Scribd
Upload
9 views14 pages

C 6 Learning 2

Uploaded by

akny111228
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
9 views14 pages

C 6 Learning 2

Uploaded by

akny111228
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 14

Learning Techniques in AI

Learning
 Learning is a process by which a system acquires knowledge.
 Learning is the activity that enables the system to do the
same task more efficiently and more effectively next time.
 Learning is the key to improve a system’s performance.
Approaches towards Learning
■Skill Refinement
■Knowledge Acquisition
■Taking Advice
■Problem Solving
■Induction
■Discovery
■Analogy
How can we learn?
 Skill refinement
■ one can learn by practicing, e.g. playing the piano.
 Knowledge acquisition
■ one can learn by experience and by storing the experience in a
knowledge base. One basic example of this type is Rote learning.
 Taking advice
■ Similar to rote learning although the knowledge that is input may
need to be transformed (or operationalised) in order to be used
effectively.
 Problem Solving
■ if a person solves a problem he may learn from this experience.
The next time he sees a similar problem he can solve it more
efficiently. This does not usually involve gathering new knowledge
but may involve reorganization of data or remembering how to
achieve the solution.
How can we learn?
 Induction
■ One can learn from examples. Humans often classify things in
the world without knowing explicit rules. Usually involves a
teacher or trainer to aid the classification.
■ An inductive approach involves the learners detecting, or
noticing, patterns and working out a 'rule' for themselves before
they practise the language. A deductive approach (rule-driven)
starts with the presentation of a rule and is followed by examples
in which the rule is applied.
 Discovery
■ Here one learns knowledge without the aid of a teacher.
 Analogy
■ If a system can recognize similarities in information already
stored then it may be able to transfer some knowledge to
improve the solution of the task at hand.
Types of Learning
1. Supervised learning is a type of machine learning where
an algorithm is trained on a labeled dataset. In this
approach, Output and Input are given to the model. The goal
is for the model to predict the labels for new, unseen data
based on what it has learned.
2. Unsupervised learning is a type of machine learning
where the algorithm is trained on data without labeled
outputs. The goal is for the model to identify patterns,
structures, or relationships within the data without explicit
guidance on what to look for.
3. Reinforcement learning (RL) is a type of machine
learning where an agent learns to make decisions by
interacting with an environment. The agent aims to
maximize a cumulative reward over time by taking actions
that influence the state of the environment.
Learning from Examples
Inductive Learning or Concept Learning
 It is concerned with finding a hypothesis from groups of positive and
negative examples.
 The task of pure inductive inference is to give a collection of examples and
return a function h that is approximates. The function h is called hypothesis.
positive examples + negative examples + background knowledge => hypothesis
 It is a system that tries to induce a general rule based on observed instance.
 It is a kind of supervised learning, where examples are provided with
classifications.
The Inductive Learning Example

Example :- Human uses Inductive Reasoning to arrive at a general conclusion


from a limited set of facts by the process of generalization.
• Case 1 :- Monkey in Haryana eat bananas.
• Case 2 :- Monkey in Kerela eat bananas.
• Case 3 :- Monkey in Gujrat eat bananas.
Conclusion:- All monkeys eat bananas.

Given: Training examples (x; f(x)) for some unknown function f


Find: A good approximation to f.
Example Applications:-
Handwriting Recognition
 x: Data from pen motion.
 f(x): Letter of the alphabet.
The inductive learning problem

Concept learning or classification


 Classification is the process of assigning to a particular input, the
name of a class to which it belongs to.
 The idea of producing a classification program that can evolve its own
class definitions is called Concept learning.
■Given a set of examples of some concept/class/category, determine if a
given example is an instance of the concept or not.
■If it is an instance, we call it a positive example.
■If it is not, it is called a negative example.
■Or we can make a probabilistic prediction (e.g., using a Bayesian net)
Discovery as Learning

 It is a restricted form of learning that acquires knowledge without the


help of a teacher.
 It has three categories:-
■ Theory Driven Discovery
■ Data Driven Discovery
■ Clustering
 AM : Theory Driven Discovery
■ Developed by Dough Lenat.
■ AM is an artificial program considered as a successful example of
implementing discovery learning.
■ AM is a program that discovers concepts in elementary mathematics and set
theory.
■ AM has 2 inputs:
■ Description of some concepts of theory (in LISP). E.g. set union,
intersection etc.
■ Information on how to perform mathematics. E.g. functions.
Discovery as Learning: Clustering

 A collection of a similar type of data is called a cluster and


technology behind the collection is called clustering.
 It is similar to induction, but difference is that in
inductive learning, a program learns to classify objects
based on the labeling provided by a teacher.
 But in clustering, no class labeling is provided. The
program must discover for itself the natural classes that
exist for the objects, in addition to a method for
classifying instances.
 AUTOCLASS is one program that accepts a number of
training cases and hypothesizes a set of classes.
Learning by Analogy

 Analogy (resemblance) involves a complicated mapping between


what might appear to be two dissimilar concepts. It is a powerful
inference tool.
■ Act cleverly like a fox.
■ He is just like a monkey.
 Humans quickly recognize the abstractions involved and
understand the meaning.
 There are two methods of analogical problem solving studied in
AI.
■ Transformational Analogy
■ Derivational Analogy
Transformational Analogy

 Look for a similar solution and copy it to the new situation making
suitable substitutions where appropriate. E.g. Geometry
 If you know about lengths of line segments and a proof that certain
lines are equal then we can make similar assertions about angles.

We know that lines RO = NY and angles AOB = COD


We have seen that RO + ON = ON + NY
So we can say that angles AOB + BOC = BOC + COD
So by a transitive rule line RN = OY
So similarly angle AOC = BOD
Derivational Analogy

 Transformational analogy does not look at how the problem was


solved -- it only looks at the final solution.
 The detailed history of a problem solving episode is called its
derivation.
 Carbonell (1986) showed that derivational analogy is a necessary
component in the transfer of skills in complex domains:
■ In translating C++ code to Java -- line by line translation is
no use. You will have to reuse the major structural and
control decisions.
■ One way to do this is to replay a previous derivation and
modify it when necessary.
■ If initial steps and assumptions are still valid copy them
across.
Explanation Based Learning
 Humans appear to learn quite a lot from one example.
 Basic idea: Use results from one example’s problem solving effort next
time around.
 An EBL accepts 4 kinds of input:
 A training example
■ what the learning sees in the world.
 A goal concept
■ a high level description of what the program is supposed to learn.
 An operational criterion
■ a description of which concepts are usable.
 A domain theory
■ a set of rules that describe relationships between objects and
actions in a domain.
 From this EBL computes, a generalization of the training example
that is sufficient not only to describe the goal concept but also satisfies
the operational criterion.

You might also like

pFad - Phonifier reborn

Pfad - The Proxy pFad of © 2024 Garber Painting. All rights reserved.

Note: This service is not intended for secure transactions such as banking, social media, email, or purchasing. Use at your own risk. We assume no liability whatsoever for broken pages.


Alternative Proxies:

Alternative Proxy

pFad Proxy

pFad v3 Proxy

pFad v4 Proxy