|
|
Convolutional Networks for Handwriting Recognition
Sladký, Jan ; Kišš, Martin (referee) ; Hradiš, Michal (advisor)
This thesis deals with handwriting recognition using convolutional neural networks. From the current methods, a network model was chosen to consist of convolutional and recurrent neural networks with the Connectist Temporal Classification. The Vertical Attention Module, which selects the relevant information in each column corresponding to the text in the figure was subsequently implemented in such a model. Then, this module was compared with other possibilities of vertical aggregation between convolutional and recurrent networks. The experiments took place on a data set containing over 80,000 lines of text from Czech letters from the 20th century. The results show that the Vertical Attention Module almost always achieves the best results on all used types of convolution networks. The resulting network achieved the best result with 8,9% of the character error rate. The contribution of this work is a neural network with a newly introduced element that can recognize lines of text.
|
|
|
Convolutional Networks for Handwriting Recognition
Sladký, Jan ; Kišš, Martin (referee) ; Hradiš, Michal (advisor)
This thesis deals with handwriting recognition using convolutional neural networks. From the current methods, a network model was chosen to consist of convolutional and recurrent neural networks with the Connectist Temporal Classification. The Vertical Attention Module, which selects the relevant information in each column corresponding to the text in the figure was subsequently implemented in such a model. Then, this module was compared with other possibilities of vertical aggregation between convolutional and recurrent networks. The experiments took place on a data set containing over 80,000 lines of text from Czech letters from the 20th century. The results show that the Vertical Attention Module almost always achieves the best results on all used types of convolution networks. The resulting network achieved the best result with 8,9% of the character error rate. The contribution of this work is a neural network with a newly introduced element that can recognize lines of text.
|
|
|
Negative externality associated with driving under the influence of alcohol
Sladký, Jan ; Hudík, Marek (advisor) ; Šťastný, Daniel (referee)
This thesis answers the question how big is the negative externality associated with driving under the influence of alcohol in crowns per kilometer driven by the driver with alcohol in blood. The calculation includes the economic consequences of accidents, specifically, loss of production, the cost of health care, administration and social expenditures, included are also the values of lost human lives and values for heavy and light injuries. Calculation of externality is used to determine the fine that internalizes this externality.
|
|
|
Discrimination in the labour market
Sladký, Jan ; Brožová, Dagmar (advisor) ; Bartoň, Petr (referee)
This bachelor work deals with discrimination in the labour market. The emphasis is above all placed on racial discrimination in the Czech republic, that is connected with the Romany minority. At first sight it may seen, that this subject matter is not a problem of economics, but I thing, that the economic view is crucial. The work focuses on an evaluation of current discrimination problem solving, evaluates if this solution is optimal and finally if there may not be a better one how to help the discriminated minorities in the labour market.
|
guest ::
RSS feed.