1,720,962 research outputs found
NETT: solving inverse problems with deep neural networks
No full textRecovering a function or high-dimensional parameter vector from indirect measurements is a central task in various scientific areas. Several methods for solving such inverse problems are well developed and well understood. Recently, novel algorithms using deep learning and neural networks for inverse problems appeared. While still in their infancy, these techniques show astonishing performance for applications like low-dose CT or various sparse data problems. However, there are few theoretical results for deep learning in inverse problems. In this paper, we establish a complete convergence analysis for the proposed NETT (network Tikhonov) approach to inverse problems. NETT considers nearly data-consistent solutions having small value of a regularizer defined by a trained neural network. We derive well-posedness results and quantitative error estimates, and propose a possible strategy for training the regularizer. Our theoretical results and framework are different from any previous work using neural networks for solving inverse problems. A possible data driven regularizer is proposed. Numerical results are presented for a tomographic sparse data problem, which demonstrate good performance of NETT even for unknowns of different type from the training data. To derive the convergence and convergence rates results we introduce a new framework based on the absolute Bregman distance generalizing the standard Bregman distance from the convex to the non-convex case
Going Beyond Counting First Authors in Author Co-citation Analysis
No full textThe 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
Nonlinear compressive Time-of-Flight 3D Imaging
No full textTime-of-flight (ToF) cameras are compact devices providing spatially and temporally resolved depth information. Possible applications include human-machine interaction in gaming industry or safety functions in automotive industry. In many applications, it is desirable to reduce the amount of data to be read out and transmitted from the ToF camera to an external host system. Using standard ToF cameras, this can only be achieved by lowering the spatial or temporal resolution.
In this thesis we propose a compressive ToF camera design that allows to reduce the amount of data while keeping high spatial and temporal resolution. This uses the theory of compressed sensing and sparse recovery. We propose two different types of algorithms to recover the images. The first, and meanwhile classical one, is based on convex optimization. The second one is based on very recent ideas from deep learning and convolutional neural networks for image reconstruction. We apply the developed reconstruction methods to data captured by a real ToF camera system and evaluate them in terms of reconstruction quality and computational effort.author: Stephan AntholzerMasterarbeit University of Innsbruck 201
Variations on the Author
No full text“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
Compressed sensing and deep learning in photoacoustic tomography
No full textPhotoakustische Tomographie ist ein biomedizinisches bildgebendes Verfahren mit hohem Kontrast und hoher Auflösung. In der Praxis ist die Anzahl der Sensoren jedoch ein limitierender Faktor für die Bildqualität. Um dies zu beheben, wurden in der Vergangenheit "compressed sensing" basierende Methoden vorgeschlagen.
Unser Ziel ist es das kombinierte Problem von "compressed sensing" und photoakustischer Tomographie zu lösen.
In dieser Arbeit entwickeln, analysieren und vergleichen wir mehrere Methoden, die Aspekte aus dem maschinellem Lernen in den Rekonstruktionsalgorithmus einbauen.Photoacoustic Tomography is biomedical imaging technique with high contrast and resolution. However, in praxis a limited number of sensors yields suboptimal results. In order to solve this issue compressed sensing based approaches have been proposed in the past.
Our goal is to solve the combined problem of compressed sensing and photoacoustic tomography.
In this work we develop, analyse and compare several methods that incorporate machine learning aspects into the reconstruction algorithms.author: Stephan AntholzerKumulative Dissertation aus sieben ArtikelnIm Artikel ist 1 hochgestelltDissertation University of Innsbruck 202
Compressed sensing and deep learning in photoacoustic tomography
No full textPhotoakustische Tomographie ist ein biomedizinisches bildgebendes Verfahren mit hohem Kontrast und hoher Auflösung. In der Praxis ist die Anzahl der Sensoren jedoch ein limitierender Faktor für die Bildqualität. Um dies zu beheben, wurden in der Vergangenheit "compressed sensing" basierende Methoden vorgeschlagen.
Unser Ziel ist es das kombinierte Problem von "compressed sensing" und photoakustischer Tomographie zu lösen.
In dieser Arbeit entwickeln, analysieren und vergleichen wir mehrere Methoden, die Aspekte aus dem maschinellem Lernen in den Rekonstruktionsalgorithmus einbauen.Photoacoustic Tomography is biomedical imaging technique with high contrast and resolution. However, in praxis a limited number of sensors yields suboptimal results. In order to solve this issue compressed sensing based approaches have been proposed in the past.
Our goal is to solve the combined problem of compressed sensing and photoacoustic tomography.
In this work we develop, analyse and compare several methods that incorporate machine learning aspects into the reconstruction algorithms.author: Stephan AntholzerKumulative Dissertation aus sieben ArtikelnIm Artikel ist 1 hochgestelltDissertation University of Innsbruck 202
Appropriate Similarity Measures for Author Cocitation Analysis
No full textWe 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
Nonlinear compressive Time-of-Flight 3D Imaging
No full textTime-of-flight (ToF) cameras are compact devices providing spatially and temporally resolved depth information. Possible applications include human-machine interaction in gaming industry or safety functions in automotive industry. In many applications, it is desirable to reduce the amount of data to be read out and transmitted from the ToF camera to an external host system. Using standard ToF cameras, this can only be achieved by lowering the spatial or temporal resolution.
In this thesis we propose a compressive ToF camera design that allows to reduce the amount of data while keeping high spatial and temporal resolution. This uses the theory of compressed sensing and sparse recovery. We propose two different types of algorithms to recover the images. The first, and meanwhile classical one, is based on convex optimization. The second one is based on very recent ideas from deep learning and convolutional neural networks for image reconstruction. We apply the developed reconstruction methods to data captured by a real ToF camera system and evaluate them in terms of reconstruction quality and computational effort.author: Stephan AntholzerMasterarbeit University of Innsbruck 201
Dispelling the Myths Behind First-author Citation Counts
No full textWe 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
- …
