1,720,957 research outputs found
Aprimorando Técnicas de Redução de Dimensionalidade para Visualização de Redes Neurais Profundas
No full textDeep Neural Networks have achieved impressive results in a wide range of applications over the past few years, being responsible for many advances in computational technology. However, debugging and understanding the inner workings from these models is a complex task, as there are often millions of variables involved in every decision. Aiming to solve this problem, researchers from the fields of Visual Analytics and Explainable Artificial Intelligence have proposed several approaches to visualize and explain different aspects of DNN models. One of such approaches is the use of Dimensionality Reduction techniques for hidden layer output visualization, which has been employed in literature with relative success. However, there are certain limitations to applying these techniques in this context that need to be addressed, such as the visual comparison between multiple multidimensional projections. Furthermore, the particular characteristics of this domain can be taken into account to generate specialized visual representations that are more informative. This doctorate thesis shows the process of investigating problems and opportunities in DNN visualization using dimensionality reduction and the development of improved visualization methods for this domain.Redes neurais profundas tem demonstrado resultados impressionantes em uma grande variedade de aplicações computacionais nos últimos anos, sendo responsáveis por diversos avanços em tecnologia. No entanto, testar e entender os mecanismos internos destes modelos é uma tarefa complexa, uma vez que o número de variáveis envolvidas em cada decisão pode chegar aos milhões. Visando resolver este problema, pesquisadores dos campos de Visual Analytics e Explainable Artificial Intelligence tem proposto várias abordagens para visualizar e explicar diferentes aspectos de modelos de redes neurais. Uma destas abordagens é o uso de técnicas de redução de dimensionalidade para a visualização do comportamento de camadas ocultas, empregado com relativo sucesso na literatura. Porém, aplicar tais técnicas neste contexto implica em certas limitações que precisam ser tratadas, principalmente no que diz respeito à comparação visual entre múltiplas projeções multidimensonais. Adicionalmente, certas características particulares deste domínio podem ser utilizadas para gerar visualizações especializadas mais informativas. Esta tese de doutorado mostra o processo de investigação de problemas e oportunidades em visualização de redes neurais utilizando redução de dimensionalidade e o desenvolvimento de métodos de visualização aprimorados para este domínio
Computer display music with support discrimination of music theory
No full textA visualização computacional de informação é um campo em expansão por oferecer meios de se interpretar e analisar vários tipos de dados em grande quantidade e/ou de grande complexidade, compreendendo diversas técnicas e ferramentas para fornecer a um usuário formas de interagir e explorar conjuntos de dados a fim de se obter informações úteis ou importantes. A música, por sua vez, é um domínio complexo e de difícil estudo sob o ponto de vista computacional devido à análise de seu conteúdo possuir caráter muitas vezes subjetivo e dependente da interpretação humana. Embora vários trabalhos tenham sido publicados a respeito do assunto nos últimos anos, a maior parte das aplicações de visualização de informação relativas a música tende a analisar conjuntos de composições musicais a fim de agrupar ou classificar dados de acordo com algum tipo de critério. Assim, a visualização das informações contidas em uma única peça musical por si só é uma área que ainda pode ser melhor explorada, sobretudo visando compreender a informação musical envolvida o conteúdo extraído por um músico a partir de partituras e tablaturas. Esta dissertação relata o desenvolvimento de uma abordagem para visualização de dados musicais referentes a melodias em guitarra, com a capacidade de exibir elementos como variações de harmonia, melodia e tempo, tendo como objetivo auxiliar um músico (ou aprendiz de músico) na tarefa de interpretar tais dados.Information visualization is an expanding research field due to its offering of novel approaches to analyze data of great size or complexity, referring to many techniques and tools in order to offer ways to interact and explore data sets to find important or useful information. Music is a domain of high complexity and hard to study and analyze by computer due to its sometimes subjective features, dependant of human interpretation. Although many research initiatives have been published regarding this subject recently, most of the music-related information visualization applications tend to analyze datasets composed by many different musical pieces, aiming to classify or group the data according to certain criteria. Thus, visualization of the information contained in a single musical piece is an area that still could be better explored, especially regarding to the comprehension of the musical information involved information extracted by a musician by reading musical scores. This document reports the development of a novel approach to musical data visualization based on electric guitar melodies, capable of showing elements such as harmony, melody and timing variations, aiming to aid a musician in the task of understanding such data
Actor-Focused Interactive Visualization for AI Planning
No full textAs we grow more reliant on AI systems for an increasing variety of applications in our lives, the need to understand and interpret such systems also becomes more pronounced, be it for improvement, trust, or legal liability. AI Planning is one type of task that provides explanation challenges, particularly due to the increasing complexity in generated plans and convoluted causal chains that connect actions and determine overall plan structure. While there are many recent techniques to support plan explanation, visual aids for navigating this data are quite limited. Furthermore, there is often a barrier between techniques focused on abstract planning concepts and domain-related explanations. In this paper, we present a visual analytics tool to support plan summarization and interaction, focusing in robotics domains using an actor-based structure. We show how users can quickly grasp vital information about actions involved in a plan and how they relate to each other. Finally, we present a framework used to design our tool, highlighting how general PDDL elements can be converted into visual representations and further connecting concept to domain
Going Beyond Counting First Authors in Author Co-citation Analysis
Full text linkThe present study examines one of the fundamental aspects of author co-citation analysis (ACA) - the way co-citation
counts are defined. Co-citation counting provides the data on which all subsequent statistical analyses and mappings
are based, and we compare ACA results based on two different types of co-citation counting - the traditional type that
only counts the first one among a cited work's authors on the one hand and a non-traditional type that takes into
account the first 5 authors of a cited work on the other hand. Results indicate that the picture produced through this non-traditional author co-citation counting contains more coherent author groups and is therefore considerably clearer. However, this picture represents fewer specialties in the research field being studied than that produced through the traditional first-author co-citation counting when the same number of top-ranked authors is selected and analyzed. Reasons for these effects are discussed
A Generic Model for Projection Alignment Applied to Neural Network Visualization
No full textDimensionality reduction techniques are popular tools for the visualization of neural network models due to their ability to display hidden layer activations and aiding the understanding of how abstract representations are being formed. However, many techniques render poor results when used to compare multiple projections resulted from different feature sets, such as the outputs of different hidden layers or the outputs from different models processing the same data. This problem occurs due to the lack of an alignment factor to ensure that visual differences represent actual differences between the feature sets and not artifacts generated by the technique. In this paper, we propose a generic model to align multiple projections when visualizing different feature sets that can be applied to any gradient descent-based dimensionality reduction technique. We employ this model to generate a variant of the UMAP method and show the results of its application.EuroVis Workshop on Visual Analytics (EuroVA)Intersecting Humans and A
Variations on the Author
Full text link“Variations on the Author” discusses two of Eduardo Coutinho’s recent films (Um Dia na Vida, from 2010, and Últimas Conversas, posthumously released in 2015) and their contribution to the general question of documentary authorship. The director’s filmography is characterized by a consistent yet self-effacing form of authorial self-inscription: Coutinho often features as an interviewer that rather than express opinions propels discourses; an interviewer that is good at listening. This mode of self-inscription characterizes him as an author who is not expressive but who is nonetheless markedly present on the screen. In Um Dia na Vida, however, Coutinho is completely absent form the image, while Últimas Conversas, on the contrary, includes a confessional prologue that moves the director from the margins to the center of his films. This article examines the ways in which these works stand out in the filmography of a director who offers new insights into the notion of cinematic authorship
Appropriate Similarity Measures for Author Cocitation Analysis
Full text linkWe provide a number of new insights into the methodological discussion about author cocitation analysis. We first argue that the use of the Pearson correlation for measuring the similarity between authors’ cocitation profiles is not very satisfactory. We then discuss what kind of similarity measures may be used as an alternative to the Pearson correlation. We consider three similarity measures in particular. One is the well-known cosine. The other two similarity measures have not been used before in the bibliometric literature. Finally, we show by means of an example that our findings have a high practical relevance.information science;Pearson correlation;cosine;similarity measure;author cocitation analysis
Dispelling the Myths Behind First-author Citation Counts
Full text linkWe conducted a full-scale evaluative citation analysis study of scholars in the XML research field to explore just how different from each other author rankings resulting from different citation counting methods actually are, and to demonstrate the capability of emerging data and tools on the Web in supporting more realistic citation counting methods. Our results contest some common arguments for the continued
use of first-author citation counts in the evaluation of scholars, such as high correlations between author rankings by first-author citation counts and other citation
counting methods, and high costs of using more realistic citation counting methods that are not well-supported by the ISI databases. It is argued that increasingly available digital full text research papers make it possible for citation analysis studies to go beyond what the ISI databases have directly supported and to employ more
sophisticated methods
- …
