Refine
Year of publication
Document Type
- Article (unreviewed) (558) (remove)
Has Fulltext
- no (558) (remove)
Is part of the Bibliography
- yes (558)
Keywords
- Schule (10)
- Bildung (8)
- Arbeitszeugnis (7)
- Digitalisierung (6)
- Energieversorgung (6)
- Export (6)
- Nachhaltigkeit (6)
- Recht (6)
- Datenschutz (5)
- Dünnschichtchromatographie (5)
Institute
- Fakultät Medien und Informationswesen (M+I) (bis 21.04.2021) (188)
- Fakultät Wirtschaft (W) (117)
- Fakultät Maschinenbau und Verfahrenstechnik (M+V) (96)
- Fakultät Elektrotechnik und Informationstechnik (E+I) (bis 03/2019) (94)
- Fakultät Medien (M) (ab 22.04.2021) (33)
- Fakultät Elektrotechnik, Medizintechnik und Informatik (EMI) (ab 04/2019) (27)
- INES - Institut für nachhaltige Energiesysteme (20)
- IMLA - Institute for Machine Learning and Analytics (16)
- IfTI - Institute for Trade and Innovation (13)
- IUAS - Institute for Unmanned Aerial Systems (4)
Open Access
- Closed Access (156)
- Open Access (125)
- Closed (70)
- Diamond (16)
- Bronze (14)
- Gold (1)
- Hybrid (1)
The mathematical representations of data in the Spherical Harmonic (SH) domain has recently regained increasing interest in the machine learning community. This technical report gives an in-depth introduction to the theoretical foundation and practical implementation of SH representations, summarizing works on rotation invariant and equivariant features, as well as convolutions and exact correlations of signals on spheres. In extension, these methods are then generalized from scalar SH representations to Vectorial Harmonics (VH), providing the same capabilities for 3d vector fields on spheres.
Projektmanagement und mit ihm die PM-Prozesse, Methoden und Werkzeuge entwickeln sich stetig weiter, in kleinen, kaum spürbaren Schritten oder in großen unübersehbaren Veränderungen. In den letzten Jahren war der Diskurs über das Pro & Contra agiler Vorgehensweisen so allgegenwärtig, dass andere Aspekte nicht immer die notwendige Aufmerksamkeit bekamen. Erkannte Notwendigkeiten der PM-Entwicklung konnten noch nicht in spürbare Fortschritte umgewandelt werden. Einflüsse der Globalisierung und der IT, aber auch die aus der zunehmenden Forderung nach Nachhaltigkeit resultierenden Veränderungen in der Projektarbeit sollen daher genauer betrachtet werden. Ist erst einmal die Sensibilität für relevante Trends beim Projektpersonal geschaffen, rücken ein aktualisiertes Kompetenzprofil und ein erweiterter Methodenkanon in greifbare Nähe.
Die fortschreitende Digitalisierung der Schulen macht es möglich, die Lerndaten der Schülerinnen und Schüler in einer zentralen Cloud zu speichern. Die Befürworter versprechen sich davon eine bessere individuelle Förderung und fordern eine bundesweite Lösung, um möglichst viele Daten auswerten zu können. Die Gegner befürchten eine automatisierte Steuerung des Lernens.
Assessing the robustness of deep neural networks against out-of-distribution inputs is crucial, especially in safety-critical domains like autonomous driving, but also in safety systems where malicious actors can digitally alter inputs to circumvent safety guards. However, designing effective out-of-distribution tests that encompass all possible scenarios while preserving accurate label information is a challenging task. Existing methodologies often entail a compromise between variety and constraint levels for attacks and sometimes even both. In a first step towards a more holistic robustness evaluation of image classification models, we introduce an attack method based on image solarization that is conceptually straightforward yet avoids jeopardizing the global structure of natural images independent of the intensity. Through comprehensive evaluations of multiple ImageNet models, we demonstrate the attack's capacity to degrade accuracy significantly, provided it is not integrated into the training augmentations. Interestingly, even then, no full immunity to accuracy deterioration is achieved. In other settings, the attack can often be simplified into a black-box attack with model-independent parameters. Defenses against other corruptions do not consistently extend to be effective against our specific attack.
Project website: https://github.com/paulgavrikov/adversarial_solarization
Fix your downsampling ASAP! Be natively more robust via Aliasing and Spectral Artifact free Pooling
(2023)
Convolutional neural networks encode images through a sequence of convolutions, normalizations and non-linearities as well as downsampling operations into potentially strong semantic embeddings. Yet, previous work showed that even slight mistakes during sampling, leading to aliasing, can be directly attributed to the networks' lack in robustness. To address such issues and facilitate simpler and faster adversarial training, [12] recently proposed FLC pooling, a method for provably alias-free downsampling - in theory. In this work, we conduct a further analysis through the lens of signal processing and find that such current pooling methods, which address aliasing in the frequency domain, are still prone to spectral leakage artifacts. Hence, we propose aliasing and spectral artifact-free pooling, short ASAP. While only introducing a few modifications to FLC pooling, networks using ASAP as downsampling method exhibit higher native robustness against common corruptions, a property that FLC pooling was missing. ASAP also increases native robustness against adversarial attacks on high and low resolution data while maintaining similar clean accuracy or even outperforming the baseline.
With the rising necessity of explainable artificial intelligence (XAI), we see an increase in task-dependent XAI methods on varying abstraction levels. XAI techniques on a global level explain model behavior and on a local level explain sample predictions. We propose a visual analytics workflow to support seamless transitions between global and local explanations, focusing on attributions and counterfactuals on time series classification. In particular, we adapt local XAI techniques (attributions) that are developed for traditional datasets (images, text) to analyze time series classification, a data type that is typically less intelligible to humans. To generate a global overview, we apply local attribution methods to the data, creating explanations for the whole dataset. These explanations are projected onto two dimensions, depicting model behavior trends, strategies, and decision boundaries. To further inspect the model decision-making as well as potential data errors, a what-if analysis facilitates hypothesis generation and verification on both the global and local levels. We constantly collected and incorporated expert user feedback, as well as insights based on their domain knowledge, resulting in a tailored analysis workflow and system that tightly integrates time series transformations into explanations. Lastly, we present three use cases, verifying that our technique enables users to (1)~explore data transformations and feature relevance, (2)~identify model behavior and decision boundaries, as well as, (3)~the reason for misclassifications.
Entity Matching (EM) defines the task of learning to group objects by transferring semantic concepts from example groups (=entities) to unseen data. Despite the general availability of image data in the context of many EM-problems, most currently available EM-algorithms solely rely on (textual) meta data. In this paper, we introduce the first publicly available large-scale dataset for "visual entity matching", based on a production level use case in the retail domain. Using scanned advertisement leaflets, collected over several years from different European retailers, we provide a total of ~786k manually annotated, high resolution product images containing ~18k different individual retail products which are grouped into ~3k entities. The annotation of these product entities is based on a price comparison task, where each entity forms an equivalence class of comparable products. Following on a first baseline evaluation, we show that the proposed "visual entity matching" constitutes a novel learning problem which can not sufficiently be solved using standard image based classification and retrieval algorithms. Instead, novel approaches which allow to transfer example based visual equivalent classes to new data are needed to address the proposed problem. The aim of this paper is to provide a benchmark for such algorithms.
Information about the dataset, evaluation code and download instructions are provided under https://www.retail-786k.org/.
Following the traditional paradigm of convolutional neural networks (CNNs), modern CNNs manage to keep pace with more recent, for example transformer-based, models by not only increasing model depth and width but also the kernel size. This results in large amounts of learnable model parameters that need to be handled during training. While following the convolutional paradigm with the according spatial inductive bias, we question the significance of \emph{learned} convolution filters. In fact, our findings demonstrate that many contemporary CNN architectures can achieve high test accuracies without ever updating randomly initialized (spatial) convolution filters. Instead, simple linear combinations (implemented through efficient 1×1 convolutions) suffice to effectively recombine even random filters into expressive network operators. Furthermore, these combinations of random filters can implicitly regularize the resulting operations, mitigating overfitting and enhancing overall performance and robustness. Conversely, retaining the ability to learn filter updates can impair network performance. Lastly, although we only observe relatively small gains from learning 3×3 convolutions, the learning gains increase proportionally with kernel size, owing to the non-idealities of the independent and identically distributed (\textit{i.i.d.}) nature of default initialization techniques.
Modern CNNs are learning the weights of vast numbers of convolutional operators. In this paper, we raise the fundamental question if this is actually necessary. We show that even in the extreme case of only randomly initializing and never updating spatial filters, certain CNN architectures can be trained to surpass the accuracy of standard training. By reinterpreting the notion of pointwise ($1\times 1$) convolutions as an operator to learn linear combinations (LC) of frozen (random) spatial filters, we are able to analyze these effects and propose a generic LC convolution block that allows tuning of the linear combination rate. Empirically, we show that this approach not only allows us to reach high test accuracies on CIFAR and ImageNet but also has favorable properties regarding model robustness, generalization, sparsity, and the total number of necessary weights. Additionally, we propose a novel weight sharing mechanism, which allows sharing of a single weight tensor between all spatial convolution layers to massively reduce the number of weights.
This paper presents the new Deep Reinforcement Learning (DRL) library RL-X and its application to the RoboCup Soccer Simulation 3D League and classic DRL benchmarks. RL-X provides a flexible and easy-to-extend codebase with self-contained single directory algorithms. Through the fast JAX-based implementations, RL-X can reach up to 4.5x speedups compared to well-known frameworks like Stable-Baselines3.
We have developed a methodology for the systematic generation of a large image dataset of macerated wood references, which we used to generate image data for nine hardwood genera. This is the basis for a substantial approach to automate, for the first time, the identification of hardwood species in microscopic images of fibrous materials by deep learning. Our methodology includes a flexible pipeline for easy annotation of vessel elements. We compare the performance of different neural network architectures and hyperparameters. Our proposed method performs similarly well to human experts. In the future, this will improve controls on global wood fiber product flows to protect forests.
Wirtschaftliche Krisenzeiten implizieren häufig Liquiditätsengpässe und bei kompletter Zahlungsunfähigkeit auch Insolvenzen. Das Instrument des Working Capital Management hilft bei der schnelleren Freisetzung von gebundenem Kapital. Sofern ein datengetriebenes Management unter Einsatz von Business-Analytics-Techniken und mit der dafür notwendigen technisch-organisatorischen Infrastruktur eingesetzt wird, entstehen neue Möglichkeiten von Einsichten in die Prozesslandschaft und die Optimierung von Durchlaufzeiten. Das Ziel ist der Aufbau eines Working-Capital- Analytics-Ansatzes.
This article provides an overview of the legal framework for website marketing. The presentation of the numerous legal provisions, which are spread over several areas of law, is oriented towards business challenges and measures. After placing the website in the context of marketing, the article focuses on the legal framework relating to the establishment, design and operation of a website. If, in addition to its communication function, a website also has a sales function, i. e. in e-commerce (online trade), additional specific legal conditions must be taken into account.
Schulen müssen bei ihrer Profilbildung mehr leisten als die reine Marketingpositionierung erfordert. Sie müssen für alle am Schulleben Beteiligten einen Sinn stiften. Es geht letztlich um eine Veränderung der Schulkultur, indem die Grundüberzeugungen und der Sinn und Zweck der Schule klar herausgearbeitet werden. Methoden aus dem Bereich der Entwicklung von Unternehmens- und Organisationskultur können hier wirksam zum Einsatz kommen.
In an extensive research project, we have assessed the application of different service models by export credit agencies (ECAs) and export-import banks (EXIMs). We conducted interviews with 35 representatives of ECAs and EXIMs from 27 countries. The question guiding this study is: How do ECAs and EXIMs adopt public service models for supporting exporters? We conducted a holistic multiple case study, investigating if and how these organisations apply public service models developed by Schedler and Guenduez, and which roles of the state are relevant. We find that there is a variety of different service models used by ECAs and EXIMs, and that the service model approaches have great potential to learn from each other and innovate existing services.
Seit mehr als 40 Jahren wiederholen sich Diskussionen und Kontroversen über Sinn und Unsinn von Informationstechnik (IT) in Bildungseinrichtungen. Wurde bislang über das Arbeiten an und mit PC, Laptop oder Tablet debattiert, drehen sich aktuelle Diskussionen verstärkt um netzbasierte Anwendungen mit Rückkanal für Schülerdaten. Das Schüler*innenverhalten wird per Software ausgewertet, um Lehrinhalte automatisiert und „individualisiert“ anzupassen. Ergänzt werden solche Lernprogramme um Anwendungen der sogenannten „Künstliche Intelligenz“ (KI), die als „Lernbegleiter“ fungieren und zumindest perspektivisch fehlende Lehrkräfte ersetzen (sollen). Damit werden technische Systeme in Schulen etabliert, von denen nicht einmal mehr die Entwickler wissen, was diese Algorithmen genau tun.
Das erfordert einen kritisch-reflektierenden Diskurs. Dafür vertritt Ralf Lankau im vorliegenden Aufsatz die These, dass essenzielle Elemente der Bildung, wie die Erziehung zu Selbstbewusstsein, Reflexion und einer kritischen Bürgerschaft, mit solchen Lernprogrammen verloren gehen.
Staatliche Exportkreditagenturen und Export-Import-Banken finanzieren, versichern und garantieren jährlich fast 1 Bio. US-Dollar – mehr als 3 % der globalen Güterexporte. Ihre Interventionen sind an internationale Rahmenbedingungen gebunden, insbesondere an das WTO-Subventionsübereinkommen (ASCM) und den OECD-Konsensus. Das komplexe Zusammenspiel beider Rechtsrahmen sorgt seit langem für Herausforderungen, vor allem hinsichtlich des Anwendungsbereichs des “safe haven” des ASCM und des “Matching”-Mechanismus der OECD. In den vergangenen Jahren hinzugekommen ist die Problematik neuer Instrumente der Exportvor- sowie der Klimafinanzierung. Der folgende Beitrag erörtert Herausforderungen und Lösungsansätze. Er zeigt auf, dass der neue OECD-Konsensus trotz zahlreicher Verbesserungen zentrale rechtliche Probleme nicht behebt.