Intelligent Systems

Document Sample
Intelligent Systems Powered By Docstoc
					CS101 Introduction to Computing

Lecture 34
      Intelligent Systems

       During the last lecture …
       (Graphics & Animation)
•   We became familiar with the role that
    graphics and animations play in computing

•   We discussed how graphics & animation are

•   We also looked at several formats used for
    storing graphics and animation
            Computer Graphics
• Images created with the help of computers

• 2-D and 3-D (displayed on a 2-D screen but in
  such a way that they give an illusion of depth)

• Used for scientific research, artistic expression,
  or for industrial applications

• Graphics have made the computer interfaces
  more intuitive by removing the need to
  memorize commands                        3
            Displaying Images
• Most all computer displays consist of a grid of
  tiny pixels arranged in a regular grid of rows
  and columns

• Images are displayed by assigning different
  colors to the pixels located in the desired
  portion of the computer display

• Let’s discuss the pixel a bit more …
• The smallest image forming element on a
  computer display

• The computer display is made up of a regular
  grid of these pixels

• The computer has the capability of assigning
  any color to any of the individual pixels on the

• Let’s now see how the computer displays a
  square                                    5
               Pixel Colors (1)
• The color of each pixel is generally represented
  in the form a triplet

• In a popular scheme – the RGB scheme – each
  part of the triplet represents the intensity of one
  of out of three primary colors: red, green, blue

• Often, the intensity of each color is represented
  with a byte, resulting in 256x256x256 (16+
  million) unique color combinations            6
             Color Mapping (1)
• Instead of letting each pixel assume one out of
  16 million possible colors, only a limited number
  of colors – called the platelet – are allowed

• For example, the platelet may be restricted to
  256 colors (requiring 1 byte/pixel instead of 3)

• In this scheme, pixels of alternating colors are
  used to simulate a color that is not present in
  the platelet

• For example, red and green pixels can be
  alternated to give the impression of bright

• The quality of the displayed image is poorer
• The computer screen consists of square-ish
  pixels arranged in a fixed grid

• At times, when a diagonal line is drawn on this
  grid, it looks more like a staircase, instead of a
  straight line

• This effect – called aliasing – can be managed
  by reducing the size of pixels
              Anti-Aliasing (1)
• Anti-aliasing is another technique used for
  managing the ‘staircase’ effect

• Let’s say that we need to draw a white straight-
  line such that it overlaps 60% with one pixel,
  and 40% with another initially, and near the
  end, 58%, 41%, and 1%, respectively, with
  three pixels

Vector or Object-Oriented Graphics
• Treats everything that is drawn as an object

• Objects retain their identity after they are drawn

• These objects can later be easily moved,
  stretched, duplicated, deleted, etc

• Are resolution independent

• Relatively small file size

• Examples: swf, svg, wmf, ps                  11
   Bit-Mapped or Raster Graphics
• Treats everything that is drawn as a bit-map

• If an object is drawn on top of another, it is
  difficult to move just one of them while leaving
  the other untouched

• Changing the resolution often requires
  considerable touch-up work

• Relatively large file size

• Examples: gif, jpg, bmp                     12
             3-D Graphics (1)
• Flat images enhanced to impart the illusion of

• We perceive the world and the objects in it in 3-
  D - breadth, width, depth - although the images
  formed on the retinas of our eyes are 2-D

• The secret of 3-D perception: stereo vision

                3-D Rendering
• The process of converting information about 3-
  D objects into a bit-map that can be displayed
  on a 2-D computer display

• Computationally, very expensive!

• Steps:
  – Draw the wire-frame (skeleton, made with thin lines)
  – Fill with colors, textures, patterns
  – Add lighting effects (reflections, shadows)   14
• Graphics in motion, e.g. cartoons

• Illusion of motion is created by showing the
  viewer a sequence of still images, rapidly

• Drawing those images - each slightly different
  from the previous one - used to be quite tedious

• Computers have helped in cutting down some
  of the tediousness                      15
                Tweening (2)
• This process of creating these in-between
  images from key images is called in-betweening
  (or tweening for short)

• The simplest algorithm for tweening calculates
  the position of a particular segment of an image
  by calculating the average of the positions of
  that same image segment belonging to
  adjacent key images
              Today’s Goals:
           (Intelligent Systems)
•   To become familiar with the distinguishing
    features of intelligent systems with respect to
    other software systems

•   To become able to appreciate the role of
    intelligent systems in scientific, business and
    consumer applications

•   To look at several techniques for designing
    intelligent systems
     (Artificial) Intelligent Systems
• SW programs or SW/HW systems designed to
  perform complex tasks employing strategies
  that mimic some aspect of human thought

• One can debate endlessly about whether a
  certain system is intelligent or not

• But to my mind, the key criterion is evolution: it
  is intelligent if it can learn (even if only a limited
  sense) and get better with time                   18
Not a Suitable Hammer for All Nails!
if the nature of computations required in a
   task is not well understood

   or there are too many exceptions to the

   or known algorithms are too complex or

then AI has the potential of offering an
   acceptable solution
Selected Applications
• Games: Chess, SimCity

• Image recognition

• Medical diagnosis

• Robots

• Business intelligence   20
      Sub-Categories of AI
• Expert systems
  – Systems that, in some limited sense, can
    replace an expert

• Robotics

• Natural language processing
  – Teaching computers to understand human
    language, spoken as well as written

• Computer vision                              21
            Selected Techniques
             • Artificial neural networks

             • Genetic algorithms

             • Rule-based systems

             • Fuzzy logic

Many times, any one of them can solve the problem at
hand, but at others, only the right one will do. Therefore,
it is important to have some appreciation of them all
           Neural Networks (1)
• Original inspiration was the human brain;
  emphasis now on usefulness as a
  computational tool

• Many useful NN paradigms, but scope of
  today's discussion limited to the feed-forward
  network, the most popular paradigm

            Neural Networks (2)
• Feed-forward Network:
  – It is a layered structure consisting of a number of
    homogeneous and simple (but nonlinear)
    processing elements

  – All processing is local to a processing element and
    is asynchronous

• During training the FN is forced to adjust its
  parameters so that its response to input data
  becomes closer to the desired response
         Genetic Algorithms (1)
• Based on Darwin's evolutionary principle of
  ‘survival of the fittest’

• GAs require the ability to recognize a good
  solution, but not how to get to that solution

          Genetic Algorithms (2)
• The procedure:
  – An initial set of random solutions is ranked in terms
    of ability to solve the problem at hand
  – The best solutions are then cross-bred and mutated
    to form a new set
  – The ranking and formation of new solutions is
    continued until a good enough solution is found or

        Rule-based Systems (1)
• Based on the principles of the logical reasoning
  ability of humans

• Components of an RBS:
  – Rule-base
  – Working memory
  – Rule interpreter

        Rule-based Systems (2)
• The design process:

  – An RBS engineer interviews the expert to acquire
    the comprehensive set of heuristics that covers the
    situations that may occur in a given domain

  – This set is then encoded in the form of IF-THEN
    structures to form the required RBS

              Fuzzy Logic (1)
• Based on the principles of the approximate
  reasoning faculty that humans use when faced
  with linguistic ambiguity

• The inputs and outputs of a fuzzy system are
  precise, only the reasoning is approximate

                  Fuzzy Logic (2)
• Parts of the knowledge-base of a fuzzy system:
  – Fuzzy rules
  – Fuzzy sets

• The output of a fuzzy system is computed by
  – The MIN-MAX technique for combining fuzzy rules
  – The centroid method for defuzzification

Now we know about a few techniques

Let’s now consider the situation when we
are given a particular problem and asked
to find an AI solution to that problem.

How do we determine the right technique
for that particular problem?

Selection of an Appropriate AI Technique
• A given problem can be solved in several ways

• Even if 2 techniques produce solutions of a
  similar quality, matching the right technique to a
  problem can save on time & resources

• Characteristics of an optimal technique:
  – The solution contains all of the required information
  – The solution meets all other necessary criteria
  – The solution uses all of the available (useful)
    knowledge                                         32
How do we determine the
suitability of a particular AI
technique for a given task
We look at the task’s requirements and then
see which technique fulfils those requirements
more completely – the one which does, is the
one we use!

Here are a few aspects of the task and the
techniques that we need to be aware off …
• Accuracy
• Explainability
• Response speed
• Scalability
                   • Learning curve
• Compactness
                   • Tolerance for complexity
• Flexibility
• Embedability     • Tolerance for noise in data
• Ease of use      • Tolerance for sparse data
                   • Independence from experts
                   • Development speed
                   • Computing ease          34
in action!
        Credit Card Issuance (1)
• Challenge. Increase the acceptance rate of
  card applicants who will turn out to be good
  credit risks

• Inputs. Applicant's personal and financial

• Output. Estimated yearly loss if application is
        Credit Card Issuance (2)
• Expert knowledge. Some rules of thumb are

• Data. Profiles & loss data available for 1+
  million applicants

• Suitable technique?

Determination of the Optimal Drug Dosage (1)

• Challenge. Warn the physician if she prescribes
  a dosage which is either too high or too low

• Inputs. Patient's medical record.
  Pharmaceutical drug dosage instructions

• Output. Warning along with reasons for the

Determination of the Optimal Drug Dosage (2)

• Data. Medical records of thousands of patients.
  Drug dosage instructions on dozens of

• Suitable technique?

Prediction of Airline Cabin Crew's Preferences (1)

• Challenge. Predict the future base/status
  preferences of the cabin crew of an airline. The
  predicted preferences will be used by the airline
  for forecasting its staffing and training

• Inputs. Crew's personal profiles. Preference
  history. Other data.

• Output. Predicted preference card for a date
  one year in the future                     40
Prediction of Airline Cabin Crew's Preferences (2)

• Expert knowledge. Some rules of thumb are

• Data. Available for the last four years for 8000
  crew members

• Suitable technique?

         The Right Technique

• Selection of the right AI technique requires
  intimate knowledge about the problem as well
  as the techniques under consideration

• Real problems may require a combination of
  techniques (AI and/or non-AI) for an optimal

A few more areas of AI

• Automatic machines that perform various tasks
  that were previously done by humans

• Example:
  – Pilot-less combat airplanes
  – Land-mine hunters
  – Autonomous vacuum-cleaners

• Components: Body structure, actuators, power-
  source, sensors, controller (the AI-based part)
    Autonomous Web Agents (1)
• Also known as mobile agents, softbots

• Computer program that performs various
  actions continuously, autonomously on behalf
  of their principal!

• Key component of the Semantic Web of

    Autonomous Web Agents (2)
• Multi-agent communities are being developed in
  which agents meet and represent the interests
  of their principals in negotiations or
  collaborations. Example:

  – Agents of a patient and a doctor get together to
    negotiate and select a mutually agreeable time,

      Decision Support Systems
• Interactive software designed to improve the
  decision-making capability of their users

• Utilize historical data, models to solve problems

• The do not make decisions - just assist in the

• They provide decision-makers with information
  via easy to manage reports, what-if scenarios,
  and graphics                               47
                  The Future?
• Get ready to see robots playing a bigger role in
  our daily lives
  – Robots will gradually move out of the industrial
    world and into our daily life, similar to the way
    computers did in the 80’s

• Decision support systems will become a bigger
  part of the professional life of doctors,
  managers, marketers, etc

• Autonomous land, air, sea vehicles controlled
  from 1000’s of miles away from the war zone
            Today’s Summary:
            Intelligent Systems
•   We looked at the distinguishing features of
    intelligent systems w.r.t. other software

•   We looked at the role of intelligent systems in
    scientific, business, consumer and other

•   We discussed several techniques for
    designing intelligent systems             49
             Next Lecture:
          (Data Management)
• To become familiar with the issues and
  problems related to data-intensive computing

• To become able to appreciate data
  management concepts and their evolution over
  the years