Artificial Intelligence (AI) is the buzzword there days, wherever we go. However some of the fundamentals / foundations required to program AI remains same as in Embedded Systems. The purpose of this talk is to introduce participants what an Artificial System is, how is it different from conventional system programming. It will provide a basic view of AI architecture and introduce audience with technologies / languages / tools. By the end of the talk audience will get basic knowledge of how AI system can be implemented.

1. Artificial Intelligence
Introduction

2. What is AI ?
• According to the father of Artificial
Intelligence, John McCarthy, it is “The science
and engineering of making intelligent
machines, especially intelligent computer
programs”.
• Any machine thinks out side of its program &
behaves like an intelligent human being

3. What to achieve with AI
• To create expert systems with human
intelligence such as learning , reasoning ,
applying & problem solving.

4. What disciplines contribute to AI

5. Applications of AI
• Games
• Natural language processing
• Expert systems
• Vision systems
• Speech recognition
• Hand writing recognition
• Intelligent Robots

6. What is Intelligence ?
• The ability of a system to calculate, reason,
perceive relationships and analogies, learn
from experience, store and retrieve
information from memory, solve problems,
comprehend complex ideas, use natural
language fluently, classify, generalize, and
adapt new situations.

7. Types of Intelligence
• Linguistic ( human tongue)
• Musical ( human ear)
• Logical ( human thinking)
• Spatial (human eyes & imagination)
• Bodily –kinesthetic ( human bodily
movements)
• Intra-personal ( human self realization)
• Interpersonal (understanding others
emotions)

8. Constituents of Intelligence
• Learning
• Perception
• Reasoning
• Problem solving
• Linguistic intelligence

9. Constituents Contd…

10. Constituents “Learning”
• Activity of Gaining knowledge or skill by
studying , practicing , being taught or experience
– Auditory (listening)
– Episodic ( a sequence of events)
– Motor ( bodily movement like writing)
– Observational
– Perceptual ( remembering past events)
– Relational ( remembering past event & acting now)
– Spatial ( visualization)
– Stimulus Response ( response to certain stimulus)

11. Constituents “Perception”
• It is the process of acquiring, interpreting,
selecting, and organizing sensory information
• Perception presumes sensing. In humans,
perception is aided by sensory organs. In the
domain of AI, perception mechanism puts the
data acquired by the sensors together in a
meaningful manner

12. Constituents “Reasoning”
• It is the set of processes that enables us to
provide basis for judgement, making
decisions, and prediction
– Inductive
• It conducts specific observations to
makes broad general statements
– Deductive
• It starts with a general statement and examines
the possibilities to reach a specific, logical
conclusion

13. Constituents “Problem Solving”
• It is the process in which one perceives and
tries to arrive at a desired solution from a
present situation by taking some path, which
is blocked by known or unknown hurdles
• Problem solving also includes decision making,
which is the process of selecting the best
suitable alternative out of multiple
alternatives to reach the desired goal are
available

14. Constituents “Linguistic Intelligence ”
• It is one’s ability to use, comprehend,
speak, and write the verbal and written
language. It is important in interpersonal
communication

15. Classification -AI

16. System Composition -AI
• System comprises
– Agent
• Perceives environment through sensors & acts
on the environment through effectors
– Environment

17. System Composition-AI Contd …

18. Agent-Terminology
• Performance Measure
– It is the criteria, which determines how successful an
agent is.
• Behavior
– It is the action that agent performs after any given
sequence of percepts.
• Percept
– It is agent’s perceptual inputs at a given instance.
• Percept Sequence
– It is the history of all that an agent has perceived till date.
• Agent Function
– It is a map from the precept sequence to an action

19. Ideal Rational Agent
• Capability of doing expected actions to
maximize its performance measure

20. Agent Structure
• Agent = Architecture + Agent Program
• Architecture = the machinery that an
agent executes on.
• Agent Program = an implementation of
an agent function.

21. Simple Reflex Agent
• It choose actions only based on the
current percept.
• It is rational only if a correct decision is
made only on the basis of current
precept.
• Its environment is completely observable

22. Simple Reflex Agent Contd…

23. Model Reflex Agent
• It uses a model of the world to choose their
actions. They maintain an internal state.
• Model − The knowledge about “how the things
happen in the world”.
• Internal State − It is a representation of
unobserved aspects of current state depending
on percept history.
• Updating the state requires the information
about −
• How the world evolves.
• How the agent’s actions affect the world

24. Model Reflex Agent Contd…

25. Goal Based Agent
• It chooses its actions in order to achieve
goals.
• Goal-based approach is more flexible than
reflex agent since the knowledge supporting
a decision is explicitly modeled, thereby
allowing for modifications.
• Goal − It is the description of desirable
situations

26. Goal based Agent Contd…

27. Utility Based Agent
• It chooses actions based on a preference
(utility) for each state.
• Goals are inadequate when −
– There are conflicting goals, out of which only few
can be achieved.
– Goals have some uncertainty of being achieved
and you need to weigh likelihood of success
against the importance of a goal.

28. Utility based Agent Contd…

29. Nature of Environment
• Real
– Continuous Interaction with Real world
• Artificial
– Other systems like key board , database etc..

30. Properties of Environment
• Discrete / Continuous − If there are a limited number of
distinct, clearly defined, states of the environment, the
environment is discrete (For example, chess); otherwise
it is continuous (For example, driving).
• Observable / Partially Observable − If it is possible to
determine the complete state of the environment at
each time point from the percepts it is observable;
otherwise it is only partially observable.
• Static / Dynamic − If the environment does not change
while an agent is acting, then it is static; otherwise it is
dynamic.

31. Properties of Environment Contd...
• Single agent / Multiple agents − The environment
may contain other agents which may be of the same
or different kind as that of the agent.
• Accessible / Inaccessible − If the agent’s sensory
apparatus can have access to the complete state of
the environment, then the environment is accessible
to that agent.

32. Properties of Environment Contd...
• Deterministic / Non-deterministic − If the next state of
the environment is completely determined by the
current state and the actions of the agent, then the
environment is deterministic; otherwise it is non-
deterministic.
• Episodic / Non-episodic − In an episodic environment,
each episode consists of the agent perceiving and then
acting. The quality of its action depends just on the
episode itself. Subsequent episodes do not depend on
the actions in the previous episodes. Episodic
environments are much simpler because the agent does
not need to think ahead

33. Research Areas AI

34. Programming Languages -AI
• Python
– Simple
– Libs like Numpy(scientific computaion)
Scypy(Advanced computing) Pybrian(machine
learning)
• Java
• C++
– Speed , talk to hardware level
• Lisp
• Prolog

35. Thank You
Contact Info: sales@wdbsystems.com
Visit us at www.wdbsystems.com