TCC - Bacharelado em Ciência da Computação (Sede)
URI permanente para esta coleçãohttps://arandu.ufrpe.br/handle/123456789/415
Navegar
4 resultados
Resultados da Pesquisa
Item Aprendizado profundo com capacidade computacional reduzida: uma aplicação à quebra de CAPTCHAs(2018-08-16) Melo, Diogo Felipe Félix de; Sampaio, Pablo Azevedo; http://lattes.cnpq.br/8865836949700771; http://lattes.cnpq.br/2213650736070295During the last decade, Deep Neural Networks has been shown to be a powerfull machine learn technique. Generally, to obtain relevant results, these techniques require high computacional power and large volumes of data, which can be a limiting factor on some cases. Neverthless, a careful project of trainig and archtecture may help to reduce these requirements. In the this work we present a comparative approach to the application of deep neural networks to text based CAPTCHAs as a way to cope with these limitations. We studied models that are capable of learn to segment and identify the text content of images, only based on examples. By experimentation of different hiper-parameters and architectures, we were capable to obtain a final model with 96.06% of token prediction accuracy in approximately 3 hours of training in a simple personal computer.Item Um currículo de aprendizado por reforço para o cenário “Run to Score with Keeper” do Google Research Football Environment(2019-12-10) Silva, Jonatan Washington Pereira da; Sampaio, Pablo Azevedo; Macário Filho, Valmir; http://lattes.cnpq.br/4346898674852080; http://lattes.cnpq.br/8865836949700771; http://lattes.cnpq.br/6846637095187550Reinforcement learning is a group of techniques that allow an agent to interact with a particular environment. Agents observe the state of the environment and perform an action, the action is evaluated through a reward obtained. The agent objective is to maximize this reward. Various issues such as three-dimensional locomotion and electronic games have been addressed by reinforcement learning (KURACH et al., 2019). The Trainament of agents for a soccer game usually has sparse rewards, what slows learning (MATIISEN et al., 2019). One technique that can solve this obstacle is the curriculum learning proposed in (BENGIO et al., 2009). This technique use simplest tasks of the main task and the increase difficult level with the time. In This work we present two curriculum, identified as 5-15-30-50 e 3-10-20-67, for the scenario Run To Score With Keeper of Football Academy. We have shown that curriculums on average achieved better results compared to training only in the main scenario, without curriculum. Curriculum 3-10-20-67 achieved a better result even considering the pattern deviation.Item Classificação de documentos de identificação com redes neurais convolucionais(2019-01-18) Rocha, Alessandro Nazário da; Sampaio, Pablo Azevedo; http://lattes.cnpq.br/8865836949700771; http://lattes.cnpq.br/2466292990350036Deep Learning has played an important role in data processing, with one of its main techniques being convolutional neural networks, which has the power to automatically learn features included in images in their layers. However, these deep artificial neural networks need a significant amount of images, for the proposed problem, already separated into categories to perform the training and validations of models that are not always available. In this context, in this work was constructed a dataset with images of Brazilian identification document of National Registry (RG) and National Qualification Card (CNH) separating them into some categories and, since they are documents with sensitive information, add a significant amount of images to obtain good results, it was a step that took time. For this reason, care was taken to preserve this sensitive information. This work presents some architectures of deep artificial neural networks to classify the images for different categories. Experiments were performed using a graphics processing unit (GPU) and using only the central processing unit (CPU). Results above 99% were obtained in some scenarios that were tested in the course of the work for the different proposed architectures.Item Proposta de um meta-modelo para avaliação de robutez de redes de computadores com base na combinação de métricas topológicas(2017) Barros, Gustavo Henrique Pinto Soares de; Araújo, Danilo Ricardo Barbosa de; http://lattes.cnpq.br/2708354422178489; http://lattes.cnpq.br/1155438495823549A growing demand for resilience and robustness in the field of computer networks rises from the great diversity of its aplications. The modern sistems display an increasing critical nature, and the occurrence of perturbations may cause significant losses either human, monetary or environmental. Optical fiber acts on the current systems as the main mean of transportation. Among its variety of applications, which are heavily dependant on its infrastructure, some of them are the internet, cable television and high transmission rates systems. The non-homogeneous and complex topology nature of these networks determine their increasing avaluation cost. For these reasons, optical networks are the study object of this research. Quantifying the robustness of networks is usually accomplished by nodes and links failure simulations, on which the monetary and temporal cost scales proportionally to the network size. This research analyzes the possibility of obtaining values of robustness metrics in complex networks which would originally be obtained from simulations through an alternative regression method. This method has as inputs the values of simple metrics which are obtained through applications other than simulations and uses artificial neural networks to forecast simulation results in a smaller period. The results are obtained through a comparison between the proposed model output and the node and link failure simulation output. They indicate that the proposed model presents a satisfactory error margin, between 10−³ and 10−9, thus the simulation values were reached successfully through regression on a smaller time period.