Neural Networks

Electrical Electronics Engineering

Neural networks, often referred to as artificial neural networks (ANNs), are sophisticated computational models inspired by the structure and function of the human brain’s neural networks. Utilized extensively in machine learning and artificial intelligence, neural networks consist of interconnected nodes, or neurons, organized into layers. These layers typically include an input layer, one or more hidden layers, and an output layer. Through a process called training, neural networks learn to recognize patterns and relationships within data by adjusting the strengths of connections (synaptic weights) between neurons. This enables them to perform tasks such as classification, regression, clustering, and pattern recognition with remarkable accuracy. Neural networks have gained prominence in various fields including computer vision, natural language processing, and autonomous systems, driving innovation and advancement in technology.

ABSTRACT

This report is an introduction to Artificial Neural Networks. The various types of neural networks are explained and demonstrated, applications of neural networks like ANNs in medicine are described, and a detailed historical background is provided. The connection between the artificial and the real thing is also investigated and explained. Finally, the mathematical models involved are presented and demonstrated.

TABLE OF CONTENTS

COVER PAGE

TITLE PAGE

APPROVAL PAGE

DEDICATION

ACKNOWLEDGEMENT

ABSTRACT

CHAPTER ONE

1.0 INTRODUCTION

1.1 BACKGROUND OF THE PROJECT

AIM OF THE PROJECT
OBJECTIVE OF THE PROJECT
SIGNIFICANCE OF THE PROJECT
STATEMENT OF STATEMENT
APPLICATION OF THE PROJECT
BENEFIT OF THE PROJECT

CHAPTER TWO

LITERATURE REVIEW

OVERVIEW OF THE STUDY
HISTORICAL BACKGROUND OF NEURAL NETWORK
THE NEED FOR NEURAL NETWORKS
COMPARISON BETWEEN NEURAL NETWORKS VERSUS CONVENTIONAL COMPUTERS
REVIEW OF DIFFERENT TYPES OF NEURAL NETWORKS

CHAPTER THREE

3.0 CONSTRUCTION METHODOLOGY

3.1 THE BASICS OF NEURAL NETWORKS

3.2 DESCRIPTION OF NEURAL NETWORK

3.3 NEURAL NETWORK ARCHITECTURE

3.4 NEURAL NETWORKS WORKING PRINCIPLE

3.5 SIMILARITIES OF HUMAN AND ARTIFICIAL NEURONES

CHAPTER FOUR

A SIMPLE NEURON
FIRING RULES
PATTERN RECOGNITION

CHAPTER FIVE

CONCLUSION
RECOMMENDATION
REFERENCE

CHAPTER ONE

1.0 INTRODUCTION

A neural network is a network or circuit of neurons, or in a modern sense, an artificial neural network. An Artificial Neural Network (ANN) is an information processing paradigm that is inspired by the way biological nervous systems, such as the brain, process information. The key element of this paradigm is the novel structure of the information processing system. It is composed of a large number of highly interconnected processing elements (neurones) working in unison to solve specific problems. ANNs, like people, learn by example. An ANN is configured for a specific application, such as pattern recognition or data classification, through a learning process. Learning in biological systems involves adjustments to the synaptic connections that exist between the neurones. This is true of ANNs as well.

1.1 AIM AND OBJECTIVE OF THE STUDY

The main aim of this work is to discus neural networks. At the end of this work the student involved shall be able to

introduce neural networks,
Study the application of neural networks,

advantages and disadvantages of neural networks,

the structures of neural networks,
pattern recognition neural networks,
different types of neural network,

and many other related subtitles.

1.2 SIGNIFICANCE OF THE STUDY

► Storing information on the entire network: Information such as in traditional programming is stored on the entire network, not on a database. The disappearance of a few pieces of information in one place does not prevent the network from functioning.

► Ability to work with incomplete knowledge: After ANN training, the data may produce output even with incomplete information. The loss of performance here depends on the importance of the missing information.

► Having fault tolerance: Corruption of one or more cells of ANN does not prevent it from generating output. This feature makes the networks fault tolerant.

► Having a distributed memory: In order for ANN to be able to learn, it is necessary to determine the examples and to teach the network according to the desired output by showing these examples to the network. The network’s success is directly proportional to the selected instances, and if the event can not be shown to the network in all its aspects, the network can produce false output

► Gradual corruption: A network slows over time and undergoes relative degradation. The network problem does not immediately corrode immediately.

► Ability to make machine learning: Artificial neural networks learn events and make decisions by commenting on similar events.

► Parallel processing capability: Artificial neural networks have numerical strength that can perform more than one job at the same time.

1.3 STATEMENT OF PROBLEM

► Hardware dependence: Artificial neural networks require processors with parallel processing power, in accordance with their structure. For this reason, the realization of the equipment is dependent.

► Unexplained behavior of the network: This is the most important problem of ANN. When ANN produces a probing solution, it does not give a clue as to why and how. This reduces trust in the network.

► Determination of proper network structure: There is no specific rule for determining the structure of artificial neural networks. Appropriate network structure is achieved through experience and trial and error.

► Difficulty of showing the problem to the network: ANNs can work with numerical information. Problems have to be translated into numerical values before being introduced to ANN. The display mechanism to be determined here will directly influence the performance of the network . This depends on the user’s ability.

► The duration of the network is unknown: The network is reduced to a certain value of the error on the sample means that the training has been completed. This value does not give us optimum results.

Science artificial neural networks that have stepped into the world in the mid-20th century are rapidly developing. In our present day, we have examined the advantages of artificial neural networks and the problems encountered in the course of their use. It should not be forgotten that the disadvantages of ANN networks, which are a developing science branch, are eliminated one by one and their advantages are increasing day by day. This means that artificial neural networks will become an indispensable part of our lives increasingly important.

1.4 APPLICATIONS OF THE STUDY

Neural network, due to some of its wonderful properties have many applications:

Image Processing and Character recognition: Given ANNs ability to take in a lot of inputs, process them to infer hidden as well as complex, non-linear relationships, ANNs are playing a big role in image and character recognition. Character recognition like handwriting has lot of applications in fraud detection (e.g. bank fraud) and even national security assessments. Image recognition is an ever-growing field with widespread applications from facial recognition in social media, cancer detention in medicine to satellite imagery processing for agricultural and defense usage. The research on ANN now has paved the way for deep neural networks that forms the basis of “deep learning” and which has now opened up all the exciting and transformational innovations in computer vision, speech recognition, natural language processing — famous examples being self-driving cars.

Applying Neural Networks to Different Industries

Neural networks are broadly used for real world business problems such as sales forecasting, customer research, data validation, and risk management.

Marketing

Target marketing involves market segmentation, where we divide the market into distinct groups of customers with different consumer behavior.

Neural networks are well-equipped to carry this out by segmenting customers according to basic characteristics including demographics, economic status, location, purchase patterns, and attitude towards a product. Unsupervised neural networks can be used to automatically group and segment customers based on the similarity of their characteristics, while supervised neural networks can be trained to learn the boundaries between customer segments based on a group of customers.

Retail and Sales

Neural networks have the ability to simultaneously consider multiple variables such as market demand for a product, a customer’s income, population, and product price. Forecasting of sales in supermarkets can be of great advantage here.

If there is a relationship between two products over time, say within 3–4 months of buying a printer the customer returns to buy a new cartridge, then retailers can use this information to contact the customer, decreasing the chance that the customer will purchase the product from a competitor.

Banking and Finance

Neural networks have been applied successfully to problems like derivative securities pricing and hedging, futures price forecasting, exchange rate forecasting, and stock performance. Traditionally, statistical techniques have driven the software. These days, however, neural networks are the underlying technique driving the decision making.

Medicine

It is a trending research area in medicine and 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 modelling parts of the human body and recognising diseases from various scans.

1.5 BENEFITS OF THE STUDY

Neural Networks can be applied to a variety of scenarios. The benefits that are associated with these applications have contributed a lot towards their popularity. The most popular areas where NNS are being applied include learning, pattern recognition and interpretation of noise and incomplete inputs.

Humans follow a different approach when solving problems when compared to computers. The objective of Neural Networks is to make computers think and solve issues like human beings. This can help computers to solve complex problems, which cannot be solved with a rule based approach. In other words, Artificial Neural Networks are being used to solve complex problems that cannot be simulated using analytical or logical techniques. They have the potential to solve issues, which cannot be solved even with expert systems. Pattern recognition is a perfect example to prove the above mentioned fact.

Neural Networks are in a position to analyze large amounts of data in an effective manner. After the analysis, it can establish characteristics and patterns, where rules or logic is not known. Loan applications are a perfect example for such a situation. After going through a large number of historical cases, the questionnaire of the applicant is being accepted or rejected. Only Artificial Neural Networks have the ability to automate this process of approving loans.

Neural Networks also have the ability to create profiles or patterns of applications that need to be denied or approved. Then a new application is matched against a pattern by the computer. The computer would gain the intelligence to classify whether it is a “yes” or “no”. Otherwise, it would go for the decision of humans. That’s the main reason why neural networks are being used for a variety of financial applications such as predicting exchange rates, predicting bankruptcy and determining when to purchase and sell stock.