Search

The rise of machine-learning applications in domains with critical end-user impact has led to a growing concern about the fairness of learned models, with the goal of avoiding biases that negatively impact specific demographic groups. Most existing bias-mitigation strategies adapt the importance of data instances during pre-processing. Since fairness is a contextual concept, we advocate for an interactive machine-learning approach that enables users to provide iterative feedback for model adaptation. Specifically, we propose to adapt the explanatory interactive machine-learning approach Caipi for fair machine learning. FairCaipi incorporates human feedback in the loop on predictions and explanations to improve the fairness of the model. Experimental results demonstrate that FairCaipi outperforms a state-of-the-art pre-processing bias mitigation strategy in terms of the fairness and the predictive performance of the resulting machine-learning model. We show that FairCaipi can both uncover and reduce bias in machine-learning models and allows us to detect human bias.

The anthropogenic climate crisis results in the gradual loss of tree species in locations where they were previously able to grow. This leads to increasing workloads and requirements for foresters and arborists as they are forced to restructure their forests and city parks. The advancements in computer vision (CV)—especially in supervised deep learning (DL)—can help cope with these new tasks. However, they rely on large, carefully annotated datasets to produce good and generalizable models. This paper presents BAMFORESTS: a dataset with 27,160 individually delineated tree crowns in 105 ha of very-high-resolution UAV imagery gathered with two different sensors from two drones. BAMFORESTS covers four areas of coniferous, mixed, and deciduous forests and city parks. The labels contain instance segmentations of individual trees, and the proposed splits are balanced by tree species and vitality. Furthermore, the dataset contains the corrected digital surface model (DSM), representing tree heights. BAMFORESTS is annotated in the COCO format and is especially suited for training deep neural networks (DNNs) to solve instance segmentation tasks. BAMFORESTS was created in the BaKIM project and is freely available under the CC BY 4.0 license.

Interactive Machine Learning (IML) can enable intelligent systems to interactively learn from their end-users, and is quickly becoming more and more relevant to many application domains. Although it places the human in the loop, interactions are mostly performed via mutual explanations that miss contextual information. Furthermore, current model-agnostic IML strategies such as CAIPI are limited to ’destructive’ feedback, meaning that they solely allow an expert to prevent a learner from using irrelevant features. In this work, we propose a novel interaction framework called Semantic Interactive Learning for the domain of document classification, located at the intersection between Natural Language Processing (NLP) and Machine Learning (ML). We frame the problem of incorporating constructive and contextual feedback into the learner as a task involving finding an architecture that enables more semantic alignment between humans and machines while at the same time helping to maintain the statistical characteristics of the input domain when generating user-defined counterexamples based on meaningful corrections. Therefore, we introduce a technique called SemanticPush that is effective for translating conceptual corrections of humans to non-extrapolating training examples such that the learner’s reasoning is pushed towards the desired behavior. Through several experiments we show how our method compares to CAIPI, a state of the art IML strategy, in terms of Predictive Performance and Local Explanation Quality in downstream multi-class classification tasks. Especially in the early stages of interactions, our proposed method clearly outperforms CAIPI while allowing for contextual interpretation and intervention. Overall, SemanticPush stands out with regard to data efficiency, as it requires fewer queries from the pool dataset to achieve high accuracy.

In the digital age, saving and accumulating large amounts of digital data is a common phenomenon. However, saving does not only consume energy, but may also cause information overload and prevent people from staying focused and working effectively. We present and systematically examine an explanatory AI system (Dare2Del), which supports individuals to delete irrelevant digital objects. To give recommendations for the optimization of related human-computer interactions, we vary different design features (explanations, familiarity, verifiability) within and across three experiments (N1 = 61, N2 = 33, N3= 73). Moreover, building on the concept of distributed cognition, we check possible cross-connections between external (digital) and internal (human) memory. Specifically, we examine whether deleting external files also contributes to human forgetting of the related mental representations. Multilevel modeling results show the importance of presenting explanations for the acceptance of deleting suggestions in all three experiments, but also point to the need of their verifiability to generate trust in the system. However, we did not find clear evidence that deleting computer files contributes to human forgetting of the related memories. Based on our findings, we provide basic recommendations for the design of AI systems that can help to reduce the burden on people and the digital environment, and suggest directions for future research.

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-indicative. The manual coding of AUs is, however, too time- and labor-intensive in clinical practice. New developments in automatic facial expression analysis have promised to enable automatic detection of AUs, which might be used for pain detection. Objective. Our aim is to compare manual with automatic AU coding of facial expressions of pain. Methods. FaceReader7 was used for automatic AU detection. We compared the performance of FaceReader7 using videos of 40 participants (20 younger with a mean age of 25.7 years and 20 older with a mean age of 52.1 years) undergoing experimentally induced heat pain to manually coded AUs as gold standard labeling. Percentages of correctly and falsely classified AUs were calculated, and we computed as indicators of congruency, “sensitivity/recall,” “precision,” and “overall agreement (F1).” Results. The automatic coding of AUs only showed poor to moderate outcomes regarding sensitivity/recall, precision, and F1. The congruency was better for younger compared to older faces and was better for pain-indicative AUs compared to other AUs. Conclusion. At the moment, automatic analyses of genuine facial expressions of pain may qualify at best as semiautomatic systems, which require further validation by human observers before they can be used to validly assess facial expressions of pain.

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 of those ubiquitous high-performing ML algorithms reveal a black-box-nature, leading to opaque and incomprehensible systems that complicate human interpretations of single predictions or the whole prediction process. This puts up a serious challenge on human decision makers to develop trust, which is much needed in life-changing decision tasks. This paper is designed to answer the question how expert companion systems for decision support can be designed to be interpretable and therefore transparent and comprehensible for humans. On the other hand, an approach for interactive ML as well as human-in-the-loop-learning is demonstrated in order to integrate human expert knowledge into ML models so that humans and machines act as companions within a critical decision task. We especially address the problem of Semantic Alignment between ML classifiers and its human users as a prerequisite for semantically relevant and useful explanations as well as interactions. Our roadmap paper presents and discusses an interdisciplinary yet integrated Comprehensible Artificial Intelligence (cAI)-transition-framework with regard to the task of medical diagnosis. We explain and integrate relevant concepts and research areas to provide the reader with a hands-on-cookbook for achieving the transition from opaque black-box models to interactive, transparent, comprehensible and trustworthy systems. To make our approach tangible, we present suitable state of the art methods with regard to the medical domain and include a realization concept of our framework. The emphasis is on the concept of Mutual Explanations (ME) that we introduce as a dialog-based, incremental process in order to provide human ML users with trust, but also with stronger participation within the learning process.

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 demands (time pressure, task complexity) activate workers’ thought control to stop distractive thoughts (nlevel2 = 143) and relate to the effort to do so (nlevel2 = 91) in daily working life and (2) how these relationships differ according workers’ general cognitive ability to suppress unwanted thoughts. To understand these person–situation interactions, an experience sampling study was combined with a laboratory task assessing the ability to suppress unwanted thoughts (think/no-think task). Multilevel modeling revealed that workers’ engage more often and more intensively in thought control activities at a moderate level of time pressure but only when they had a higher general ability to suppress unwanted thoughts. For workers with a lower ability to suppress unwanted thoughts, increasing time pressure was negatively related to thought control activities, even at very low levels of time pressure. Thus, whether time pressure activates or hinders thought control depends on individuals’ ability to suppress distractive thoughts.

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 Studentinnen im Studium sein. In diesem Beitrag wird untersucht, ob vorangegangene Schulleistungen sowie intrinsische Motivation für die Studiengangswahl, nämlich Begabung und Interesse für das Fach, die subjektive Einschätzung des Studienerfolgs von Informatikstudierenden beeinflussen. Obwohl Studentinnen sich im Vergleich zu ihren Kommilitonen in ihren durchschnittlichen Mathematikleistungen nicht signifikant unterscheiden und sie im Durchschnitt die bessere Abiturabschlussnote erzielen, unterschätzen sie sich in ihrem persönlichen Studienerfolg signifikant, insbesondere in stark techniklastigen Informatikstudiengängen. Ebenso können Studentinnen von einer hohen intrinsischen Motivation, hinsichtlich ihrer Erfolgseinschätzungen im Studium nicht profitieren. Die durchgeführte Analyse bezieht sich auf das Datenmaterial aus dem ESF-Forschungsprojekt „Alumnae Tracking“.

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, die Beziehung von Informatik zur Mediennutzung selbständig herzustellen. Umgekehrt sind Kinder hochmotiviert, digitale Medien zu nutzen, wenden sie allerdings häufig rein konsumierend an. Es wird ein Konzept für elementarinformatische Unterrichtseinheiten vorgestellt, das die Integration digitaler Medien und informatischer Inhalte in die Vor- und Grundschule zum Ziel hat. Wir plädieren für eine Vermittlung von Informatikkonzepten aus drei Perspektiven: Bezug des Konzepts zur Lebenswirklichkeit der Kinder, spielerisch-entdeckendes Lernen abstrakter Konzepte durch «begreifbares» Material und «Wiedererkennen» der gelernten Konzepte bei der Nutzung digitaler Medien. Es werden Lerneinheiten vorgeschlagen, die in verschiedene Fächer integriert werden können. Zudem wird eine Handreichung für pädagogische Fachkräfte und Lehrkräfte beschrieben, die darauf abzielt, diesen die Integration informatischer Themen unter Nutzung digitaler Medien in den Unterricht zu erleichtern. Der Schwerpunkt des Beitrags liegt auf der Begründung der elementarinformatischen Konzepte, zusätzlich werden Verweise auf bereits durchgeführte Massnahme in verschiedenen Bildungseinrichtungen und erste empirische Befunde gegeben.