|
|
Indoor Robot - Control Neural Network
Křepelka, Pavel ; Kopečný, Lukáš (referee) ; Žalud, Luděk (advisor)
In this document, I describe possibilities of mobile robot navigation. This problems are solving many different ways, but there isn’t satisfactorily result to this day. You find there describe of deterministic algorithms, this algorithms can be used for simply actions like obstacle avoiding or travel in corridor. For global navigation this algorithms fails. In next part of document is theory of artificial neural nets (perceptron, multi layer neural nets, self organization map) and using them in mobile robots. Own navigation algorithms was tested on constructed mobile robot or simulated in SW described in chapter 6. Design own control algorithms is based on neural net (Kohonen net). Designed algorithms can be used for one-point navigation or complex global navigation. In document, there is comparing of various ways to navigation, their advantages and disadvantages. Goal of this document is find effective algorithm for navigation and artificial intelligence appears to be the right solution.
|
|
|
RBF-networks with a dynamic architecture
Jakubík, Miroslav ; Mrázová, Iveta (advisor) ; Kukačka, Marek (referee)
In this master thesis I recapitulated several methods for data clustering. Two well known clustering algorithms, concretely K-means algorithm and Fuzzy C-means (FCM) algorithm, were described in the submitted work. I presented several methods, which could help estimate the optimal number of clusters. Further, I described Kohonen maps and two models of Kohonen's maps with dynamically changing structure, namely Kohonen map with growing grid and the model of growing neural gas. At last I described quite new model of radial basis function neural networks. I presented several learning algorithms for this model of neural networks, RAN, RANKEF, MRAN, EMRAN and GAP. In the end of this work I made some clustering experiments with real data. This data describes the international trade among states of the whole world.
|
|
|
RBF-networks with a dynamic architecture
Jakubík, Miroslav ; Mrázová, Iveta (advisor) ; Kukačka, Marek (referee)
In this master thesis I recapitulated several methods for data clustering. Two well known clustering algorithms, concretely K-means algorithm and Fuzzy C-means (FCM) algorithm, were described in the submitted work. I presented several methods, which could help estimate the optimal number of clusters. Further, I described Kohonen maps and two models of Kohonen's maps with dynamically changing structure, namely Kohonen map with growing grid and the model of growing neural gas. At last I described quite new model of radial basis function neural networks. I presented several learning algorithms for this model of neural networks, RAN, RANKEF, MRAN, EMRAN and GAP. In the end of this work I made some clustering experiments with real data. This data describes the international trade among states of the whole world.
|
|
|
RBF-networks with a dynamic architecture
Jakubík, Miroslav ; Mrázová, Iveta (advisor) ; Kukačka, Marek (referee)
In this master thesis I recapitulated several methods for clustering input data. Two well known clustering algorithms, concretely K-means algorithm and Fuzzy C-means (FCM) algorithm, were described in the submitted work. I presented several methods, which could help estimate the optimal number of clusters. Further, I described Kohonen maps and two models of Kohonen's maps with dynamically changing structure, namely Kohonen map with growing grid and the model of growing neural gas. At last I described quite new model of radial basis function neural networks. I presented several learning algorithms for this model of neural networks. In the end of this work I made some clustering experiments with real data. This data describes the international trade among states of the whole world.
|
|
|
Indoor Robot - Control Neural Network
Křepelka, Pavel ; Kopečný, Lukáš (referee) ; Žalud, Luděk (advisor)
In this document, I describe possibilities of mobile robot navigation. This problems are solving many different ways, but there isn’t satisfactorily result to this day. You find there describe of deterministic algorithms, this algorithms can be used for simply actions like obstacle avoiding or travel in corridor. For global navigation this algorithms fails. In next part of document is theory of artificial neural nets (perceptron, multi layer neural nets, self organization map) and using them in mobile robots. Own navigation algorithms was tested on constructed mobile robot or simulated in SW described in chapter 6. Design own control algorithms is based on neural net (Kohonen net). Designed algorithms can be used for one-point navigation or complex global navigation. In document, there is comparing of various ways to navigation, their advantages and disadvantages. Goal of this document is find effective algorithm for navigation and artificial intelligence appears to be the right solution.
|
guest ::
