Conventional problem solving. These machines solve a

Conventional
Vs Intelligent Computing

Conventional
computing
Conventional
computing is used by Von Neumann computers . These are the machines
that follows an already described set of instructions to process
data. These
machines
use
an
intellectual
approach to problem solving. These
machines
solve a
problem
sequentially,
meaning one
task at a time. The
problem
is
coded in program and data structures.
The
way the problem is to solved is
required and
written
unambiguously.

We Will Write a Custom Essay Specifically
For You For Only $13.90/page!


order now

These
machines are completely
predictable. Any
malfunction
is due to a software or hardware fault.

Problems
With The Conventional Computers :-

Not
able to recognise patterns.

Not
able to manage the different
kind of data
obtained in the real world.

Not
able
to express the “how and
why” questions in
a problem.

Only
operate within the parameters that were programmed into it.

Intelligent
Computers

An
intelligent system is a machine interconnected to other computers
having capacity to gather and analyse data and communicate with
other systems. Other criteria for intelligent systems include
the capacity to learn from experience, security, connectivity, the
ability to adapt according to current data and the capacity for
remote monitoring and management.

The
goal of intelligent computing is to understand the principles that
make intelligent behaviour possible, in natural or artificial
systems. The main hypothesis is that reasoning is computation. The
central engineering goal is to specify methods for the design of
useful, intelligent artefacts.

Many
techniques used in intelligent computing are neural
networks, fuzzy logic, genetic algorithms, and intelligent agents,
etc.

Advantages

machines
will be able to do jobs that require detailed instructions

mental
alertness and decision making capabilities

less
injuries and stress to human beings

Applications:-

game
playing by making them more realistic.

Speech
recognition

Understanding
natural language

Machine
learning

Intelligent
agents

Intelligent
Agents are
applications that perform repetitive tasks.The
concept of intelligent agent is central in intelligent
computing.
An agent perceives its environment through percept and acts through
actuators. Agents can improve their performance through learning.
Types
of agents:-

Reflex
agents, model-based agents, goal- based agents, utility-based agents
, learning
agents.

Utility-based
agents

Sometimes
achieving the desired goal is not enough. We may look for quicker,
safer, cheaper trip to reach a destination.

Agent
happiness should be taken into consideration. We call it utility.

A
utility function is the agent’s performance measure

Because
of the uncertainty in the world, a utility agent choses

the
action that maximizes the expected utility.

Goal-based
agents

Knowing
the current state of the environment is not enough. The agent needs
some goal
information.

Agent
program combines the goal information with the envi- ronment model
to choose the actions that achieve that goal.

Consider
the future with “What will happen if I do A?”

Flexible
as knowledge supporting the decisions is explicitly rep-

resented
and can be modified.

Learning
agents

• Four
conceptual components:

–  Learning
element: responsible for making improvements

–  Performance
element: responsible for selecting external ac-

tions.
It is what we considered as agent so far.

–  Critic:
How well is the agent is doing w.r.t. a fixed perfor-

mance
standard.

–  Problem
generator: allows the agent to explore.

Learning
Agents

These
have advantage that they first in the unknown environments and then
learn form their doings. The learning element in these uses feedback
form ‘critic’ on how the agent is doing and decides how the
performance element should be modified to do better in the future.

Conclusion

Intelligent
computing and conventional computing are not competing but complement
each other. There are tasks are more suited to an algorithmic
approach like arithmetic operations and tasks that are more suited to
neural networks. Even more, a large number of tasks, require systems
that use a combination of the two approaches (normally a conventional
computer is used to supervise the neural network) in order to perform
at maximum efficiency.