|
| |
|
| |
|
| |
|
| |
|
|
Úvod do statistického rozpoznávání
Pudil, Pavel ; Somol, Petr ; Haindl, Michal
Pattern recognition problem is briefly characterized as a process of machine learning. Its main stages (dimensionality reduction and classifier design) are stated. Statistical approach is given priority here. Two approaches to dimensionality reduction, namely feature selection (FS) and feature extraction (FE) are specified. Though FS is a special case of FE, they are very different from a practical viewpoint and thus must be considered separately.
|
|
|
Rozpoznávání založené na vícerozměrných modelech
Haindl, Michal ; Pudil, Pavel ; Somol, Petr
This chapter explains general model-based approaches to several basic pattern recognition applications followed by a concise description of three fundamental multi-dimensional data model classes. For each model class a solution to parameter estimation and model data synthesis is outlined. Finally an overview of the strengths and weaknesses of studied multi-dimensional data model groups is given.
|
|
| |
|
| |
|
|
History of Artificial Intelligence - Neural Networks
Šuchman, Ondřej ; Jirků, Petr (advisor) ; Berka, Petr (referee)
The main aim of my bachelor thesis is to map historical development of neural networks from the beginning (first mathematical model of neuron from 1943) to present and application of neural networks to "intelligent" devices, which can recognize the patterns, graphical data or convert English written text to the oral form (NETtalk). I have carefully studied the literature named in the chapter "Literatura a zdroje" in order to achieve this aim. In the first charter there is the theoretical survey about the field of artificial intelligence and neural networks. Then the thesis is well-arranged to five periods, which were important for neural networks in either good or bad way. To the most important discoveries are dedicated more space and there is mentioned their functionality and using possibilities. There is not enough space on this thesis to cover all the neural networks ever made. The aim of the thesis is to demostrate certain kinds of networks, their first usage, the most important algorithms and also to mention the significant applications of neural networks.
|
|
|
Extrakce informací z textu
Michalko, Boris ; Labský, Martin (advisor) ; Svátek, Vojtěch (referee) ; Nováček, Jan (referee)
Cieľom tejto práce je preskúmať dostupné systémy pre extrakciu informácií a možnosti ich použitia v projekte MedIEQ. Teoretickú časť obsahuje úvod do oblasti extrakcie informácií. Popisujem účel, potreby a použitie a vzťah k iným úlohám spracovania prirodzeného jazyka. Prechádzam históriou, nedávnym vývojom, meraním výkonnosti a jeho kritikou. Taktiež popisujem všeobecnú architektúru IE systému a základné úlohy, ktoré má riešiť, s dôrazom na extrakciu entít. V praktickej časti sa nacházda prehľad algoritmov používaných v systémoch pre extrakciu informácií. Opisujem oba typy algoritmov ? pravidlové aj štatistické. V ďalšej kapitole je zoznam a krátky popis existujúcich voľných systémov. Nakoniec robím vlastný experiment s dvomi systémami ? LingPipe a GATE na vybraných korpusoch. Meriam rôzne výkonnostné štatistiky. Taktiež som vytvoril malý slovník a regulárny výraz pre email aby som demonštroval taktiež pravidlá pre extrahovanie určitých špecifických informácií.
|
guest ::
