1. INTRODUCTION TO
ARTIFICIAL INTELLIGENCE
USING FUZZY LOGIC AND
NEURAL NETWORK
By: Mr. Snehal Dewaji Gongle
Electronics & Communication
Engg.
MIET Gondia, Maharashtra
Email:
gonglesnehal4@gmail.com
2. Contents
Introduction to Artificial Intelligence
Artificial Intelligence using Fuzzy and NN
Fuzzy Logic
Traditional Logic v/s Fuzzy Logic
Neural Network
Biological aspect for Architecture of Artificial
Neural Network
Fuzzy-Neural Hybrid Network
Conclusion and Reference
3. Intro to Artificial Intelligence:
The branch of computer science concerned with
making computers behave like humans. The term
was coined in 1956 by John McCarthy at the
Massachusetts Institute of Technology.
Machines that perceive, understand and
react to their environment in other words
Machines that think is due to Artificial
Intelligence.
Definition:
Example:
The Automatic Car Parking:
The Auto-pilot mode in
planes:
4. Artificial Intelligence using Fuzzy
and Neural Network:
AI applications built on logic
Induction, semantic queries, system of logic
These sequence, systems or queries are solved
on the basics of Fuzzy Sets.
Computers as same as humans
As humans connect their thoughts by the flow of
neuronal data transfer
Same as the neural data transfer the Artificial
Neural Network transfer the data in computers.
Computers much better than humans
The accuracy rate in the calculation part is high as
compared.
5. Fuzzy logic:
Definition of fuzzy logic
o A form of knowledge representation suitable for
notions that cannot be defined precisely, but
which depend upon their contexts.
History:
In the year 1965 Lotfi Zadeh, published his famous
paper (Fuzzy sets). Zadeh extended the work on
possibility theory into a formal system of mathematical
logic, and introduced a new concept for applying natural
language terms.
This new and multi-valued logic for representing and manipulating
fuzzy terms was called fuzzy logic.
7. Fuzzy logic is based on the idea that all
things admit of degrees or can be drew
into sets . Temperature, height, speed,
distance, beauty – all come on a sliding
scale.
We can have different characteristics of players
on basis of:
Strength: strong, medium, weak
Aggressiveness: meek, medium, nasty
If meek and attacked, run away fast
If medium and attacked, run away slowly
If nasty and strong and attacked, attack back
Fuzzy set theory:
An object is in a set by matter of
degree
1.0 => in the set
0.0 => not in the set
0.0 < object < 1.0 => partially in the
setExample:
8. Neural Network:
Neural Networks are used for:
pattern recognition (objects in images,
voice, medical diagnostics for diseases,
etc.)
exploratory analysis (data mining)
predictive models and control
A method of computing, based on
the interaction of multiple
connected processing elements
Definition:
NN consist of inputs, outputs,
hidden data and weights
9. Biological aspect for architecture of
Artificial Neural Network:
Such as neuron has many no. Of inputs
(dendrites) and a single output (axon) in that
format we design the neural network consist of
Synapse
Axon
Cell body
Dendrites
Neuron
10. Fuzzy-Neural Hybrid Network:
For example, while neural networks are good at
recognizing patterns, they are not good at explaining how
they reach their decisions.
Fuzzy logic systems, which can reason with imprecise
information, are good at explaining their decisions but they
cannot automatically acquire the rules they use to make
those decisions.
These limitations have been a central driving force behind
the creation of intelligent hybrid systems where two or more
techniques are combined in a manner that overcomes
individual techniques even after they are hard at training
period but lately they are excellent in accuracy.
In Hybrid network both the Fuzzy Logic and
Neural Network are taken and combined
together to form Fuzzy-Neural Network.
11. • Transfer function g is linear
• If wk=0 then wk AND xk=0 while if wk=1 then wk
AND xk= xk independent of xk
y=OR(x1 AND w1, x2 AND w2 … xn AND wn)
OR:[0,1]x[0,1]n->[0,1]
OR Fuzzy-Neural:
y=AND(x1 OR w1, x2 OR w2 … xn OR wn)
AND:[0,1]x[0,1]n->[0,1]
And Fuzzy-Neural:
y = g(w.x)
12. Conclusion and Reference:
Fuzzy logic provides a
way to represent linguistic and
subjective attributes of the real world in
computing.
Yes Neural Networks are hard at the
training part, and also they are time
consuming but once it is trained its
accuracy is great
With the help of Fuzzy and Neural
Network the Artificial Intelligence can be
developed.
Reference:
L. Smith, "An Introduction to Neural Networks", URL:
http://www.cs.stir.ac.uk/~lss/NNIntro/InvSlides.html