AI systems can deliver scalable feedback in large courses and often achieve high consistency with human grading. Yet, students continue to view human feedback as more credible, actionable, and trustworthy, motivating growing interest in hybrid approaches that combine AI and human input. Despite advances in this area, three key challenges remain: (1) understanding when and why students escalate from AI to human support, (2) identifying how design interventions such as transparency, explainability, and endorsement affect trust and uptake, and (3) evaluating whether hybrid AI+human feedback models improve learning outcomes compared to AI-only or human-only systems. This study uses controlled experiments and structured interviews to investigate these questions. The results aim to guide the responsible design of hybrid feedback systems that align scalability with pedagogical credibility.

In response to the growing enrolment in software engineering programs, there is a pressing need for scalable methods to provide effective feedback for students. We designed a GPT-driven interactive assistant, FeedbackPulse, to aid educators in delivering high-quality feedback and alleviating their workload. FeedbackPulse provides real-time, personalised feedback suggestions to educators for improving their feedback to students. Preliminary evaluations of FeedbackPulse in a software engineering course have demonstrated its promising capabilities.

Test methods that can keep up with the ongoing increase in complexity of semiconductor products and their underlying technologies are an essential prerequisite for maintaining quality and safety of our daily lives and for continued success of our economies and societies. There is a huge potential how test methods can benefit from recent breakthroughs in domains such as artificial intelligence, data analytics, virtual/augmented reality, and security. The Graduate School on “Intelligent Methods for Semiconductor Test and Reliability” (GS-IMTR) at the University of Stuttgart is a large-scale, radically interdisciplinary effort to address the scientific-technological challenges in this domain. It is funded by Advantest, one of the world leaders in automatic test equipment. In this paper, we describe the overall philosophy of the Graduate School and the specific scientific questions targeted by its ten projects.

In One-Class Classification (OCC), data affiliated with only one given class are accessible during training, while the trained algorithm must be capable of distinguishing the given class from all other unknown classes during test. OCC can be considered as a general case for many anomaly detection and novelty discovery problems and is more challenging than conventional binary and multi-class classification due to the absence of unknown classes. In literature, one of the most popular techniques towards OCC is autoencoder because autoencoders can capture the intrinsic structure of training data and are expected to have smaller reconstruction errors for the given class than those of unknown classes. As a result, during test, data from the known and unknown classes can be discriminated by thresholds. Despite the wide application of autoencoders in OCC, we have recently discovered that autoencoders can easily generalize to unknown classes, although they are trained on one given class only. The unexpected behavior reduces the overall OCC performance and leads to performance degradation during training. This paper proposes a novel solution to regularize the generalization ability of autoencoders and reduce performance degradation in OCC by introducing a feature weighting block in the latent space of autoencoders. Intensive experiments show that our method enables a training without performance degradation and significantly improves the OCC ability in comparison with contemporary state-of-the-art approaches.

With the dramatically increasing requirements on semiconductor products, improving the yield is one of the major tasks for semiconductor manufacturers. To minimize losses, automatic and efficient wafer testing tools are required to quickly notify the engineers of potential problems. One such technique is wafer map defect pattern classification, which has inspired and motivated extensive research over the last decades. Many popular studies often design novel wafer map defect identification algorithms based on manual feature extraction, statistical learning and deep neural networks, having achieved significant advancement and success. However, these methods often face challenges of training large-scale networks and few of them have noticed the full usage of the information within each wafer map. Based on the concerns above, this paper proposes a multi-task learning framework based on neural networks that fuses the information of the entire wafer map as well as the state of each individual die to enhance the defect pattern classification capability. Extensive experiments on a public real-world dataset have been conducted to justify the effectiveness of our method. Specifically, our method achieved an classification accuracy of 96.3%, which was better or comparable to other state-of-the-art approaches that required notably larger network sizes and heavy data augmentation.

Both process variations and defects in cells can lead to additional small delays within specifications, while the latter must be identified because they may degrade soon into critical faults for circuits and result in threat to reliability. Therefore, discriminating small delays due to defects from those due to variations has drawn increasingly attention in the test community over the recent years. One promising research direction is to formulate the task into binary classification by using delays under a few supply voltages as the only variables for data-driven algorithms. However, many approaches often assume the availability of delay information from both defective and non-defective cells or combinational circuits. This assumption implies a large time consumption for simulation, and considerable costs for manufactured defective devices. To address the issues above, this paper proposes to use unsupervised deep learning techniques to train an recognizer on non-defective data only but still can identify defects during inference. Specifically, we have proposed to use a weighted autoencoder with a novel data augmentation technique to solve this problem. Experiments show that our approach has comparable detection capability as supervised learning schemes, while our method does not require any defective data. Moreover, in practice, our approach is more robust to unbalanced datasets and to non-target defects than other methods.

Feature selection is generally used as one of the most important preprocessing techniques in machine learning, as it helps to reduce the dimensionality of data and assists researchers and practitioners in understanding data. Thereby, by utilizing feature selection, better performance and reduced computational consumption, memory complexity and even data amount can be expected. Although there exist approaches leveraging the power of deep neural networks to carry out feature selection, many of them often suffer from sensitive hyperparameters. This paper proposes a feature mask module (FM-module) for feature selection based on a novel batch-wise attenuation and feature mask normalization. The proposed method is almost free from hyperparameters and can be easily integrated into common neural networks as an embedded feature selection method. Experiments on popular image, text and speech datasets have shown that our approach is easy to use and has superior performance in comparison with other state-of-the-art deep-learning-based feature selection methods.

Conventional unsupervised image segmentation methods use color and geometric information and apply clustering algorithms over pixels. They preserve object boundaries well but often suffer from over-segmentation due to noise and artifacts in the images. In this paper, we contribute on a preprocessing step for image smoothing, which alleviates the burden of conventional unsupervised image segmentation and enhance their performance. Our approach relies on a convolutional autoencoder (CAE) with the total variation loss (TVL) for unsupervised learning. We show that, after our CAE-TVL preprocessing step, the over-segmentation effect is significantly reduced using the same unsupervised image segmentation methods. We evaluate our approach using the BSDS500 image segmentation benchmark dataset and show the performance enhancement introduced by our approach in terms of both increased segmentation accuracy and reduced computation time. We examine the robustness of the trained CAE and show that it is directly applicable to other natural scene images.