An Introduction to Artificial Intelligence, Overview of the technology, applications, components, strong v/s weak AI, different categories of AI, related examples, expert systems, NLP etc.

1. Future that is ahead of us!!

2. An Overview of Artificial Intelligence
An Overview of Artificial Intelligence
• Artificial intelligence (AI): ability of computers to
mimic or duplicate the functions of the human brain
• AI­based computer systems have many applications in
different fields, such as:
– Medical diagnoses
– Exploration for natural resources
– Determining what is wrong with mechanical devices
– Assisting in designing and developing other computer
systems
• AI is accomplished by studying how human brain thinks,
and how humans learn, decide, and work while trying to
solve a problem, and then using the outcomes of this study
as a basis of developing intelligent software and systems.

3. What constitutes AI
Artificial intelligence is
multi­discipline area
based on disciplines such
as Computer Science,
Biology, Psychology,
Linguistics, Mathematics,
and Engineering.

4. With and Without AI
Programming Without AI Programming with AI
A computer program without AI can answer
the specific questions it is meant to solve.
A computer program with AI can answer the
generic questions it is meant to solve.
Modification in the program leads to change
in its structure.
AI programs can absorb new modifications by
putting highly independent pieces of
information together. Hence you can modify
even a minute piece of information of
program without affecting its structure.
Modification is not quick and easy. It may
lead to affecting the program adversely.
Quick and Easy program modification.

5. • Strong AI is general artificial intelligence
– In principle able to learn and act intelligently in a broad
general range, as humans can.
• Narrow AI
– Constrained in problem sets / domains
– Set of techniques for intelligent decisions / actions
– Ubiquitous across many software systems
– Does not attempt to solve the problem of general
intelligence
– Most AI today is narrow AI
Strong AI vs Weak/Narrow AI

6. An Overview of Artificial Intelligence
Artificial Intelligence in Perspective
• Artificial intelligence systems consists of:
– People
– Procedures
– Hardware
– Software
– Data
– and knowledge
needed to develop computer systems and machines
that demonstrate the characteristics of intelligence

7. An Overview of Artificial Intelligence
What is Intelligence
• The ability of a system to
– calculate, reason, perceive relationships and analogies,
– Learn from experience and apply knowledge acquired
from experience e.g. : computerized AI chess software
– store and retrieve information from memory,
– solve problems, comprehend complex ideas, handle
complex situations
– use natural language fluently, classify, generalize, and
adapt new situations.
– Solve problems even in the case when important
information is missing
– Determine what is important
– React quickly and correctly to a new situation

8. An Overview of Artificial Intelligence
The Nature of Intelligence (continued)
• Understand visual images
– Perceptive system: approximates the way humans hear,
see, or feel objects
• Process and manipulate symbols
– On a limited basis with machine­vision hardware and
software

9. Intelligence Description Example
Linguistic intelligence The ability to speak, recognize, and use mechanisms
of phonology (speech sounds), syntax (grammar), and
semantics (meaning).
Narrators, Orators
Musical intelligence The ability to create, communicate with, and
understand meanings made of sound, understanding
of pitch, rhythm.
Musicians, Singers, Composers
Logical­mathematical
intelligence
The ability of use and understand relationships in
the absence of action or objects. Understanding
complex and abstract ideas.
Mathematicians, Scientists
Spatial intelligence The ability to perceive visual or spatial information,
change it, and re­create visual images without
reference to the objects, construct 3D images, and to
move and rotate them.
Map readers, Astronauts,
Physicists
Bodily­Kinesthetic
intelligence
The ability to use complete or part of the body to
solve problems or fashion products, control over fine
and coarse motor skills, and manipulate the objects.
Players, Dancers
Intra­personal intelligence The ability to distinguish among one’s own feelings,
intentions, and motivations.
Interpersonal intelligence The ability to recognize and make distinctions
among other people’s feelings, beliefs, and
intentions.
Mass Communicators,
Interviewers
Different types of Intelligence

10. What is intelligence?
• Rational agent model
– Choosing among alternatives in such a way to maximize
achievement of goals within time and other resource constraints
• Ability to make accurate (enough) predictions
• Requires
– Ability to receive and process information
– Remember
– Learn and abstract from information
– Model
– Plan
– Act
– Evaluate progress

11. An Overview of Artificial Intelligence
The Difference Between Natural and Artificial
Intelligence
A Comparison of Natural and Artificial Intelligence

12. An Overview of Artificial Intelligence
Different systems of Artificial Intelligence
Conceptual Model of Artificial Intelligence

13. Examples of AI applications in various areas
Expert Systems Flight­tracking systems, Clinical systems.
Natural Language
Processing
Google Now feature, speech recognition, Automatic
voice output.
Neural Networks Pattern recognition systems such as face recognition,
character recognition, handwriting recognition.
Robotics Industrial robots for moving, spraying, painting,
precision checking, drilling, cleaning, coating, carving,
etc.
Fuzzy Logic
Systems
Consumer electronics, automobiles, etc.

14. An Overview of Artificial Intelligence
Expert Systems
• Hardware and software that stores knowledge and
makes inferences, similar to a human expert
• Used in many business applications

15. An Overview of Artificial Intelligence
Robotics
• Mechanical or computer devices that perform tasks
requiring a high degree of precision or that are tedious
or hazardous for humans
• Contemporary robotics combines high­precision
machine capabilities with sophisticated controlling
software
• Many applications of robotics exist today
• Research into robots is continuing

16. An Overview of Artificial Intelligence
Robotics (continued)
Robots can be used in situations that are hazardous or inaccessible to
humans. The Rover was a remote­controlled robot used by NASA to
explore the surface of Mars.

17. An Overview of Artificial Intelligence
Vision Systems
• Hardware and software that permit computers to
capture, store, and manipulate visual images and
pictures
• Used by the U.S. Justice Department to perform
fingerprint analysis
• Can be used in identifying people based on facial
features
• Can be used with robots to give these machines “sight”

18. An Overview of Artificial Intelligence
Natural Language Processing and Voice Recognition
• Natural language processing: allows the computer
to understand and react to statements and commands
made in a “natural” language, such as English
• Voice recognition involves converting sound waves
into words

19. An Overview of Artificial Intelligence
Natural Language Processing and Voice Recognition
(continued)
Dragon Systems’ Naturally Speaking 8 Essentials uses continuous voice recognition,
or natural speech, allowing the user to speak to the computer at a normal pace
without pausing between words. The spoken words are transcribed immediately
onto the computer screen. (Source: Courtesy of Nuance Communications, Inc.)

20. An Overview of Artificial Intelligence
Learning Systems
• Combination of software and hardware that allows the
computer to change how it functions or reacts to
situations based on feedback it receives
• Learning systems software requires feedback on the
results of actions or decisions
• Feedback is used to alter what the system will do in
the future

21. An Overview of Artificial Intelligence
Neural Networks
• Computer system that can simulate the functioning of
a human brain
• Ability to retrieve information even if some of the
neural nodes fail
• Fast modification of stored data as a result of new
information
• Ability to discover relationships and trends in large
databases
• Ability to solve complex problems for which all the
information is not present

22. An Overview of Artificial Intelligence
Other Artificial Intelligence Applications
• Genetic algorithm: an approach to solving large,
complex problems in which a number of related
operations or models change and evolve until the best
one emerges
• Intelligent agent: programs and a knowledge base
used to perform a specific task for a person, a process,
or another program

23. An Overview of Artificial Intelligence
An Overview of Expert Systems
• Like human experts, computerized expert systems use
heuristics, or rules of thumb, to arrive at conclusions or
make suggestions
• Used in many fields for a variety of tasks, such as:
– Designing new products and systems
– Developing innovative insurance products
– Increasing the quality of healthcare
– Determining credit limits for credit cards
– Determining the best fertilizer mix to use on certain soils

24. An Overview of Artificial Intelligence
An Overview of Expert Systems (continued)
• Research conducted in AI during the past two decades
is resulting in expert systems that:
– Explore new business possibilities
– Increase overall profitability
– Reduce costs
– Provide superior service to customers and clients

25. An Overview of Artificial Intelligence
When to Use Expert Systems
• Develop an expert system if it can do any of the
following:
– Provide a high potential payoff or significantly reduce
downside risk
– Capture and preserve irreplaceable human expertise
– Solve a problem that is not easily solved using
traditional programming techniques
– Develop a system more consistent than human experts

26. An Overview of Artificial Intelligence
When to Use Expert Systems (continued)
• Develop an expert system if it can do any of the
following (continued):
– Provide expertise needed at a number of locations at the
same time or in a hostile environment that is dangerous
to human health
– Provide expertise that is expensive or rare
– Develop a solution faster than human experts can
– Provide expertise needed for training and development
to share the wisdom and experience of human experts
with a large number of people

27. An Overview of Artificial Intelligence
Components of Expert Systems
Figure 7.8: Components of an Expert System

28. An Overview of Artificial Intelligence
Components of Expert Systems (continued)
• Knowledge base: component of an expert system that
stores all relevant information, data, rules, cases, and
relationships used by the expert system
• Some tools and techniques for creating a knowledge base
are:
– Assembling human experts
– Using fuzzy logic: shades of gray; “fuzzy sets”
– Using rules: IF­THEN statements
– Using cases: modifying solutions to cases in knowledge base

29. An Overview of Artificial Intelligence
Components of Expert Systems (continued)
Rules for a Credit Application

30. An Overview of Artificial Intelligence
The Inference Engine
• Seeks information and relationships from the knowledge
base and provides answers, predictions, and suggestions
the way a human expert would
• Backward chaining
– Starting with conclusions and working backward to
supporting facts
• Forward chaining
– Starting with facts and working forward to solutions

31. An Overview of Artificial Intelligence
The Explanation Facility
• Allows a user or decision maker to understand how the
expert system arrived at certain conclusions or results
• Example: allow a doctor to determine the logic or rationale
of the diagnosis made by a medical expert system

32. An Overview of Artificial Intelligence
The Knowledge Acquisition Facility
• Provides convenient and efficient means of capturing and
storing all the components of the knowledge base
• Acts as an interface between experts and the knowledge
base
• Acquisition can be manual or a mixture of manual and
automated
• Knowledge base must be validated and updated frequently

33. An Overview of Artificial Intelligence
The Knowledge Acquisition Facility (continued)
Knowledge Acquisition Facility

34. An Overview of Artificial Intelligence
The User Interface
• Specialized user interface software is employed for
designing, creating, updating, and using expert
systems
• Main purpose of the user interface is to make the
development and use of an expert system easier for
users and decision makers

35. An Overview of Artificial Intelligence
Expert Systems Development
Steps in the Expert System Development Process

36. An Overview of Artificial Intelligence
Participants in Developing and Using Expert
Systems
• Domain expert: individual or group who has the
expertise or knowledge one is trying to capture in the
expert system
• Knowledge engineer: individual who has training or
experience in the design, development,
implementation, and maintenance of an expert system
• Knowledge user: individual or group who uses and
benefits from the expert system

37. An Overview of Artificial Intelligence
Participants in Developing and Using Expert
Systems (continued)
Participants in Expert Systems Development and Use

38. An Overview of Artificial Intelligence
Expert Systems Development Tools and Techniques
• Traditional programming languages
• Special programming languages
– LISP, PROLOG
• Expert system shells
– Expert system shell is a collection of software packages
and tools used to design, develop, implement, and
maintain expert systems
• Off­the­shelf expert system shells

39. An Overview of Artificial Intelligence
Expert Systems Development Tools and Techniques
(continued)
Expert Systems Development

40. An Overview of Artificial Intelligence
Applications of Expert Systems and Artificial
Intelligence
• Credit granting and loan analysis
• Stock picking
• Catching cheats and terrorists
– Gambling casinos
• Budgeting
– Prototype testing programs
• Games
– Crossword puzzles

41. An Overview of Artificial Intelligence
Applications of Expert System and Artificial
Intelligence (continued)
• Information management and retrieval
– Uses bots
• AI and expert systems embedded in products
– Antilock braking system, television
• Plant layout and manufacturing
• Hospitals and medical facilities
– Probability of contracting diseases, lab analysis, home
diagnosis, appointment scheduling
• Help desks and assistance

42. An Overview of Artificial Intelligence
Applications of Expert System and Artificial
Intelligence (continued)
• Employee performance evaluation
• Virus detection
– Uses neural network technology
• Repair and maintenance
– Telephone networks, aerospace equipment
• Shipping and marketing
• Warehouse optimization
– Restocking, location

43. An Overview of Artificial Intelligence
Virtual Reality
• Virtual reality system: enables one or more users to
move and react in a computer­simulated environment
• Immersive virtual reality: user becomes fully
immersed in an artificial, three­dimensional world that
is completely generated by a computer

44. An Overview of Artificial Intelligence
Interface Devices
• Head­mounted display (HMD)
– Screens directed at each eye; position tracker
• CAVE
– Provides illusion of immersion through projection of
stereo images on floors and walls
• Haptic interface
– Relays sense of touch and other physical sensations

45. An Overview of Artificial Intelligence
Interface Devices (continued)
Military personnel train in an immersive CAVE system

46. Approaches to AI
• Brain emulation
• Brain simulation
• Symbolic
– Cognitive simulation
– Logic based
– Anti­logic or “scruffy”
– Knowledge­based
• Sub­symbolic
– Bottom up, embodied, situated
– Computational intelligence
• Neural networks
• Connectionist
– Evolutionary computation

47. Knowledge Acquisition
• Input Modalities
– Senses
• Vision
• Hearing
• Data communication
• Touch
• Accelerometers
• Other tech..
– Text/Video
• Linear modalities
• Speech recognition
• Natural language Processing
– Preassembled knowledge / data structures

48. Memory
• Temporal Memory
– Crucial to temporal reasoning
• Cause and affect inference
• Prediction
• Factual Memory
– Searchable fact stores
– Enabling inference
• Associative Memory
– Association between memories. How are memories and inferences strengthened or weakened
by new memories?
• Memory Trimming
– What is the proper tradeoff between detail and size/speed? How is saliency determined for
current and future goals? How does the memory structure cache and prune over time?
• Learning
– What can be inferred or generalized?
– What patterns and abstractions subsuming many facts and saving resources can be garnered?
• Search and Retrieval

49. Knowledge Representation
• Fundamental Goal
– Represent knowledge in a matter facilitating efficient, accurate
retrieval and reasoning
• Categories and Objects
– Categorization of objects is a basic central abstraction form and
greatly enhances efficiency
• Events
• Mental events and objects
• Reasoning Systems for Categories
– Semantic networks
– Description logics
• Reasoning with defaults
– Default facts are specified at category level and inherited

50. KR Categories
• Taxonomies
– Membership
– Relationships among categories
• Sub­categories
• Partitioning (exhaustive decomposition)
• Physical composition
– Part/whole
– Containment
• General relationships

51. KR ­ Events
• Event <= fluent, time
– A condition that varies over time at a particular
time or time period.
– So KR events are statements about facts
concerning referents in time
– Time­intervals and interval reasoning
– Time varying knowledge
• e.g., President(USA, time)

52. KR – Mental Events
• Beliefs
– Beliefs are internal states of the AI
• Subject to change with changing information
• Self­modeling
• internal state
• Knowledge about internal state of other
agents
• Modal logic

53. Inference
• Logical Inference
– Deduction
• Derives b from a where b is a formal consequence of a. Deriving consequences of what is
known or assumed.
– Induction
• Reasons from experience to an hypothesis generalizing experience. A “jumping to
conclusions”. Does not guarantee accuracy.
– Abduction
• Seeks plausible explanations or necessities for the facts to be as they are.
• Backward chaining from sought result to possible evidence.
• Backward chaining
– Starting from a goal and looking for conditions that support / infer that goal
recursively until known facts or sufficiently strong beliefs are found.
• Forward chaining
– A form of deductive inference chasing that may or may not converge on a goal.

54. Goal Seeking
• Intelligence is difficult to speak of without goals, that which a
system seeks
• Goal seeking requires
– Goal formulation
– Problem formulation of what actions to consider in light of state and
goal
• Considers cost, likelihood of success of each possible action
– Performance measure
• An Intelligent agent optimizes its performance measurement
• Examples
– Touring problems
– Traveling salesman,
– Robot navigation
– Assembly sequencing

55. Basic Simple Search Techniques
• Exhaustive
– Can be exponential from combinatorial explosion but will find solution if exist
• Uniformed search
– No information for preferring one choice over another at each point
– Breadth first, uniform cost, depth first, depth limited iterative deepening, bi­
directional
• Informed (heuristic) search
– Greedy, best­first
– A* search
• Combines cost to reach node with distance from node to goal
– Memory bound heuristic search (combining iterative deepening with A*)
– Heuristic Sources
• Relaxing problem constraints
• Subproblem recognition from pattern database
• From experience

56. More sophisticated search
• Optimization problems
• Best state according to objective function (global maximum or minimum)
• Hill climbing search
• Simulated annealing
• Local beam search
• Genetic algorithm
– Successor states generate by combination of two or more states with modification
• Continuous space searches
• Searching with nondeterministic actions
– And­or trees
• Each node/action has several possible outcomes or range of outcomes (ands)
• Searching with incomplete perception
• Online search problems
– Real travel cost not just computational for each node traversed
• Depth first is best choice often
• Hill climbing is also workable
– Learning a map of the environment as it goes is important

57. Machine Learning Algorithm Types
• Supervised
– Input data is pre­labeled as to appropriate results. The learner approximates
the labeling function.
• Unsupervised
– Models set of inputs, like clustering
• Semi­supervised
– Combines labeled and unlabeled samples
• Reinforcement
– Learns due to feedback resulting from each attempt/guess. Common in neural
nets
• Transduction
– Tries to predict new outputs based on training inputs,outups and on test inputs
• Learning to learn
– Learns its own inductive bias based on experience

58. Machine Learning Approaches
• Decision tree learning
• Association rule learning
• Artificial Neural networks
• Genetic programming
• Inductive logic programming
• Support Vector Machines
• Clustering
• Bayesian Networks
• Reinforcement Learning
• Representation Learning

59. …..

…

60. What is intelligence?
• Rational agent model
– Choosing among alternatives in such a way to maximize
achievement of goals within time and other resource
constraints
• Ability to make accurate (enough) predictions
• Requires
– Ability to receive and process information
– Remember
– Learn and abstract from information
– Model
– Plan
– Act
– Evaluate progress