Backpropagation

Backpropagation
Fuzzy Logic
What is Fuzzy Logic?

1/30/2023 AIES 29
Sensitivity: Confidential (C2)
Fuzzy logic
• Fuzzy means uncertain, indefinite, vague, or unclear.
• It is a computing technique that is based on the degree of truth.
• A fuzzy logic system uses the input’s degree of truth and linguistic
variables to produce a certain output.
• This technique is different from boolean logic
• In boolean logic, two categories (0 and 1) are used to describe objects
• Example – the temperature in water served in glass may be
BL - High (1) or Low (0)
Fuzzy logic- very cold, very warm, or warm.

1/30/2023 AIES 30
Sensitivity: Confidential (C2)
Fuzzy Logic
• The inventor/father of fuzzy logic is Lotfi Zadeh
• Fuzzy Logic (FL) is a method of reasoning that resembles human
reasoning.
• The approach of FL imitates the way of decision making in humans
that involves all intermediate possibilities between digital values YES
and NO.
• The conventional logic block that a computer can understand takes
precise input and produces a definite output as TRUE or FALSE,
which is equivalent to human’s YES or NO.
• Fuzzy Logic in AI provides valuable flexibility for reasoning

1/30/2023 AIES 31
Sensitivity: Confidential (C2)
Why Fuzzy Logic?
• It solves the problem of uncertainty in the engineering field.
• When accurate reasoning is not available, it provides an accurate level
of reasoning.
• Fuzzy logic has a simple structure that is easy to understand.
• It is an effective way of controlling machines.
• It provides solutions to various industrial problems (especially
decision making).
• It requires little data to be executed.

1/30/2023 AIES 32
Sensitivity: Confidential (C2)
Fuzzy Logic Systems Architecture

1/30/2023 AIES 33
Sensitivity: Confidential (C2)
 Fuzzy Logic Systems Architecture
Fuzzification
• This component for transforming the system inputs, i.e., it converts the crisp number into
fuzzy steps.
• Crisp numbers are those inputs which are measured by the sensors and then fuzzification
passed them into the control systems for further processing
• This component divides the input signals into following five states in any Fuzzy Logic
system:
✔ Large Positive (LP)
✔ Medium Positive (MP)
✔ Small (S)
✔ Medium Negative (MN)
✔ Large negative (LN)

1/30/2023 AIES 34
Sensitivity: Confidential (C2)
Rule Base
▪ It is component used for storing the set of rules and the If-Then conditions given by the
experts used for controlling the decision-making systems.
Inference Engine
• It allows users to find the matching degree between the current fuzzy input and the rules
• After the matching degree, this system determines which rule is to be added according to
the given input field
Defuzzification
• takes the fuzzy set inputs generated by the Inference Engine, and then transforms them
into a crisp value
• The crisp value is a type of value which is acceptable by the user.

1/30/2023 AIES 35
Sensitivity: Confidential (C2)
Fuzzy Set
• A Fuzzy set is a set whose elements have degrees of membership
• A fuzzy set is a pair (A, µA)
• where A is a set
µA : A → [0, 1]
For all x ∈ A, µA(x) is called the grade/degree of membership of x
• Fuzzy set fully defined by membership function (µA)

1/30/2023 AIES 36
Sensitivity: Confidential (C2)
Membership Function
• The membership function is a function which represents the graph of fuzzy sets, and
allows users to quantify the linguistic term.
• It is a graph that defines how each point in the input space is mapped to membership
value between 0 and 1.
• A membership function for a fuzzy set A on the universe of discourse X is defined as
μA:X → [0,1].
• Here, each element of X is mapped to a value between 0 and 1. It is
called membership value or degree of membership. It quantifies the degree of
membership of the element in X to the fuzzy set A.

✔ x axis represents the universe of discourse.

✔ y axis represents the degrees of membership in the [0, 1] interval.

1/30/2023 AIES 37
Sensitivity: Confidential (C2)
Membership Function
A = {30,60,42,45} Degree of fastness =
µA = {(30,0),(60,1),(43.0.2),(45,0.5) 0 if speed(x) <= 40
speed(x) - 40/10 if 40 < speed (x) < 50
1 if speed(x) >= 50
Example –

x1 = 30 = 0 (30,0)
x2 = 60 = 1 (60,1)
x3 = 42 = 42 – 40/10 = 2/10 =0.2 (42,0.2)
x4 = 45 = 45-40/10 = 5/2 = 0. 5 (45,0.5)

1/30/2023 AIES 38
Sensitivity: Confidential (C2)
Application Areas of Fuzzy Logic
• The key application areas of fuzzy logic are as given −
• Automotive Systems
• Automatic Gearboxes, Four-Wheel Steering, Vehicle environment control,etc
• Consumer Electronic Goods
• Photocopiers, Still and Video Cameras, Television,etc
• Domestic Goods
• Microwave Ovens, Refrigerators, Toasters, Vacuum Cleaners, Washing
Machines, etc
• Environment Control
• Air Conditioners/Dryers/Heaters, Humidifiers, etc

1/30/2023 AIES 39
Sensitivity: Confidential (C2)
Advantages and Disadvantages of FLSs

• Advantages of FLSs
• Mathematical concepts within fuzzy reasoning are very simple.
• You can modify a FLS by just adding or deleting rules due to flexibility of fuzzy
logic.
• Fuzzy logic Systems can take imprecise, distorted, noisy input information.
• FLSs are easy to construct and understand.
• Fuzzy logic is a solution to complex problems in all fields of life, including
medicine, as it resembles human reasoning and decision making.
• Disadvantages of FLSs
• There is no systematic approach to fuzzy system designing.
• They are understandable only when simple.
• They are suitable for the problems which do not need high accuracy.

1/30/2023 AIES 40
Sensitivity: Confidential (C2)
1/30/2023 AIES 43