|
|
The decision boundary
Gróf, Zoltán ; Hynčica, Tomáš (oponent) ; Jirsík, Václav (vedoucí práce)
The main aim of this master's thesis is to describe the subject of the implementation of decision boundaries with the help of artificial neural networks. The objective is to present theoretical knowledge concerning this field and on practical examples prove these statements. The work contains basic theoretical description of the field of pattern recognition and the field of feature based representation of objects. A classificator working on the basis of Bayes decision is presented in this part, and other types of classificators are named as well. The work then deals with artificial neural networks in more detail; it contains a theoretical description of their function and their abilities in the creation of decision boundaries in the feature plane. Examples are shown from literature for the use of neural networks in corresponding problems. As part of this work, the program ANN-DeBC was created using Matlab, for the generation of practical results about the usage of feed-forward neural networks for the implementation of decision boundaries. The work contains a detailed description of this program, and the achieved results are presented and analyzed. It is shown as well, how artificial neural networks are creating decision boundaries in the form of geometrical shapes. The effects of the chosen topology of the neural network and the number of training samples on the success of the classification are observed, and the minimal values of these parameters are determined for the successful creation of decision boundaries at the individual examples. Furthermore, it's presented how the neural networks behave at the classification of realistically distributed training samples, and what methods can affect the shape of the created decision boundaries.
|
|
|
Image processing with neural networks
Gróf, Zoltán ; Pohl, Jan (oponent) ; Jirsík, Václav (vedoucí práce)
This bachelor’s thesis centralizes on the possible uses of neural networks in the field of computer vision. This work contains basic theoretic knowledge of the field of neural networks and image processing. It discusses how successfully can neural networks be applied through the separate steps of image processing, what kind of neural networks are suitable for these steps, and what are the problems that might appear with their use. The work discusses the fields of classification and image understanding in a more detailed level. It’s shown how the use of neural networks can be appropriate in these applications. An own program was created as part of this work to demonstrate the classification capabilities of neural networks. It’s shown a neural network is created and trained for the recognition of handwritten numbers. The trained neural network was subject to different tests, through which the conclusion was reached, that it works with a high success rate, but is sensitive to changes in the input objects: change of size and location. A number of possible solutions were designed for this problem.
|
|
|
Image processing with neural networks
Gróf, Zoltán ; Pohl, Jan (oponent) ; Jirsík, Václav (vedoucí práce)
This bachelor’s thesis centralizes on the possible uses of neural networks in the field of computer vision. This work contains basic theoretic knowledge of the field of neural networks and image processing. It discusses how successfully can neural networks be applied through the separate steps of image processing, what kind of neural networks are suitable for these steps, and what are the problems that might appear with their use. The work discusses the fields of classification and image understanding in a more detailed level. It’s shown how the use of neural networks can be appropriate in these applications. An own program was created as part of this work to demonstrate the classification capabilities of neural networks. It’s shown a neural network is created and trained for the recognition of handwritten numbers. The trained neural network was subject to different tests, through which the conclusion was reached, that it works with a high success rate, but is sensitive to changes in the input objects: change of size and location. A number of possible solutions were designed for this problem.
|
|
|
The decision boundary
Gróf, Zoltán ; Hynčica, Tomáš (oponent) ; Jirsík, Václav (vedoucí práce)
The main aim of this master's thesis is to describe the subject of the implementation of decision boundaries with the help of artificial neural networks. The objective is to present theoretical knowledge concerning this field and on practical examples prove these statements. The work contains basic theoretical description of the field of pattern recognition and the field of feature based representation of objects. A classificator working on the basis of Bayes decision is presented in this part, and other types of classificators are named as well. The work then deals with artificial neural networks in more detail; it contains a theoretical description of their function and their abilities in the creation of decision boundaries in the feature plane. Examples are shown from literature for the use of neural networks in corresponding problems. As part of this work, the program ANN-DeBC was created using Matlab, for the generation of practical results about the usage of feed-forward neural networks for the implementation of decision boundaries. The work contains a detailed description of this program, and the achieved results are presented and analyzed. It is shown as well, how artificial neural networks are creating decision boundaries in the form of geometrical shapes. The effects of the chosen topology of the neural network and the number of training samples on the success of the classification are observed, and the minimal values of these parameters are determined for the successful creation of decision boundaries at the individual examples. Furthermore, it's presented how the neural networks behave at the classification of realistically distributed training samples, and what methods can affect the shape of the created decision boundaries.
|
host ::
RSS.