Ute Schmid

Ute Schmid
Otto-Friedrich-Universität Bamberg · Department of Applied Computer Sciences

Prof. Dr.

About

297
Publications
30,524
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
1,430
Citations
Introduction
research interests: Interpretable machine learning; human-lilke machine-learning; relational learning; inductive programming; explaining black-box classifiers methods: inductive logic programming; logic models; psychological experiments current projects: explaining classifiers for facial expressions of pain (PainFaceReader); a cognitive companion to delete irrelevant digital objects (Dare2Del); explaining classifiers for medical image data (TraMeExCo)
Additional affiliations
September 2004 - present
Otto-Friedrich-Universität Bamberg
Position
  • Professor
March 2001 - August 2004
Universität Osnabrück
Position
  • Lecturer
Education
April 1990 - June 1994
Technische Universität Berlin
Field of study
  • Computer Science (Informatik)
October 1989 - June 1994
Technische Universität Berlin
Field of study
  • Computer Science/Cognitive Science
October 1986 - March 1989
Technische Universität Berlin
Field of study
  • Psychologie

Publications

Publications (297)
Article
Machine learning based image classification algorithms, such as deep neural network approaches, will be increasingly employed in critical settings such as quality control in industry, where transparency and comprehensibility of decisions are crucial. Therefore, we aim to extend the defect detection task towards an interactive human-in-the-loop appr...
Conference Paper
Nowadays, Artificial Intelligence (AI) algorithms show a strong performance for many use cases, making them desirable for real-world scenarios where the algorithms provide high-impact decisions. However, one major drawback of AI algorithms is their susceptibility to bias and resulting unfairness. This has a huge influence for their application, as...
Chapter
Would you trust physicians if they cannot explain their decisions to you? Medical diagnostics using machine learning gained enormously in importance within the last decade. However, without further enhancements many state-of-the-art machine learning methods are not suitable for medical application. The most important reasons are insufficient data s...
Conference Paper
This paper presents results from a video-based study on the impact of prior information on the user experience dimensions perceived intelligence, subjective performance, and trust in autonomous driving. A simulated autonomous driving situation is presented to test participants, while they are given different prior information in terms of descriptio...
Preprint
Full-text available
The topic of comprehensibility of machine-learned theories has recently drawn increasing attention. Inductive Logic Programming (ILP) uses logic programming to derive logic theories from small data based on abduction and induction techniques. Learned theories are represented in the form of rules as declarative descriptions of obtained knowledge. In...
Article
Full-text available
In recent research, human-understandable explanations of machine learning models have received a lot of attention. Often explanations are given in form of model simplifications or visualizations. However, as shown in cognitive science as well as in early AI research, concept understanding can also be improved by the alignment of a given instance fo...
Preprint
Full-text available
Would you trust physicians if they cannot explain their decisions to you? Medical diagnostics using machine learning gained enormously in importance within the last decade. However, without further enhancements many state-of-the-art machine learning methods are not suitable for medical application. The most important reasons are insufficient data s...
Preprint
Full-text available
Artificial Intelligence and Digital Twins play an integral role in driving innovation in the domain of intelligent driving. Long short-term memory (LSTM) is a leading driver in the field of lane change prediction for manoeuvre anticipation. However, the decision-making process of such models is complex and non-transparent, hence reducing the trustw...
Preprint
Machine learning based image classification algorithms, such as deep neural network approaches, will be increasingly employed in critical settings such as quality control in industry, where transparency and comprehensibility of decisions are crucial. Therefore, we aim to extend the defect detection task towards an interactive human-in-the-loop appr...
Article
Full-text available
Introduction: The experience of pain is regularly accompanied by facial expressions. The gold standard for analyzing these facial expressions is the Facial Action Coding System (FACS), which provides so-called action units (AUs) as parametrical indicators of facial muscular activity. Particular combinations of AUs have appeared to be pain-indicati...
Preprint
Full-text available
One major drawback of deep neural networks (DNNs) for use in sensitive application domains is their black-box nature. This makes it hard to verify or monitor complex, symbolic requirements. In this work, we present a simple, yet effective, approach to verify whether a trained convolutional neural network (CNN) respects specified symbolic background...
Chapter
Full-text available
Zusammenfassung Verfahren der Künstlichen Intelligenz, insbesondere datenintensive Methoden des maschinellen Lernens, halten immer mehr Einzug in industrielle Anwendungen. Im Normalfall werden KI-Anwendungen meist als fertige Black-Box-Komponenten betrachtet, welche nicht in der Lage sind, mit Anwendern zu interagieren. Am Beispiel von Parametriera...
Chapter
We propose a method for explaining the results of black box image classifiers to domain experts and end users, combining two example-based explanatory approaches: Firstly, prototypes as represen- tative data points for classes, and secondly, contrastive example com- parisons in the form of near misses and near hits. A prototype globally explains th...
Conference Paper
Full-text available
Human gender bias is reflected in language and text production. Because state-of-the-art machine translation (MT) systems are trained on large corpora of text, mostly generated by humans, gender bias can also be found in MT. For instance when occupations are translated from a language like English, which mostly uses gender neutral words, to a langu...
Preprint
Full-text available
In the last years, XAI research has mainly been concerned with developing new technical approaches to explain deep learning models. Just recent research has started to acknowledge the need to tailor explanations to different contexts and requirements of stakeholders. Explanations must not only suit developers of models, but also domain experts as w...
Chapter
In the last years, XAI research has mainly been concerned with developing new technical approaches to explain deep learning models. Just recent research has started to acknowledge the need to tailor explanations to different contexts and requirements of stakeholders. Explanations must not only suit developers of models, but also domain experts as w...
Preprint
Full-text available
Human gender bias is reflected in language and text production. Because state-of-the-art machine translation (MT) systems are trained on large corpora of text, mostly generated by humans, gender bias can also be found in MT. For instance when occupations are translated from a language like English, which mostly uses gender neutral words, to a langu...
Chapter
We propose Case-based reasoning (CBR) as an approach to assist human operators who control special purpose production machines. Our support system automatically extracts knowledge from machine data and creates recommendations, which help the operators solve problems with a production machine. This support has to be comprehensive and maintainable by...
Article
Full-text available
In this design study, we present IRVINE, a Visual Analytics (VA) system, which facilitates the analysis of acoustic data to detect and understand previously unknown errors in the manufacturing of electrical engines. In serial manufacturing processes, signatures from acoustic data provide valuable information on how the relationship between multiple...
Chapter
With the growing number of applications of machine learning in complex real-world domains machine learning research has to meet new requirements to deal with the imperfections of real world data and the legal as well as ethical obligations to make classifier decisions transparent and comprehensible. In this contribution, arguments for interpretable...
Preprint
In recent research, human-understandable explanations of machine learning models have received a lot of attention. Often explanations are given in form of model simplifications or visualizations. However, as shown in cognitive science as well as in early AI research, concept understanding can also be improved by the alignment of a given instance fo...
Preprint
Full-text available
Explainable AI has emerged to be a key component for black-box machine learning approaches in domains with a high demand for reliability or transparency. Examples are medical assistant systems, and applications concerned with the General Data Protection Regulation of the European Union, which features transparency as a cornerstone. Such demands req...
Article
Full-text available
Given the recent successes of Deep Learning in AI there has been increased interest in the role and need for explanations in machine learned theories. A distinct notion in this context is that of Michie’s definition of ultra-strong machine learning (USML). USML is demonstrated by a measurable increase in human performance of a task following provis...
Article
Full-text available
Explainability has been recognized as an important requirement of artificial intelligence (AI) systems. Transparent decision policies and explanations regarding why an AI system comes about a certain decision is a pre-requisite if AI is supposed to support human decision-making or if human-AI collaborative decision-making is envisioned. Human-AI in...
Article
With the increasing prevalence of Machine Learning in everyday life, a growing number of people will be provided with Machine-Learned assessments on a regular basis. We believe that human users interacting with systems based on Machine-Learned classifiers will demand and profit from the systems’ decisions being explained in an approachable and comp...
Article
Full-text available
Increasing quality and performance of artificial intelligence (AI) in general and machine learning (ML) in particular is followed by a wider use of these approaches in everyday life. As part of this development, ML classifiers have also gained more importance for diagnosing diseases within biomedical engineering and medical sciences. However, many...
Preprint
Given the recent successes of Deep Learning in AI there has been increased interest in the role and need for explanations in machine learned theories. A distinct notion in this context is that of Michie's definition of Ultra-Strong Machine Learning (USML). USML is demonstrated by a measurable increase in human performance of a task following provis...
Chapter
Full-text available
Digitale Medien sind aus der heutigen Lebens- und Arbeitswelt nicht mehr wegzudenken. Entsprechend rückt die Förderung medienbezogener Kompetenzen auch in den Fokus der schulischen Bildung. Der vorliegende Beitrag stellt den Ansatz der Experimentierkiste Informatik zur Verzahnung medienpädagogischer Themen mit informatischer Grundbildung vor. Die E...
Chapter
Explainable AI has emerged to be a key component for black-box machine learning approaches in domains with a high demand for reliability or transparency. Examples are medical assistant systems, and applications concerned with the General Data Protection Regulation of the European Union, which features transparency as a cornerstone. Such demands req...
Article
Full-text available
In modern work environments, it can be difficult for workers to avoid becoming distracted from their current task. This study investigates person–situation interactions to predict thought control activities (kind of self-control), which aim to stop distracting thoughts that enter the mind. Specifically, it was examined (1) how challenging work dema...
Article
Damit Kinder digitale Medien als kreative Werkzeuge begreifen, müssen sie diese souverän nutzen, deren Funktionsweise aber auch hinterfragen können. Der integrative Ansatz der Forschungsgruppe Elementarinformatik (FELI) berücksichtigt eine medienpädagogische Perspektive, die die Vermittlung informatischer Grundkenntnisse mit einbezieht. Hierzu muss...
Chapter
End-to-end learning with deep neural networks, such as convolutional neural networks (CNNs), has been demonstrated to be very successful for different tasks of image classification. To make decisions of black-box approaches transparent, different solutions have been proposed. LIME is an approach to explainable AI relying on segmenting images into s...
Chapter
With the increasing number of deep learning applications, there is a growing demand for explanations. Visual explanations provide information about which parts of an image are relevant for a classifier’s decision. However, highlighting of image parts (e.g., an eye) cannot capture the relevance of a specific feature value for a class (e.g., that the...
Preprint
Neural networks with high performance can still be biased towards non-relevant features. However, reliability and robustness is especially important for high-risk fields such as clinical pain treatment. We therefore propose a verification pipeline, which consists of three steps. First, we classify facial expressions with a neural network. Next, we...
Article
Full-text available
Exploiting mutual explanations for interactive learning is presented as part of an interdisciplinary research project on transparent machine learning for medical decision support. Focus of the project is to combine deep learning black box approaches with interpretable machine learning for classification of different types of medical images to combi...
Chapter
Im vorliegenden Beitrag wird dafür plädiert, im Kontext der Diskussion zur digitalen Bildung informatische Bildung zum Gegenstand kontinuierlicher Bildungsprozesse zu machen und bereits im Kindergarten die Ausbildung informatischer Vorläuferfähigkeiten zu fördern, auf die der medienbezogene Unterricht in der Grundschule aufbauen kann. Hierzu wurde...
Book
This book constitutes the refereed proceedings of the 43rd German Conference on Artificial Intelligence, KI 2020, held in Bamberg, Germany, in September 2020. The 16 full and 12 short papers presented together with 6 extended abstracts in this volume were carefully reviewed and selected from 62 submissions. As well-established annual conference ser...
Article
Pain sensation is essential for survival, since it draws attention to physical threat to the body. Pain assessment is usually done through self-reports. However, self-assessment of pain is not available in the case of noncommunicative patients, and therefore, observer reports should be relied upon. Observer reports of pain could be prone to errors...
Preprint
End-to-end learning with deep neural networks, such as convolutional neural networks (CNNs), has been demonstrated to be very successful for different tasks of image classification. To make decisions of black-box approaches transparent, different solutions have been proposed. LIME is an approach to explainable AI relying on segmenting images into s...
Preprint
Full-text available
With the increasing number of deep learning applications, there is a growing demand for explanations. Visual explanations provide information about which parts of an image are relevant for a classifier's decision. However, highlighting of image parts (e.g., an eye) cannot capture the relevance of a specific feature value for a class (e.g., that the...
Conference Paper
Damit Kinder zu souveränen Akteuren in einer zunehmend von Digitalisierung geprägten Welt werden, bedarf es zielgerichteter Bildungsangebote. Im Workshop werden die von der Forschungsgruppe Elementarinformatik entwickelten Lehr-Lern-Konzepte der Experimentierkiste Informatik vorgestellt, die anschließend in Kleingruppen erprobt werden können. Die M...
Research Proposal
Full-text available
The ability to formulate formally verifiable requirements is crucial for the safety verification of software units in the automotive industries. However, it is very restricted for complex perception tasks involving deep neural networks (DNNs) due to their black-box character. For a solution we propose to identify or enforce human interpretable conc...
Book
Sind Maschinen bald schlauer als wir? Haben dann die Roboter das Sagen? Um diese Fragen realistisch beantworten zu können, musst du erst einmal herausfinden, was Künstliche Intelligenz eigentlich ist. Dieses Buch hilft dir dabei. Kapitel für Kapitel beantwortet es folgende Fragen: Wie denken Computer? Wie lernen Computer? Wie spielen Computer? Wie...
Preprint
Full-text available
This roadmap paper describes an interdisciplinary approach to develop an image-based transparent medical expert companion for facial pain estimation. The companion combines human understandable logic rules and visualization to explain the results. Using this information, healthcare professionals can then make informed decisions.
Article
Deep neural networks are successfully used for object and face recognition in images and videos. In order to be able to apply such networks in practice, for example in hospitals as a pain recognition tool, the current procedures are only suitable to a limited extent. The advantage of deep neural methods is that they can learn complex non-linear rel...
Article
Full-text available
Future work environments will offer technical applications to manage increasing amounts of information for organizations, teams, and individuals. In this context, psychological concepts of intentional forgetting (IF) can be applied to improve the performance of work systems or to extend the cognitive capacities of humans in technical systems. Diffe...
Article
Full-text available
Emerging technologies at work encourage the collection and storage of large amounts of data. However, these vast quantities of data are likely to impair efficient work decisions by employees over time, with negative consequences for the organization. As human attention increasingly represents the scarce resource at work, the present paper focuses o...
Article
Future work environments offer numerous technical applications to manage increasing amounts of information for organizations, teams, and individuals. Psychological concepts of intentional forgetting (IF) can be applied to improve the performance of work systems or to extend cognitive capacities of humans in technical systems. Different IF mechanism...
Presentation
Kinder wachsen in einer zunehmend digitalisierten Welt auf. Das Konzept der Elementarinformatik sieht vor, Medienkompetenz und informatische Grundkompetenzen miteinander zu verzahnen. Hierzu wurden Spiel- und Erfahrungsmaterialien mit Begleitmaterial für pädagogische Fach- und Lehrkräfte zum Einsatz in Kindertagesstätten und Grundschulen konzipiert...
Conference Paper
Deep learning networks are successfully used for object and face recognition in images and videos. In order to be able to apply such networks in practice, for example in hospitals as a pain recognition tool, the current procedures are only suitable to a limited extent. The advantage of deep learning methods is that they can learn complex non-linear...
Article
Dare2Del is an assistive system which facilitates intentional forgetting of irrelevant digital objects. For an assistive system to be helpful, the user has to trust the system’s decisions. Explanations are a crucial component in establishing this trust. We will introduce different types of explanations which can vary along different dimensions such...
Conference Paper
Many people believe that every fourth year is a leap year. However, this rule is too general: year X is a leap year if X is divisible by 4 except if X is divisible by 100 except if X is divisible by 400. We call such a theory with alternating generalisation and specialisation a step-wise narrowed theory. We present and evaluate an extension to the...
Chapter
Full-text available
Current trends, like digital transformation and ubiquitous computing, yield in massive increase in available data and information. In artificial intelligence (AI) systems, capacity of knowledge bases is limited due to computational complexity of many inference algorithms. Consequently, continuously sampling information and unfiltered storing in kno...
Article
Full-text available
During the 1980s Michie defined Machine Learning in terms of two orthogonal axes of performance: predictive accuracy and comprehensibility of generated hypotheses. Since predictive accuracy was readily measurable and comprehensibility not so, later definitions in the 1990s, such as Mitchell’s, tended to use a one-dimensional approach to Machine Lea...
Article
In jüngerer Zeit wendet sich die Informatikdidaktik in Deutschland zunehmend dem Primärbereich zu. Aktuell werden in einem Arbeitskreis der Gesellschaft für Informatik Bildungsstandards für die Grundschule entwickelt und zur Diskussion gestellt. Im vorliegenden Beitrag wird diese Diskussion aufgegriffen. Zunächst werden Konzepte und wissenschaftlic...
Conference Paper
We present the mentoring program make IT which was designed to motivate female high school students to study computer science. The measures of the program address different factors which have been shown to hinder a decision of girls to study a STEM¹ subject. First empirical results of a mainly qualitative evaluation of the program show that the pro...
Article
Full-text available
Im vorliegenden Beitrag plädieren wir für eine Verzahnung von Informatikdidaktik mit Medienpädagogik und Schulpädagogik. Es wird postuliert, dass Mediennutzung und Vermittlung von Informatikkonzepten wechselseitig aufeinander bezogen werden sollten. Bei einer Vermittlung von Informatikkonzepten ohne Bezug zum Computer wird es Kindern nicht gelingen...
Article
Full-text available
Obwohl ein Anstieg des Frauenanteils in den Informatikstudiengängen zu verzeichnen ist, gilt die IT-Branche nach wie vor als Männerdomäne. Der weibliche Anteil in deutschen IT-Abteilungen beträgt knapp 10 Prozent (Weitzel et al. 2017). Ein Grund für die mangelnde Präsenz der Frauen im IT-Bereich könnte die geringere Erfolgserwartung der Studentinne...
Article
This article aims to investigate gender differences among German computer sciences graduates. Utilizing data from the unique Bamberg Alumnae Tracking Study, we analyze whether or not male and female graduates differ in their level of academic achievement in computer sciences. We also examine the graduates' self-perceptions of their professional ski...