critic: Tells the Learning Element how agent is doing (success or failure) by
comparing with a fixed standard of performance.
■ Problem Generator: Suggests problems or actions that will generate new
examples or experiences that will aid in training the system further.
Example : Automated Taxi on city roads
e.g. , quick right turn across three lanes of traffic, observe reaction of
other drivers.
Problem Generator: Try south city road .
Rote learning
• Rote learning technique avoids understanding the inner complexities but focuses on
memorizing the material so that it can be recalled by the learner exactly the way
it was read or heard.
A process of learning by example. The system tries to induce a general rule from a set
of observed instances. The learning methods extract rules and patterns out of massive
data sets.
brick (rectangular block) with a wedge (triangular block) suitably placed on top of it,
tent – as 2 wedges touching side by side, or an arch – as 2 non-touching bricks
supporting a third wedge or brick.
The program for Each concept is learned through near miss. A near miss is an object
that is not an instance of the concept but a very similar to such instances.
The program uses procedures to analyze the drawing and construct a semantic net
representation.
An example of such an structural for the house is shown below.
Object - house Semantic net
A
has-part has-part
Supported - by
B C
isa
isa
Wedge Brick
Node A represents entire structure, which is composed of
two parts : node B, a Wedge, and node C, a Brick.
Links in network include supported-by, has-part, and isa.
Winston's program
Winston's program followed 3 basic steps in concept formulation:
1.Select one known instance of the concept. Call this the concept definition.
2.Examine definitions of other known instance of the concept. Generalize the
definition to include them.
3.Examine descriptions of near misses. Restrict the definition to exclude
these.
Both steps 2 and 3 of this procedure rely heavily on comparison process by which
similarities and differences between structures can be detected.
Winston's program can be similarly applied to learn other concepts such as "ARCH".
Decision Trees
Decision trees represent rules. Rules are easily expressed so that humans
can understand them or even directly use in a database access language
like SQL so that records falling into a particular category may be retrieved.
Decision Trees
■ Decision tree is a classifier in the form of a tree structure where each node is either a leaf or decision node.
‡ leaf node – indicates the target attribute (class) values of examples.
‡ decision node – specify test to be carried on an attribute-value.
•
■ Decision tree is a typical inductive approach to learn knowledge on classification. The conditions are :
‡ Predefined classes : Categories to which examples are to be assigned must already be defined (ie
supervised data).
‡ Discrete classes: Classes must be sharply delineated; continuous classes broken up into vague
categories as "hard", "flexible", "soft".
‡ Sufficient data: Enough training cases to distinguish valid patterns.