Neural Networks And their Applications

Neural Networks

Abstract

This Article is whole about Neural Networks and their applications. The brief historical background of neural networks is provided. The term “Neural net” is explained and the reasons why we use or prefer neural networks over conventional methods. Some of the major applications of neural networks are explained. The connection between the artificial and the real thing is also investigated and explained.

Neural Networks

Brief History of Neural Networks

The concept of neural networks was come into being when the first model of neuron was created by two physiologists, McCulloch and Pitts in 1943.

Pitts
Pitts
McCulloch
McCulloch
 That neuron model has two inputs and a single output. McCulloch and Pitts noted that a neuron would active only if both of its inputs were active. The weights for each input were equal, and the output was binary. Until the inputs summed up to a certain threshold level, the output would remain zero. The McCulloch and Pitts' neuron has become known today as a logic circuit. In the 1950's, Rosenblatt's work resulted in a two-layer network, The Perceptron (a kind of a single-layer artificial network with only one neuron), which was capable of learning certain classifications by adjusting connection weights. Although the perceptron was successful in classifying certain patterns, it had a number of limitations. It was not able to solve the classic XOR (exclusive or) problem. Such limitations led to the decline of the field of neural networks. However, the perceptron had laid foundations for later work in neural computing.
perceptron
perceptron

In the early 1980's, researchers showed renewed interest in neural networks. Recent work includes Boltzmann machines, Hopfield nets, competitive learning models, multilayer networks, and adaptive resonance theory models.

What is a Neural Net?

•    A neural net is an artificial representation of human brain that tries to simulate its learning functions. An Artificial Neural Network (ANN) is often called “Neural Network” or simply Neural Net.
•    Traditionally, the word neural network is referred to a network of Biological neurons in the nervous system that process and broadcast information.
•    Artificial neural network is an interrelated group of artificial neurons that uses a mathematical model or computational model for information processing based on a connectionist approach to computation.
•    Artificial neural networks are composed of interrelating artificial neurons which may share some properties of biological neural networks.
•    Artificial neural networks is a network of simple processing neurons which can reveal composite global performance, determined by links between processing elements(neurons) and elements parameters.
•    Artificial neural network is a system that changes its structure based on internal or external information that flows through the network.
•    Artificial neural networks are an effort at modeling the information processing capabilities of nervous systems.

Why Use Neural Networks?

Neural networks have remarkable ability to derive meaning from complicated data; can be used to extract patterns and detect trends that are too complex to be noticed by either humans or other computer techniques. A trained neural network can be thought of as an "expert" in the category of information it has been given to analyze. The conventional computers are not so good for interacting with noisy data or data from environment but the neural networks help where we cannot formulate an algorithmic solution.
Neural Networks are a form of multiprocessing computer system, with
•    Simple processing elements
•    A high degree of interconnection
•    Simple scalar massages, and
•    Adaptive interaction between elements (neurons).
Neural networking is the science of creating computational solutions modeled after the brain.  Like the human brain, neural networks are trainable-once they are taught to solve one complex problem, they can apply their skills to a new set of problems without having to begin the learning process from scrape. These neural networks have a strong capability to work just like a human brain. These actions are performed by interconnected group of artificial neurons that uses a mathematical model for information manipulation.
Neural networking

Neural Network Applications

Neural networks have been successfully applied to broad spectrum of data-intensive applications. Neural Networks can be applied to a wide variety of problems, from breast cancer detection to classification of satellite imagery.There are many different types of Neural Networks, each of which has different strengths particular to their applications. The abilities of different networks can be related to their structure, dynamics and learning methods.
Neural Networks offer improved performance over conventional technologies in areas which include: Machine Vision, Robust Pattern Detection, Signal Filtering, Virtual Reality, Data Segmentation, Data Compression, Data Mining, Text Mining, Artificial Life, Adaptive Control, Optimization and Scheduling, Complex Mapping and more.

Neural networks in medicine

Artificial Neural Networks (ANN) has a great work to do with the medicine field. It is believed that they will receive extensive application to biomedical systems in the next few years. At the moment, the research is mostly on modeling parts of the human body and recognizing diseases from various scans (e.g. cardiograms, CAT scans, ultrasonic scans, etc.).

Modeling and Diagnosing the Cardiovascular System

Neural Networks are practically used to model the human cardiovascular system and give best results. Diagnosis can be attained by building a model of the cardiovascular system of an individual and comparing it with the real time physiological measurements taken from the patient. If this routine is carried out regularly, potential harmful medi cal conditions can be detected at an early stage and thus make the process of hostility the disease much easier.
A model of an individual's cardiovascular system must imitate the relationship among physiological variables (i.e., heart rate, systolic and diastolic blood pressures, and breathing rate) at different physical activity levels. If a model is modified to an individual, then it becomes a model of the physical condition of that individual. The simulator will have to be able to adapt the features of any individual without the management of an expert. This calls for a neural network.
Another reason that justifies the use of ANN technology is the ability of ANNs to provide sensor fusion which is the combining of values from several different sensors. Sensor fusion enables the ANNs to learn complex relationships among the individual sensor values, which would otherwise be lost if the values were individually analyzed. In medical modeling and diagnosis, this implies that even though each sensor in a set may be sensitive only to a specific physiological variable, ANNs are capable of detecting complex medical conditions by fusing the data from the individual biomedical sensors.

Electronic noses

ANNs are used experimentally to implement electronic noses. Electronic noses have several prospective applications in telemedicine. Telemedicine is the practice of medicine over long distances via a communication link. The electronic nose would identify odours in the remote surgical environment. These identified odours would then be electronically transmitted to another site where a door generation system would recreate them.

Instant Physician

An application developed in the mid-1980s called the "instant physician" trained an auto associative memory neural network to store a large number of medical records, each of which includes information on symptoms, diagnosis, and treatment for a particular case. After training, the net can be presented with input consisting of a set of symptoms; it will then find the full stored pattern that represents the "best" diagnosis and treatment.

Neural Networks in business

Business is a abstracted field with several general areas of specialization such as accounting or financial analysis. Almost any neural network application would fit into one business area or financial analysis. Some of the basic applications of neural networks in business field are applicable in marketing and credit evaluation. Neural networks made business faster.

Marketing

The marketing application has been incorporated with a neural network system. The Airline Marketing Tactician (a trademark abbreviated as AMT) is a computer system made of various intelligent technologies including expert systems. A feed forward neural network is integrated with the AMT and was trained using back-propagation to assist the marketing control of airline seat allocations. Additionally, the application's environment changed quickly and frequently, which required a continuously adaptive solution. The system is used to screen and recommend booking advice for each departure. Such information has a direct impact on the productivity of an airline and can provide a technological advantage for users of the system. [Hutchison & Stephens, 1987]
Whereas it is significant that neural networks have been applied to this problem, it is also essential to see that this intelligent technology can be integrated with expert systems and other approaches to make a functional system. Neural networks played a major role in this integration.

Credit Evaluation

The HNC Company, founded by Robert Hecht-Nielsen, has developed several neural network applications. One of them is the Credit Scoring system which increases the productivity of the existing model up to 27%. The HNC neural systems were also applied to advance monitoring. A neural network automated advance insurance underwriting system was developed by the Nestor Company. This system was trained with 5048 applications of which 2597 were certified. The data related to property and borrower qualifications. In a conservative mode the system agreed on the underwriters on 97% of the cases. In the liberal model the system agreed 84% of the cases. This is system run on an Apollo DN3000 and used 250K memory while processing a case file in approximately 1 sec.

Conclusion

The computing world has a lot to achieve from neural networks. Their ability to learn by example makes them very flexible and powerful. There is no more complexity of formulating an algorithm and no need to understand the internal functionality of actions performed. Neural networks is a great step towards the success of virtual reality and its highly applications in other major fields of real life. Neural networks replaced many conventional methods and gave significant performance than ever before, but there are some tasks for which neural networks will never replace the conventional methods.
Finally, I would like to state that even though neural networks have a huge potential we will only get the best of them when they are integrated with computing, AI, fuzzy logic and related subjects.
أحدث أقدم