sc31x - ARNAB

runmidgeAI and Robotics

Oct 20, 2013 (3 years and 10 months ago)

67 views


Soft computing is a field of computer
science which makes use of inexact
solutions for problems which has no
known method to compute an exact
solution


It uses imprecision, uncertainty, partial
truth, and approximation as input


Hard computing


Deals with precise values


Accurate output is needed


Useful in critical systems


Soft computing



Deals with assumptions


Accuracy is not necessary


Useful for
routine,control
,
decison

making tasks




Fuzzy Systems


Neural Networks


Evolutionary Computation



Machine Learning


Probabilistic Reasoning


Founded in 1940


Artificial neural network mimics the
biological neuron network in function


Warren S
Mullcock


Based on fuzzy set theory and fuzzy logic


Uses numeric ranges of sets (fuzzy sets )
to measure and represent the logical
evaluations of partially accurate findings


Most applications in control and decision
making


Founded by
Lofti

A
Zadeh



Pattern recognition
based on training
data,Classification

supervised by
instructor.


Unsupervised machine
learning is also used
where the machine
learns from the given
data by detecting
patterns.

Orange

Apple

?

Instructor


Models based on human reasoning.


Closer to human thinking and biologically
inspired


Models can be


Linguistic


Comprehensible


Fast when computing


Effective in practice.


Heavy
industry


R
obotic
arms,
Humanoid robots



Home appliances


Washing
machines, ACs,
Refrigerators
,
cameras



Automobiles


Travel
Speed Estimation, Sleep
Warning Systems, Driver
-
less
cars



Spacecrafts


Maneuvering
of a Space
Shuttle(FL), Optimization of Fuel
-
efficient Solutions for
space craft




If you are viewing this presentation from
slideshare

then: