Java Smart Network Planning Artificial Intelligence AI

1
Java Smart Network Planning Artificial
Intelligence (AI)

• Zakeria Shaik
• MSc Network Systems

2
Introduction to AI What is Intelligence?
Intelligent taken as a whole consist of the
following skills. 1) The ability to reason. 2)
The ability to acquire and apply knowledge. 3)The
ability to manipulate and communicate ideas
3
(No Transcript)
4
The age of Intelligent Machines
1st Industrial Revolution The age of automation
machine extend and multiply mans physical
capabilities. 2nd Industrial Revolution The age
of Info TechMachine extend and multiply mans
mental capabilities. Information and Knowledge
Revolution The age of knowledge
Technology..Working Smarter, Not harder . How
do we make our system smarter?- The solution is
by building in Intelligence.
5
Definition of AI
.. The science of making machines do things that
would require intelligence if done by humans -
Marvin Minsky. AI is the part of the computer
science concerned with designing intelligent
computer systems - E.Feigenbaum. Systems that
can demonstrate human like reasoning capability
to enhance the quality of life and improve
business competitiveness - Japan-Spore AI
centre.
6
History of AI
Important research that laid the ground work of
AI In 1900-50s Formal grammar and language
theories. In 1920-30s Formalisation of
reasoning (Predicate calculus and propositional
logic) 1940-50sCybernetics-Communication in man
and machine. 1950sReality of Digital
computers(Mark I, ENIAC and UNIVAC) OthersInforma
tion theory, Neurological theories, Boolean
Algebra etc.
7
History Of AI
Dartmouth Conference
New Technology Support
Japan 5th Generation Computer
AI Winter
mid-1980s
1948
1970s - 80s
Time
8
Examples of AI

• Robots
• Chess-playing program
• Voice recognition system
• Speech recognition system
• Grammar checker
• Pattern recognition
• Medial diagnosis
• System malfunction rectifier

• Game Playing
• Machine Translation
• Resource Scheduling
• Expert systems (diagnosis,
  advisory,planning etc)
• Machine learning
• Intelligent interfaces

9
Problem with Search

• Search is one of the most powerful approaches to
  problem solving in AI.
• Search is a universal problem solving mechanism
  that
• Systematically explores the alternative
• Finds the sequence of steps towards a solution.
  
  

Problem space hypothesis All goal oriented
symbolic activities occur in a problem
space. Search in a problem space is claimed to be
a completely general model intelligence.
10
Defining a Search problem.
State Space described by an initial space and
the set of possible actions available
(operators). A path is any sequence of actions
that lead from one state to another. Goal test
applicable to a single state problem to determine
if it is the goal state. Path cost relevant if
more than one path leads to the goal, and we
want the shortest path.
11
Toy Problem
Vacuum problem as a single- state problem.

• Initial stateone of the problem shown above.
• Operators move left, move right,suck.
• Goal testNo dirt in any square.
• Path cost Each action cost 1.

12
Toy Problems 8-Puzzle Problem.
Initial State The location of each of the 8
tiles in one of the nine squares Operators
blank moves (1) Left (2) Right (3) Up (4)
Down Goal Test state matches the goal
configuration Path cost each step costs 1, total
path cost no. of steps
13
Search Strategies.
General Search Problem Criteria for evaluating
search strategies Blind (UN-informed) search
strategies ? Breadth-first search ?
Uniform cost search ? Depth-first search
? Depth-limited search ? Iterative deepening
search ? BI-directional search Comparing
search strategies Heuristic (informed) search
strategies
14
General Search Problem
Search tree representation.
15
Conclusion.
An agent perceives and acts in an environment. It
has an architecture and is implemented by a
program.
An ideal agent always chooses the action which
maximizes its expected performance, given the
percept sequence received so far.
An autonomous agent uses its own experience
rather than built-in knowledge of the
environment by the designer. An agent program
maps from a percept to an action and updates its
internal state.
16
Conclusion Cont.
Reflex agents respond immediately to percepts.
Goal-based agents act in order to achieve their
goal(s). Utility-based agents maximize their
own utility function. Representing knowledge is
important for successful agent design.
Some environments are more difficult for agents
than others. The most challenging environments
are inaccessible, non-deterministic,
non-episodic, dynamic, and continuous. eg. the
Robocup Challenge (Kitano, 1997)