Ingeniero Civil Industrial / Frente a las diversas crisis y problemáticas que han afectado a la economía norteamericana y europea estos últimos 20 años, se observa que casi sorpresivamente la tendencia de la tasa de ahorro sobre el PIB de cada país es al alza generalmente. Es que no solamente desempleo han traído estos fenómenos económicos, sino que también un aumento en la variabilidad de los salarios de los trabajadores. La literatura que investiga estos hechos dice que efectivamente este aumento ocurre y que influye directamente en el aumento del ahorro. La razón de esto es que la población ve más inciertos sus ingresos futuros, entonces deciden disminuir el consumo presente en pro de cuidarse frente a un posible futuro adverso. En este documento, por lo tanto, se pretende demostrar que el efecto del denominado Riesgo Intrínseco Microeconómico también está presente sobre las Tasas de Ahorro de los países. Para este estudio se generarán economías modeladas con un Modelo Neoclásico de Crecimiento Estándar en donde se busca endogenizar las variables del salario y de los recursos disponibles en cada período. De esta forma se busca entender si efectivamente un aumento en la volatilidad del salario trae consigo un aumento en el ahorro. De acuerdo a lo obtenido, no se puede comprobar que a un mayor Riesgo Intrínseco Microeconómico el ahorro aumente, lo que sí es cierto para tasas de interés negativas. Esto se debe a que al estar frente a un escenario donde la volatilidad de los salarios es alta, se toma una postura menos conservadora ya que, dado que en el modelo, por cierto, no se consideran restricciones de transferencias y que el Efecto Renta es predominante, existe la posibilidad del endeudamiento teniendo más seguridad que en algún momento se podrán pagar cuando el salario sea alto.

he concern of the thesis is analysis and comparison of network probes. This thesis is dedicated to open-source solutions of network probes, which are available under public license. The first part of the thesis describes architecture and function principles of network probes. Next part describes each probe and its functions. Last part of the thesis contains the description of the solution of network probe and principles of its operation.

Artificial neural networks are demanding to computational power of a computer. Increasing their learning speed could mean new posibilities for research or aplication of the algorithm. And that is a purpose of this thesis. The usage of graphics processing units for neural networks learning is one way how to achieve above mentioned goals. This thesis is offering a survey of theoretical background and consequently implementation of a software library for neural networks learning with a Backpropagation algorithm with a support of acceleration on graphics processing unit.

This report contains design, architecture and implementation of a system that is used to~monitor services and files in computer networks. The monitoring system is based on~principles of software defined networks. The~first part of the report focuses on the description of~ SDN principles and OnePK platform, which is used for the construction of the monitoring system. The second part of the work consists of the design and implementation of~the~monitoring system as a OnePK application. Finally, the evaluation of the monitoring system is provided.

Title: Text mining in social network analysis Author: Bc. Michal Hušek Department: Department of Theoretical Computer Science and Mathematical Logic Supervisor: doc. RNDr. Iveta Mrázová, CSc., Department of Theoretical Computer Science and Mathematical Logic Abstract: Nowadays, social networks represent one of the most important sources of valuable information. This work focuses on mining the data provided by social networks. Multiple data mining techniques are discussed and analysed in this work, namely, clustering, neural networks, ranking algorithms and histogram statistics. Most of the mentioned algorithms have been implemented and tested on real-world social network data and the obtained results have been mutually compared against each other whenever it made sense. For computationally demanding tasks, graphic processing units have been used in order to speed up calculations for vast amounts of data, e.g., during clustering. The performed tests have confirmed lower time requirements. All the performed analyses are, however, independent of the actually involved type of social network. Keywords: data mining, social networks, clustering, neural networks, ranking algorithms, CUDA

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.

The presented master thesis is focused on the stock markets returns analysis using a new type of neural network. First chapter of the thesis describes the underlying theory of the financial time series prediction, Efficient Market Hypothesis and conventional forecasting models. Following part illustrates biological framework, basic principles, functioning of neural networks, their architecture and several well-known learning algorithms such as Gradient descent, Levenberg-Marquardt algorithm or Conjugate gradient. It also mentions certain disadvantages which influence the performance and effectiveness of neural networks. Third chapter is devoted to two applied metaheuristic techniques, i.e. genetic algorithms and simulated annealing that were integrated into neural networks framework to eliminate above mentioned drawbacks. Next chapter describes details of presented hybrid network, whereas the last section is aimed at evaluation of overall results of all models. It shows that on the examined sample hybrid network clearly outperformed standard techniques as well as ordinary neural networks and in most cases achieved the least mean squared error among all explored methods. Keywords: stock returns analysis, neural networks, genetic algorithms, simulated annealing, hybrid networks JEL classification:...

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.

El presente artículo describe la aplicación de “Lean” como mejora de los procesos productivos de una fábrica dedicada a la elaboración de chocolates y confituras, donde se identificó que existía un problema de demanda insatisfecha. El primer paso para la reversión de este escenario fue realizar un análisis de las causas-raíz. Al aplicarse algunas herramientas se identificaron diferentes motivos que fueron causantes del problema. Para confirmar esta información y orientar el análisis hacia una causa puntual, se calculó el TAKT-time del proceso productivo tradicional. Con el cuello de botella plenamente identificado, el paso siguiente fue realizar el análisis de los mudas que podrían hallarse a lo largo del proceso. Como propuesta, se planteó un modelo de producción esbelta conformado por un conjunto de mejoras que impactaron en la eliminación de desperdicios y reducción del TAKT-Time, lo cual implicó nivelar el flujo de producción y desaparecer el cuello de botella.

1 Title: Convolutional neural networks and their application in object detection Author: Matej Hrinčár Department: Department of Theoretical Computer Science and Mathematical Logic Supervisor: doc. RNDr. Iveta Mrázová, CSc. Supervisor's e-mail address: Iveta.Mrazova@mff.cuni.cz Abstract: Nowadays, it has become popular to enhance live sport streams with an augmented reality like adding various statistics over the hockey players. To do so, players must be automatically detected first. This thesis deals with such a challenging task. Our aim is to deliver not only a sufficient accuracy but also a speed because we should be able to make the detection in real time. We use one of the newer model of neural network which is a convolutional network. This model is suitable for proces- sing image data a can use input image without any preprocessing whatsoever. After our detailed analysis we choose this model as a detector for hockey players. We have tested several different architectures of the networks which we then compared and choose the one which is not only accurate but also fast enough. We have also tested the robustness of the network with noisy patterns. Finally we assigned detected pla- yers to their corresponding teams utilizing K-mean algorithm using the information about their jersey color. Keywords:...