The document introduces artificial intelligence (AI), covering its definition, goals, approaches, and types, including machine learning and the k-means algorithm. It discusses applications of AI in various fields such as marketing, robotics, and natural language processing, highlighting both advantages and limitations of AI technology. The conclusion reflects on AI's contributions to understanding intelligence and the ongoing challenges in modeling human reasoning.

2. ARTIFICIAL INTELLIGENCE

3. INTRODUCTION TO A.I.
WHAT IS A.I
GOALS OF A.I
APPROCHES OF AI
TYPES OF A.I.
MACHINE LEARING
K-MEAN ALGORITHEM
APPLICATION OF A.I
ADVANATAGES & DISADVATGES
LIMITATION OF A.I
CONCLUSIONS ON A.I
CONTENTS

4.  Artificial = a human creation that did not occur naturally
 Intelligence = the ability to learn and apply knowledge
 Artificial Intelligence = man-made device/system that is able
to act with and/or mimic human intelligence
 The study in development of intelligent machines and
software
INTRODUCTION

5. ARTICIACAL INTELLEGENCE
WHAT IS A.I. ?
Artificial Intelligence (A.I) is a branch of computer science
that studies the computational requirements for tasks such as
perception, reasoning and learning and develop systems to
perform those tasks
It is related to the similar task of using computers to
understand human intelligence.

6. * A.I deals with symbolic,
Algorithmic-Methods of problem
solving.
* AI works with pattern matching methods which attempt to
describe objects, events or processes in terms of their qualitative
features and logical and computational Relationship.
ARTICIACAL INTELLEGENCE

7. GOALS OF AI
The definition of AI gives four possible goals to
pursue:
 1. Systems that think like humans.
 2. Systems that think rationally.
 3. Systems that act like humans
 4. Systems that act rationally
Most of AI work falls into category (2) and (4).

8.  Replicate human intelligence: still a distant goal.
 Solve knowledge intensive tasks.
 Make an intelligent connection between
perception and action.
 Enhance human-computer and computer to
computer Interaction / communication.
GENERAL GOALS OF AI

9.  Develop concepts, theory and practice of building
intelligent machines
 Emphasis is on system building.
ENGINEERING BASED GOALS

10.  Develop concepts, mechanisms and vocabulary to
understand biological
 Intelligent behavior.
 Emphasis is on understanding intelligent behavior.
SCIENCE BASES GOALS OF AI

11.  Cognitive science:
Think human-like
 Laws of Thought:
Think Rationally
 Turing Test:
Act Human-like
 Rational Agent:
Act Rationally
AI APPROCHES

12.  Knowledge representation and Commonsense
knowledge
 Automated planning and scheduling
 Machine learning
 Natural language processing
 Machine perception, Computer vision and Speech
recognition
 Affective computing
 Computational creativity
 Artificial general intelligence and AI-complete
TYPES OF AI

13.  Machine:
A machine is a tool containing one or more parts
that uses energy to perform an intended action.
 Learning:
Learning is the act of acquiring new, or modifying
and reinforcing, existing knowledge, behaviors,
skills, values, or preferences and may involve
synthesizing different types of information.
MACHINE LEARNING

14. Ability of a machine to improve its own
performance through the use of software that
employs artificial intelligence techniques to
mimic the ways by which humans seem to learn,
such as repetition and experience.
WHAT IS MACHINE
LEARING?

15. Data is recorded from some real-world phenomenon.
What might we want to do with that data?
 Prediction:
- What can we predict about this phenomenon?
 Description:
- How can we describe/understand this
phenomenon in a new way?
LEARNING FROM DATA

16. Types of problems:
 Reinforcement learning
 Supervised learning
 Unsupervised learning
MACHINE LEARNING

17.  Reinforcement learning:
It is learning from interaction with an environment; from the
consequences of action, rather than from explicit teaching.
 Supervised learning:
Training data includes both the input and desired results. For
example the correct are known and are given in input to the
model during the learning process. The construction of a proper,
validation and attest set crucial.
MACHINE LEARNING

18. Unsupervised learning:
The data have no target attribute. We want to explore
the data to find some intrinsic structures in them. The
model is not provided with the correct result during
the training . It can be used to cluster the input data
in classes on the basis of their statistical properties. It
is further divided into:
1.Clustering
2.Hidden Markov models
3.Blind signal separation
MACHINE LEARNING

19. Clustering:
 Clustering of data is a method by which large sets
of data are grouped into clusters of smaller sets of
similar data.
 The example below demonstrates the clustering of
balls of same colors. There are a total of 9 balls
which are of three different colors. We are
interested in clustering of balls of the three
different colors into three different groups.
SUPERVISED LEARNING

20. The balls of same color are clustered into a group as
shown below
Thus, we see clustering means grouping of data or
dividing a large data set into smaller data sets of
some similarity.
CLUSTERING

21. A clustering algorithm has following types:
 Partitional clustering
1. k-Means (and EM)
2. k-Medoids
 Hierarchical clustering
1. Agglomerative
2. Divisive
3. BIRCH
CLUSTERING

22. Examples of Clustering Applications:
 Marketing: Help marketers discover distinct groups in
their customer bases, and then use this knowledge to
develop targeted marketing programs
 Land use: Identification of areas of similar land use in
an earth observation database.
 Insurance: Identifying groups of motor insurance
policy holders with a high average claim cost.
 Urban planning: Identifying groups of houses
according to their house type, value, and geographical
location.
 Seismology: Observed earth quake epicenters should
be clustered along continent faults
CLUSTERING

23.  K-means is a partitional clustering algorithm
 Let the set of data points (or instances) D be
{x1, x2, …, xn},
 where xi = (xi1, xi2, …, xir) is a vector in a real-
valued space X  Rr, and r is the number of
attributes (dimensions) in the data.
 The k-means algorithm partitions the given data
into k clusters.
• Each cluster has a cluster center, called
centroid.
• k is specified by the user
K-MEANS

24.  Works when we know k, the number of clusters
we want to find
 Randomly pick k points as the “centroids” of the k
clusters
 Loop:
 For each point, put the point in the cluster to whose
centroid it is closest
 Recomputed the cluster centroids
 Repeat loop (until there is no change in clusters
between two consecutive iterations.)
K-MEANS

25. Algorithm k-mean (k,D)
1. Choose k data point as the initial centroids (cluster
centers)
2. Repeat
3. For each data point x ∈ to D do
4. Compute the distance from x each centroid.
5. Assign x to the closest centroid //a
centroid represent a cluster
6. endfor
7. re-compute the centroid using the current
cluster membership
8. Until the stopping criterion is met
K-MEANS ALGORITHEM

26. Random Selection of k and cluster
assignment
K-MEANS EXPLANATION

27. Draw distance from two pints & draw
perpendicular bisector
K-MEANS EXPLANATION

28. The clustered will be colored According to
centroids base on perpendicular bisector
left side of cluster line give the red colors
and right side are colored yellow
K-MEANS EXPLANATION

29. Now will take the average of the each cluster,
the average will be new position of the centroid
And the centroid move to new position, this is
first iterations
K-MEANS EXPLANATION

30. Now draw distance from two centroids and
draw perpendicular bisector
K-MEANS EXPLANATION

31. Now the clustered will be colored
according to centroids base on
perpendicular bisector
left side of cluster line give the red colors
and right side are colored yellow
K-MEANS EXPLANATION

32. Now will take the average of the each
cluster, the average will be new position of
the centroid
And the centroid move to new position, this
is second iterations
K-MEANS EXPLANATION

33. Now draw distance from two centroids and
draw perpendicular bisector
K-MEANS EXPLANATION

34. Now the clustered will be colored
according to centroids base on
perpendicular bisector and will take the
average of the each cluster, the average
will be new position of the centroid
And the centroid move to new position, this
is third iterations.
K-MEANS EXPLANATION

35. Again draw distance from two pints and
draw perpendicular bisector
K-MEANS EXPLANATION

36. Again it will take the average of each
cluster and at this time centroids average
does not change/move. So this it stop. And
it is our fourth iterations
K-MEANS EXPLANATION

37. Time Complexity of K-Mean Algorithm:
Complexity is O (n * K * I )
n = number of points,
K = number of clusters,
I = number of iterations,
TIME COMPLEXITY

38.  Expert systems
 Natural Language Processing (NLP)
 Speech recognition
 Computer vision
 Robotics
 Automatic Programming
APPLICATION OF AI

39. This prospered greatly with the Digital Revolution, and
helped introduce people, especially children, to a life of
dealing with various types of Artificial Intelligence
 Games are Interactive computer program, an emerging
area in which the goals of human-level AI are pursued.
 Games are made by creating human level artificially
intelligent entities, e.g. enemies, partners, and support
characters that act just like humans.
GAME PLAYING

40. The goal of NLP is to enable people and computers to
communicate in a natural (humanly) language(such as,
English) rather than in a computer language.
The field of NLP is divided in 2
categories—
 Natural Language understanding.
 Natural Language generation.
NATURAL LEARNING PROCESS

41. The primary interactive method of communication
used by humans is not reading and writing, it is
speech.
The goal of speech recognition research is to allow
computers to understand human speech. So that they
can hear our voices and recognize the words we are
speaking.
It simplifies the process of interactive
communication between people and computers, thus
it advances the goal of NLP.
SPEECH RECOGNIZATION

42. People generally use vision as their primary
means of sensing their environment, we generally see
more than we hear, feel or smell or taste.
The goal of computer vision
research is to give computers this
same powerful facility for
understanding their surrounding.
Here A.I helps computer to
understand what they see through
attached cameras.
COUMPUTER VISION

43. A ``knowledge engineer'' interviews experts in a certain
domain and tries to embody their knowledge in a
computer program for carrying out some task.
Expert systems currently are designed to assist experts,
not to replace them, They have been used in medical
diagnosis, chemical analysis, geological explorations etc.
Domain of E.S.
Knowledge base
Facts Heuristics
Phases in Expert System
EXPERT SYSTEM

44. A Robot is a electro-mechanical
device that can by programmed to
perform manual tasks or a
reprogrammable multi functional
manipulator designed to move materials,
parts, tools, or specialized devices
through variable programmed motions
for performance of variety of tasks.
An ‘intelligent’ robot includes
some kind of sensory apparatus that
allows it to respond to change in it’s
environment.
ROBOTICS

45. Don’t need sleep
 Easier copying
Save the time
ADVANTAGES

46. It will take long time to build
Small amount of information
Can’t provide a human feel
No emotional understanding
DISADVANTAGES

47. Weather forecasting:- Military:-
DARPA Van:-
RUNNING PROJECTS

48.  It cannot understand natural language robustly
(e.g., read and understand articles in a newspaper)
 Surf the web
 Interpret an arbitrary visual scene
 Learn a natural language
 Construct plans in dynamic real-time domains
 Exhibit true autonomy and intelligence
 Still need greater software flexibility
LIMITATION OF AI

49. CONCLUSION
In its short existence, AI has increased understanding of the nature
of intelligence and provided an impressive array of application in
a wide range of areas. It has sharpened understanding of human
reasoning and of the nature of intelligence in general. At the same
time, it has revealed the complexity of modeling human reasoning
providing new areas and rich challenges for the future.

50. THANK YOU