UNIT 3

AN INTRODUCTION TO THE NEURO-FUZZY SYSTEM

In the field of artificial intelligence, neuro-fuzzy refers to combinations of artificial neural networks and fuzzy logic. Neuro-
Fuzzy Hybrid System is a combination of Neural Network and Fuzzy Logic. Neuro-fuzzy hybridization results in a hybrid
intelligent system that synergizes these two techniques by combining the human-like reasoning style of fuzzy systems with the
learning and connectionist structure of neural networks. Neuro-fuzzy hybridization is widely termed as the fuzzy neural network
(FNN) or neuro-fuzzy system (NFS) in the literature. Neuro-fuzzy system (the more popular term is used henceforth)
incorporates the human-like reasoning style of fuzzy systems through the use of fuzzy sets and a linguistic model consisting of a
set of IF-THEN fuzzy rules. The main strength of neuro-fuzzy systems is that they are universal approximators with the ability
to solicit interpretable IF-THEN rules.

STRENGTH OF NFHS:

The strength of neuro-fuzzy systems involves two contradictory requirements in fuzzy modelling:
interpretability versus accuracy.
• The learning procedure is constrained to ensure the semantic properties of the underlying fuzzy system.
• A neuro-fuzzy system based on an underlying fuzzy system is trained by means of a data-driven learning method derived from
neural network theory.
This heuristic only takes into account local information to cause local changes in the fundamental fuzzy system.

SPECIAL THREE-LAYER:
o The first layer corresponds to the input variables.
o The second layer symbolizes the fuzzy rules.
o The third layer represents the output variables.

Genetic fuzzy systems are fuzzy systems constructed by using genetic algorithms or genetic programming, which mimic the
process of natural evolution, to identify its structure and parameter.

A hybrid intelligent system denotes a software system which employs, in parallel, a combination of methods and techniques
from artificial intelligence .

Fuzzy Logic or Fuzzy Set Theory: - Fuzzy means not clear, distinct, precise or blurred (with unclear outline).

 It is a flexible machine learning technique.

 Fuzzy logic deals with uncertainty or vagueness existing in a system and formulating fuzzy rules to find a solution to
problems.
 Fuzzy logic use values between 0 and 1.

 Fuzzy set also consist of Fuzzy rule base to perform approximate reasoning somewhat similar to the human brain.
 Example of Fuzzy logic: - For automatic breaking system the traditional values are taken as either 0 or 1.

Central driving force for the creation of hybrid soft computing systems:

 Every soft computing technique has particular computational parameters which make them suited for a particular
problem and not for others.
 ability to learn & decision making

 Neural Networks are good at recognizing patterns but they are not good at explaining how they reach their decisions.

 Fuzzy logic is good at explaining the decisions but cannot automatically acquire the rules used for making the decision.

 These limitations act as a central driving force for the creation of hybrid soft computing systems where two or more
techniques are combined in a suitable manner that overcomes the of individual techniques.

 The aim is to build highly automated, intelligent machines for the future generations using all of these techniques.

 Hybrid System: - A Hybrid Intelligent System is one that combines at least two intelligent technologies.

 For example, combining a neural network with a fuzzy system results in a hybrid neuro-fuzzy system.

 Hybridization: The main aim of the concept of hybridization is to overcome the weakness in one technique while applying
it and bringing out the strength of the other technique to find a solution by combining them.

 Neuro-fuzzy hybrid system (NFHS): - Proposed by J.S.R Jang (Jyh-Shing Roger Jang) in the early '90s.

 Neuro-Fuzzy hybridization is widely termed as Fuzzy Neural Network (FNN) or Neuro-Fuzzy System(NFS).

 NFHS is a learning mechanism that utilizes the training and learning algorithms from neural networks to find
parameters of a fuzzy system.

 Neuro-Fuzzy Hybrid System is a combination of fuzzy system and neural network.

 The human-like reasoning style of fuzzy systems is incorporated by the use of

. Fuzzy sets
. Linguistic model
. along with IF-THEN fuzzy rules
Comparison of Fuzzy Systems with Neural Networks

 A black box is a device, system or object which can be viewed in terms of its inputs and outputs without any knowledge of
its internal workings.

THE ARCHITECTURE OF THE NEURO - FUZZY HYBRID SYSTEM

 The architecture is a three-layer feedforward neural network model.

 First layer corresponds to the input variables.
 Second layer corresponds to the fuzzy rules.
 Third layer corresponds to the output variables.
 Classification of the neuro-fuzzy hybrid system

 NFS are classified into the following two categories:

1. Cooperative NFSs
2. General Neuro-fuzzy hybrid systems

Cooperative NFS: Fuzzy system is governed by fuzzy IF-THEN rules.

1. A fuzzy system is a set of fuzzy rules that convert inputs to outputs.

2. A fuzzy rule is defined as a conditional statement in the form: IF x is A. THEN y is B. where x and y are linguistic
variables; A and B are linguistic values determined by fuzzy sets on the universe of discourse X and Y, respectively.
3. Linguistic variables: variable whose values are words or sentences rather than numbers. For E.g., Speed, Temp. and
service.
4. Linguistic value: Values or terms used to describe the linguistic variables. For E.g., for speed (slow, fast, faster), for
temperature (cool, warm, hot), for service (good, poor, excellent.).
5. IF temperature IS hot THEN Speed up fan.

6. ANN attempt to learn parameters from the fuzzy system.

7. FNN learns "fuzzy set" from the given "training data". This is done by fitting membership function with a neural
network; fuzzy sets then being determined offline.
8. membership function (MF) is a curve that defines how each point in the input space is mapped to a membership value
(or degree of membership) between 0 and 1.

General Neuro-fuzzy hybrid systems:

1. Architecture of General Neuro-Fuzzy Hybrid Systems

2. Advantage of general NFHS: there is no communication between NN and FS.
3. The rule base of fuzzy system is assumed to be a NN.
4. Fuzzy sets are regarded as weights.
5. And the rules and input, output variables as Neurons.
6. The choice to include or discard neurons can be made In learning step.
7. Fuzzy knowledge base is represented by neurons of NN.
8. Membership functions expressing the linguistic terms Of the inference rule should be formulated for building Fuzzy
controller.
Advantages of Neuro-fuzzy hybrid systems:

1. It can handle any kind of information (numeric, linguistic, logical, etc.)

2. It can manage imprecise, partial, vague or imperfect information.

3. It has self-learning, self-organizing and self-tuning capabilities.

4. It doesn’t need prior knowledge of relationships of data.

Areas of Applications for the use of Hybrid System:

 Engineering Design
 Stock market analysis and prediction
 Medical diagnosis
 Process control
 Credit card analysis