Refine
Year of publication
Document Type
- Conference Proceeding (19)
- Article (unreviewed) (16)
- Article (reviewed) (10)
- Doctoral Thesis (3)
- Report (3)
- Letter to Editor (1)
- Study Thesis (1)
Conference Type
- Konferenzartikel (14)
- Konferenz-Abstract (3)
- Konferenz-Poster (1)
- Sonstiges (1)
Has Fulltext
- no (53) (remove)
Is part of the Bibliography
- yes (53)
Keywords
- Deep Leaning (3)
- Deep Learning (3)
- Hochschuldidaktik (3)
- machine learning (3)
- Advanced Footwear Technology (2)
- Alexander von Humboldt (2)
- Artificial Intelligence (2)
- Biomechanics (2)
- Exercise Science (2)
- Export (2)
Institute
- Fakultät Elektrotechnik, Medizintechnik und Informatik (EMI) (ab 04/2019) (20)
- Fakultät Maschinenbau und Verfahrenstechnik (M+V) (13)
- Fakultät Wirtschaft (W) (9)
- IMLA - Institute for Machine Learning and Analytics (9)
- Fakultät Medien (M) (ab 22.04.2021) (7)
- INES - Institut für nachhaltige Energiesysteme (4)
- IBMS - Institute for Advanced Biomechanics and Motion Studies (ab 16.11.2022) (3)
- IfTI - Institute for Trade and Innovation (2)
- Zentrale Einrichtungen (2)
- ivESK - Institut für verlässliche Embedded Systems und Kommunikationselektronik (2)
Open Access
- Diamond (53) (remove)
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.
The COVID19 pandemic, a unique and devastating respiratory disease outbreak, has affected global populations as the disease spreads rapidly. Recent Deep Learning breakthroughs may improve COVID19 prediction and forecasting as a tool of precise and fast detection, however, current methods are still being examined to achieve higher accuracy and precision. This study analyzed the collection contained 8055 CT image samples, 5427 of which were COVID cases and 2628 non COVID. The 9544 Xray samples included 4044 COVID patients and 5500 non COVID cases. The most accurate models are MobileNet V3 (97.872 percent), DenseNet201 (97.567 percent), and GoogleNet Inception V1 (97.643 percent). High accuracy indicates that these models can make many accurate predictions, as well as others, are also high for MobileNetV3 and DenseNet201. An extensive evaluation using accuracy, precision, and recall allows a comprehensive comparison to improve predictive models by combining loss optimization with scalable batch normalization in this study. Our analysis shows that these tactics improve model performance and resilience for advancing COVID19 prediction and detection and shows how Deep Learning can improve disease handling. The methods we suggest would strengthen healthcare systems, policymakers, and researchers to make educated decisions to reduce COVID19 and other contagious diseases.
Convolutional neural networks (CNN) define the state-of-the-art solution on many perceptual tasks. However, current CNN approaches largely remain vulnerable against adversarial perturbations of the input that have been crafted specifically to fool the system while being quasi-imperceptible to the human eye. In recent years, various approaches have been proposed to defend CNNs against such attacks, for example by model hardening or by adding explicit defence mechanisms. Thereby, a small “detector” is included in the network and trained on the binary classification task of distinguishing genuine data from data containing adversarial perturbations. In this work, we propose a simple and light-weight detector, which leverages recent findings on the relation between networks’ local intrinsic dimensionality (LID) and adversarial attacks. Based on a re-interpretation of the LID measure and several simple adaptations, we surpass the state-of-the-art on adversarial detection by a significant m argin and reach almost perfect results in terms of F1-score for several networks and datasets. Sources available at: https://github.com/adverML/multiLID
Artificial Intelligence (AI) can potentially transform many aspects of modern society in various ways, including automation of tasks, personalization of products and services, diagnosis of diseases and their treatment, transportation, safety, and security in public spaces, etc. Recently, AI technology has been transforming the financial industry, offering new ways to analyse data and automate processes, reduce costs, increase efficiency, and provide more personalized services to customers. However, it also raised important ethical and regulatory questions that need to be addressed by the industry and society as a whole. The aim of the Erasmus+ project Transversal Skills in Applied Artificial Intelligence - TSAAI (KA220-HED - Cooperation Partnerships in higher education) has been to establish a training platform that will incorporate teaching guidelines based on a curriculum covering different areas of application of AI technology. In this work, we will focus on applying AI models in the financial and insurance sectors.
Running shoes were categorized either as motion control, cushioned, or minimal footwear in the past. Today, these categories blur and are not as clearly defined. Moreover, with the advances in manufacturing processes, it is possible to create individualized running shoes that incorporate features that meet individual biomechanical and experiential needs. However, specific ways to individualize footwear to reduce individual injury risk are poorly understood. Therefore, the purpose of this scoping review was to provide an overview of (1) footwear design features that have the potential for individualization; (2) human biomechanical variability as a theoretical foundation for individualization; (3) the literature on the differential responses to footwear design features between selected groups of individuals. These purposes focus exclusively on reducing running-related risk factors for overuse injuries. We included studies in the English language on adults that analyzed: (1) potential interaction effects between footwear design features and subgroups of runners or covariates (e.g., age, gender) for running-related biomechanical risk factors or injury incidences; (2) footwear perception for a systematically modified footwear design feature. Most of the included articles (n = 107) analyzed male runners. Several footwear design features (e.g., midsole characteristics, upper, outsole profile) show potential for individualization. However, the overall body of literature addressing individualized footwear solutions and the potential to reduce biomechanical risk factors is limited. Future studies should leverage more extensive data collections considering relevant covariates and subgroups while systematically modifying isolated footwear design features to inform footwear individualization.
Training deep neural networks using backpropagation is very memory and computationally intensive. This makes it difficult to run on-device learning or fine-tune neural networks on tiny, embedded devices such as low-power micro-controller units (MCUs). Sparse backpropagation algorithms try to reduce the computational load of on-device learning by training only a subset of the weights and biases. Existing approaches use a static number of weights to train. A poor choice of this so-called backpropagation ratio limits either the computational gain or can lead to severe accuracy losses. In this paper we present TinyProp, the first sparse backpropagation method that dynamically adapts the back-propagation ratio during on-device training for each training step. TinyProp induces a small calculation overhead to sort the elements of the gradient, which does not significantly impact the computational gains. TinyProp works particularly well on fine-tuning trained networks on MCUs, which is a typical use case for embedded applications. For typical datasets from three datasets MNIST, DCASE2020 and CIFAR10, we are 5 times faster compared to non-sparse training with an accuracy loss of on average 1%. On average, TinyProp is 2.9 times faster than existing, static sparse backpropagation algorithms and the accuracy loss is reduced on average by 6 % compared to a typical static setting of the back-propagation ratio.
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.
Public export credits and trade insurance require a global framework of institutions, rules and regulations to avoid subsidies and a race to the bottom. The extensive modernisation of the Arrangement on Officially Supported Export Credits (Arrangement) of the Organisation for Economic Co-operation and Development intends to re-level the playing field. This Practitioner Commentary describes the demand for adequate government interventions, considers the need for the reform and discusses key aspects of the new Arrangement. We argue that there is a breakthrough in several important areas such as tenors, repayment terms and green finance. However, we also find that the modernisation falls short in areas such as the interplay between different rulebooks, pre-shipment instruments' regulations and climate action.