Automating the monitoring of industrial processes has the potential to enhance efficiency and optimize quality by promptly detecting abnormal events and thus facilitating timely interventions. Deep learning, with its capacity to discern non-trivial patterns within large datasets, plays a pivotal role in this process. Standard deep learning methods are suitable to solve a specific task given a specific type of data. During training, deep learning demands large volumes of labeled data. However, due to the dynamic nature of the industrial processes and environment, it is impractical to acquire large-scale labeled data for standard deep learning training for every slightly different case anew. Deep transfer learning offers a solution to this problem. By leveraging knowledge from related tasks and accounting for variations in data distributions, the transfer learning framework solves new tasks with little or even no additional labeled data. The approach bypasses the need to retrain a model from scratch for every new setup and dramatically reduces the labeled data requirement. This survey first provides an in-depth review of deep transfer learning, examining the problem settings of transfer learning and classifying the prevailing deep transfer learning methods. Moreover, we delve into applications of deep transfer learning in the context of a broad spectrum of time series anomaly detection tasks prevalent in primary industrial domains, e.g., manufacturing process monitoring, predictive maintenance, energy management, and infrastructure facility monitoring. We discuss the challenges and limitations of deep transfer learning in industrial contexts and conclude the survey with practical directions and actionable suggestions to address the need to leverage diverse time series data for anomaly detection in an increasingly dynamic production environment.

Deep learning, especially in the form of convolutional neural networks (CNNs), has triggered substantial improvements in computer vision and related fields in recent years. This progress is attributed to the shift from designing features and subsequent individual sub-systems towards learning features and recognition systems end to end from nearly unprocessed data. For speaker clustering, however, it is still common to use handcrafted processing chains such as MFCC features and GMM-based models. In this paper, we use simple spectrograms as input to a CNN and study the optimal design of those networks for speaker identification and clustering. Furthermore, we elaborate on the question how to transfer a network, trained for speaker identification, to speaker clustering. We demonstrate our approach on the well known TIMIT dataset, achieving results comparable with the state of the art-without the need for handcrafted features.

Face Recognition (FR) is increasingly influencing our lives: we use it to unlock our phones; police uses it to identify suspects. Two main concerns are associated with this increase in facial recognition: (1) the fact that these systems are typically less accurate for marginalized groups, which can be described as “bias”, and (2) the increased surveillance through these systems. Our paper is concerned with the first issue. Specifically, we explore an intuitive technique for reducing this bias, namely “blinding” models to sensitive features, such as gender or race, and show why this cannot be equated with reducing bias. Even when not designed for this task, facial recognition models can deduce sensitive features, such as gender or race, from pictures of faces—simply because they are trained to determine the “similarity” of pictures. This means that people with similar skin tones, similar hair length, etc. will be seen as similar by facial recognition models. When confronted with biased decision-making by humans, one approach taken in job application screening is to “blind” the human decision-makers to sensitive attributes such as gender and race by not showing pictures of the applicants. Based on a similar idea, one might think that if facial recognition models were less aware of these sensitive features, the difference in accuracy between groups would decrease. We evaluate this assumption—which has already penetrated into the scientific literature as a valid de-biasing method—by measuring how “aware” models are of sensitive features and correlating this with differences in accuracy. In particular, we blind pre-trained models to make them less aware of sensitive attributes. We find that awareness and accuracy do not positively correlate, i.e., that bias $$\ne$$≠ awareness. In fact, blinding barely affects accuracy in our experiments. The seemingly simple solution of decreasing bias in facial recognition rates by reducing awareness of sensitive features does thus not work in practice: trying to ignore sensitive attributes is not a viable concept for less biased FR.

Segmenting newspaper pages into articles that semantically belong together is a necessary prerequisite for article-based information retrieval on print media collections like e.g. archives and libraries. It is challenging due to vastly differing layouts of papers, various content types and different languages, but commercially very relevant for e.g. media monitoring. We present a semantic segmentation approach based on the visual appearance of each page. We apply a fully convolutional neural network (FCN) that we train in an end-to-end fashion to transform the input image into a segmentation mask in one pass. We show experimentally that the FCN performs very well: it outperforms a deep learning-based commercial solution by a large margin in terms of segmentation quality while in addition being computationally two orders of magnitude more efficient.

We present the “AI-Atlas” didactic concept as a coherent set of best practices for teaching Artificial Intelligence (AI) and Machine Learning (ML) to a technical audience in tertiary education, and report on its implementation and evaluation within a design-based research framework and two actual courses: an introduction to AI within the final year of an undergraduate computer science program, as well as an introduction to ML within an interdisciplinary graduate program in engineering. The concept was developed in reaction to the recent AI surge and corresponding demand for foundational teaching on the subject to a broad and diverse audience, with on-site teaching of small classes in mind and designed to build on the specific strengths in motivational public speaking of the lecturers. The research question and focus of our evaluation is to what extent the concept serves this purpose, specifically taking into account the necessary but unforeseen transfer to ongoing hybrid and fully online teaching since March 2020 due to the COVID-19 pandemic. Our contribution is two-fold: besides (i) presenting a general didactic concept for tertiary engineering education in AI and ML, ready for adoption, we (ii) draw conclusions from the comparison of qualitative student evaluations (n = 24–30) and quantitative exam results (n = 62–113) of two full semesters under pandemic conditions with the result of previous years (participants from Zurich, Switzerland). This yields specific recommendations for the adoption of any technical curriculum under flexible teaching conditions—be it on-site, hybrid, or online.