19-06-2012, 11:59 AM
Artificial Neural Networks
ABSTRACT
The present work encompasses a study of image recognition and corresponding information retrieval by means of a feed forward three layer neural system in defence sector. Where the system intelligence in recognizing the patterns is checked and fault tolerance analysis of the same is done. The image to be fed to the neural net after preprocessing. To support our project application, an appropriate neural net architecture is selected for design. Selection of proper activation function plays a very major role in the design of architecture. Applying an appropriate learning rule, the designed neural net is trained to learn the patterns.
INTRODUCTION:
An Artificial Neural Network (ANN) also called Neural Network 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 (neurons) working in parallel to solve specific problems.
Custom defined precise recognition:
Here decision does not belong to the domain of experience, if the object hasn’t been learned. Recalling generates an error. A pre defined threshold of error is used to check the acceptability of error in recalling. If it is less than the threshold, maximum correlation is used to take the decision otherwise object will declare a new pattern.
FAULT TOLERANT ANALYSIS OF ANN SYSTEM:
When a system designed, several parameters available to check the quality of system like speed, power consumption, size etc. Another kind of parameter, which defines the reliability of system, is fault tolerance.
If defines the reliability of the system output if any fault happens. For a given design, to know the performance value with respect to fault tolerance, it requires to analyze the system thoroughly. ANN works on parallel distributed computing, so expectation of fault tolerance is very high. This is matter of interest to know how faults in ANN affect its performance.
ANALYSIS OF INTERNAL DYNAMICS IN ANN:
To have a better understanding of ANN, it requires detail information about its internal dynamics. By selecting the various factors like hidden layer weights, outer layer weights, learning rate, error function etc, and the mechanism behind providing such an outstanding performance can be explored.
Apart from this, how improvement in performance can be done, solution can be searched through such analysis.
INFORMATION RETRIEVAL:
In practical application, after recognition some action taken place. In this project this action taken as retrieval of information associated with that particular image. The proposed system will not only recognize the true image but also if true image has been corrupted with various types of noise. Following ways the true image will corrupt with noise.
ARTIFICIAL NEURAL NETWORK:
An artificial neural network (ANN) also called neural network is an information processing paradigm that is inspired by the way biological nervous system, 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 (neurons) working I parallel to solve problems.
ANNs, like people, learn by example. An ANN is configured for a specific application, such as pattern recognition, signal processing and data classification etc. through a learning process .
Overview of ANN
Neural network simulations appear to be a recent development. However, this field was established before the advent of computers, and has survived at least one major setback and several eras.
Many important advances have been boosted by the use of inexpensive computer emulations. Following an initial period of enthusiasm, the field survived a period of frustration and disrepute. During this period when funding and professional support was minimal, important advances were made by relatively few researchers. These pioneers were able to develop convincing technology, which surpassed the limitations identified by Minsky and Papert. They published a book (in 1969) in which they summed up a general feeling of frustration (against neural networks) among researchers, and was thus accepted by most without further analysis. Currently, the neural network field enjoys a resurgence of interest and a corresponding increase in funding .
ABSTRACT
The present work encompasses a study of image recognition and corresponding information retrieval by means of a feed forward three layer neural system in defence sector. Where the system intelligence in recognizing the patterns is checked and fault tolerance analysis of the same is done. The image to be fed to the neural net after preprocessing. To support our project application, an appropriate neural net architecture is selected for design. Selection of proper activation function plays a very major role in the design of architecture. Applying an appropriate learning rule, the designed neural net is trained to learn the patterns.
INTRODUCTION:
An Artificial Neural Network (ANN) also called Neural Network 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 (neurons) working in parallel to solve specific problems.
Custom defined precise recognition:
Here decision does not belong to the domain of experience, if the object hasn’t been learned. Recalling generates an error. A pre defined threshold of error is used to check the acceptability of error in recalling. If it is less than the threshold, maximum correlation is used to take the decision otherwise object will declare a new pattern.
FAULT TOLERANT ANALYSIS OF ANN SYSTEM:
When a system designed, several parameters available to check the quality of system like speed, power consumption, size etc. Another kind of parameter, which defines the reliability of system, is fault tolerance.
If defines the reliability of the system output if any fault happens. For a given design, to know the performance value with respect to fault tolerance, it requires to analyze the system thoroughly. ANN works on parallel distributed computing, so expectation of fault tolerance is very high. This is matter of interest to know how faults in ANN affect its performance.
ANALYSIS OF INTERNAL DYNAMICS IN ANN:
To have a better understanding of ANN, it requires detail information about its internal dynamics. By selecting the various factors like hidden layer weights, outer layer weights, learning rate, error function etc, and the mechanism behind providing such an outstanding performance can be explored.
Apart from this, how improvement in performance can be done, solution can be searched through such analysis.
INFORMATION RETRIEVAL:
In practical application, after recognition some action taken place. In this project this action taken as retrieval of information associated with that particular image. The proposed system will not only recognize the true image but also if true image has been corrupted with various types of noise. Following ways the true image will corrupt with noise.
ARTIFICIAL NEURAL NETWORK:
An artificial neural network (ANN) also called neural network is an information processing paradigm that is inspired by the way biological nervous system, 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 (neurons) working I parallel to solve problems.
ANNs, like people, learn by example. An ANN is configured for a specific application, such as pattern recognition, signal processing and data classification etc. through a learning process .
Overview of ANN
Neural network simulations appear to be a recent development. However, this field was established before the advent of computers, and has survived at least one major setback and several eras.
Many important advances have been boosted by the use of inexpensive computer emulations. Following an initial period of enthusiasm, the field survived a period of frustration and disrepute. During this period when funding and professional support was minimal, important advances were made by relatively few researchers. These pioneers were able to develop convincing technology, which surpassed the limitations identified by Minsky and Papert. They published a book (in 1969) in which they summed up a general feeling of frustration (against neural networks) among researchers, and was thus accepted by most without further analysis. Currently, the neural network field enjoys a resurgence of interest and a corresponding increase in funding .