Skip to main content

Fuzziness in Neural Networks

Artificial neural network (ANN) is a network of efficient computing systems the central theme of which is borrowed from the analogy of biological neural networks. ANNs are also named as “artificial neural systems,” parallel distributed processing systems,” “connectionist systems.” ANN acquires large collection of units that are interconnected in some pattern to allow communications between units. These units, also referred to as nodes or neurons, are simple processors which operate in parallel.

Every neuron is connected with other neuron through a connection link. Each connection link is associated with a weight having the information about the input signal. This is the most useful information for neurons to solve a particular problem because the weight usually inhibits the signal that is being communicated. Each neuron is having its internal state which is called the activation signal. Output signals, which are produced after combining the input signals and the activation rule, may be sent to other units. It also consists of a bias ‘b’ whose weight is always 1.

Neural Network Model

Why to use Fuzzy Logic in Neural Network

As we have discussed above that every neuron in ANN is connected with other neuron through a connection link and that link is associated with a weight having the information about the input signal. Hence we can say that weights have the useful information about input to solve the problems.

Following are some reasons to use fuzzy logic in neural networks −

  • Fuzzy logic is largely used to define the weights, from fuzzy sets, in neural networks.

  • When crisp values are not possible to apply, then fuzzy values are used.

  • We have already studied that training and learning help neural networks perform better in unexpected situations. At that time fuzzy values would be more applicable than crisp values.

  • When we use fuzzy logic in neural networks then the values must not be crisp and the processing can be done in parallel.

Fuzzy Cognitive Map

It is a form of fuzziness in neural networks. Basically FCM is like a dynamic state machine with fuzzy states (not just 1 or 0).

Difficulty in using Fuzzy Logic in Neural Networks

Despite having numerous advantages, there is also some difficulty while using fuzzy logic in neural networks. The difficulty is related with membership rules, the need to build fuzzy system, because it is sometimes complicated to deduce it with the given set of complex data.

Neural-Trained Fuzzy Logic

The reverse relationship between neural network and fuzzy logic, i.e., neural network used to train fuzzy logic is also a good area of study. Following are two major reasons to build neuraltrained fuzzy logic −

  • New patterns of data can be learned easily with the help of neural networks hence, it can be used to preprocess data in fuzzy systems.

  • Neural network, because of its capability to learn new relationship with new input data, can be used to refine fuzzy rules to create fuzzy adaptive system.

Examples of Neural-Trained Fuzzy system

Neural-Trained Fuzzy systems are being used in many commercial applications. Let us now see a few examples where Neural-Trained Fuzzy system is applied −

  • The Laboratory for International Fuzzy Engineering Research (LIFE) in Yokohama, Japan has a back-propagation neural network that derives fuzzy rules. This system has been successfully applied to foreign-exchange trade system with approximately 5000 fuzzy rules.

  • Ford Motor Company has developed trainable fuzzy systems for automobile idle-speed control.

  • NeuFuz, software product of National Semiconductor Corporation, supports the generation of fuzzy rules with a neural network for control applications.

  • AEG Corporation of Germany uses neural-trained fuzzy control system for its water – and energy conserving machine. It is having total of 157 fuzzy rules.



Anurag Rana

Comments

Popular posts from this blog

Standard and Formatted Input / Output in C++

The C++ standard libraries provide an extensive set of input/output capabilities which we will see in subsequent chapters. This chapter will discuss very basic and most common I/O operations required for C++ programming. C++ I/O occurs in streams, which are sequences of bytes. If bytes flow from a device like a keyboard, a disk drive, or a network connection etc. to main memory, this is called   input operation   and if bytes flow from main memory to a device like a display screen, a printer, a disk drive, or a network connection, etc., this is called   output operation . Standard Input and Output in C++ is done through the use of  streams . Streams are generic places to send or receive data. In C++, I/O is done through classes and objects defined in the header file  <iostream> .  iostream  stands for standard input-output stream. This header file contains definitions to objects like  cin ,  cout , etc. /O Library Header Files There are...

Data Warehousing - An Overview

Anurag Information Technology (IT) has historically influenced organizational performance and competitive standing. The increasing processing power and sophistication of analytical tools and techniques have put the strong foundation for the product called data warehouse. There are a number of reasons that any organization should consider a data warehouse, which can be the critical tool for maximizing the organization’s investment in the information it has collected and stored throughout the enterprise. IT managers need to understand the rationale and benefits of data warehouses because they may need to design and implement, or procure this kingpin of business intelligence. The data warehouses are supposed to provide storage, functionality and responsiveness to queries beyond the capabilities of today's transaction-oriented databases. Also data warehouses are set to improve the data access performance of databases. Traditional databases balance the requirement of data access w...

Genotype Representation

Binary Representation This is one of the simplest and most widely used representation in GAs. In this type of representation the genotype consists of bit strings. For some problems when the solution space consists of Boolean decision variables – yes or no, the binary representation is natural. Take for example the 0/1 Knapsack Problem. If there are n items, we can represent a solution by a binary string of n elements, where the x th  element tells whether the item x is picked (1) or not (0). For other problems, specifically those dealing with numbers, we can represent the numbers with their binary representation. The problem with this kind of encoding is that different bits have different significance and therefore mutation and crossover operators can have undesired consequences. This can be resolved to some extent by using  Gray Coding,  as a change in one bit does not have a massive effect on the solution. Real Valued Representation For problems where we want to define ...