Machine Learning Interpretability Professors and Supervisors in Germany | ApplySharif

فیلترهای فعال:

جست‌وجوی استاد و پژوهشگر

استاد راهنما، استاد دانشگاه یا پژوهشگر مناسب برای مسیر پژوهشی‌تان را پیدا کنید و با او ارتباط بگیرید.

نمایش ۷۳۶-۷۵۰ از ۱٬۰۷۰ استاد راهنما

اطلاعات این پروفایل‌ها از صفحات عمومی دانشگاه‌ها جمع‌آوری شده و ممکن است به‌روز نباشد.

Hanna Drimallaمشاهده پروفایل

استاد

Bielefeld UniversityGermany

Prof. Dr. Hanna Drimalla is a Professor at the University of Bielefeld's Faculty of Engineering, leading the Human-Centered Artificial Intelligence Group within CITEC (Center for Cognitive Interaction Technology). She holds additional roles including membership in the Faculty Conference of University Professors, the Habilitation Committee, and the Collaborative Research Center TRR 318 'Constructing Explainability'. Education: She earned a PhD in Psychology (2019) from Humboldt University Berlin with research on autism and machine learning, a Master's in Computational Science (2017, University of Potsdam), and earlier degrees in Psychology from Ruhr University Bochum (2013). Research focuses on automatic affect recognition using multimodal data, computer-based stress measurement through physiological and behavioral signals, and social embedding analysis via online interaction patterns. Current projects include developing explainable AI for affective computing, privacy-preserving data donation platforms (Dona), and stress detection algorithms validated in natural environments. Teaching responsibilities include courses on artificial intelligence, media computing, and applied interaction technology. She coordinates modules like 39-Inf-17-Ba_A (Bachelor's thesis) and 39-M-Inf-INT-app (Applied Interaction Technology). Labs/Teams: Active in CITEC and the Human-Centered AI group, collaborating on the TRR 318 'Constructing Explainability' project (Subproject A06) and the Joint Research Center on Cooperative and Cognition-enabled AI.

پروفایل رسمی دانشگاه

Katja Langenbucherمشاهده پروفایل

استاد

Goethe-University FrankfurtGermany

Professor Katja Langenbucher is a distinguished academic specializing in corporate and capital markets law at Goethe University Frankfurt am Main. She holds the Chair of Civil Law, Commercial Law and Banking Law at the House of Finance and serves as an affiliated professor at SciencesPo, Paris. Additionally, she is a permanent visiting professor at Fordham Law School in New York City and coordinates the LawLab – Fintech & AI as Bridge Professor at the Leibniz Institute for Financial Research SAFE. Her academic affiliations span multiple prestigious institutions: Goethe University Frankfurt am Main (Primary appointment) SciencesPo, Paris (Affiliated professor) Fordham Law School, NYC (Permanent visiting professor) Leibniz Institute for Financial Research SAFE (SAFE Fellow) Ecole de Droit, SciencesPo, Paris (Affiliated professor) Professor Langenbucher's research focuses on corporate and capital markets law, with particular emphasis on banking corporate governance, FinTech, artificial intelligence, and algorithm-based credit scoring. Her work bridges legal theory with practical applications in financial regulation and technological innovation. Her publications reveal a strong focus on the intersection of law, finance, and technology, with recent work concentrating on AI applications in credit scoring, digital asset regulation, and corporate governance frameworks. She has developed expertise in legal transplants - the process by which legal concepts move across jurisdictions - and applies this perspective to analyze corporate and capital markets law. Professor Langenbucher has received notable recognition for her work: Alfred Grosser Chaire at SciencesPo, Paris (2008) Edward Mulligan Distinguished Professorship at Fordham Law School (2018) Bok Visiting International Professorship at PennLaw, Philadelphia (2022) She maintains significant professional engagement through various appointments: Member of the Administrative Board of BaFin (German Federal Financial Supervisory Authority) Member of the Advisory Board of Alte Leipziger/Halle'sche Nationale Group Member of the Administrative Board of the Fondation Nationale des Sciences Politique Member of the Center for AI and Digital Policy-Global Academic Network Former Supervisory Board Member of Postbank Former Member of the EU Commission's High Level Forum on Capital Markets Union Board member of the Association of Banking Law Board member and funding committee member of the Economics and Law Working Group of the Donors' Association for the Promotion of Sciences and Humanities in Germany Former expert reviewer at the Alexander von Humboldt Foundation Professor Langenbucher's work demonstrates a commitment to connecting academic research with practical regulatory challenges, particularly in the rapidly evolving areas of financial technology and artificial intelligence applications in finance.

پروفایل رسمی دانشگاه

Arun Nagarajahمشاهده پروفایل

استاد

University of Duisburg-EssenGermany

Prof. Dr.-Ing. Arun Nagarajah is Chair of Product Development Processes and Data Management at the University of Duisburg-Essen's Faculty of Engineering (IPE). He holds a doctorate from RWTH Aachen University (2010) and previously worked in the automotive industry and supply sector, leading product data management and digitalization initiatives. His research focuses on digitalization in engineering processes, product lifecycle management, machine learning applications, and knowledge graph-based standards interpretation. He leads projects like the UMEK initiative on multidisciplinary engineering processes in power plant construction and has contributed to over 50 peer-reviewed publications since 2011. Education: Mechanical Engineering & Quality Management, University of Wuppertal Doctorate in Mechanical Engineering, RWTH Aachen University (2010) Research Interests: Digital twins, sustainable product design, machine learning in engineering, requirements mining from standards, and modular product development. His work bridges theoretical frameworks (e.g., knowledge graphs) with practical applications in automotive, manufacturing, and energy sectors. Grants & Projects: Led the BMWI-funded UMEK project (2015-2018), focusing on multidisciplinary engineering processes in power plants. Collaborates on initiatives like SMART Standards for machine-actionable engineering guidelines. Labs/Teams: Heads the Product Engineering Processes (PEP) research group, specializing in data-driven product development methodologies and digital transformation in industry.

پروفایل رسمی دانشگاه

Markus Ankenbrandمشاهده پروفایل

پژوهشگر

Julius-Maximilians-Universität WürzburgGermany

Dr. Markus Ankenbrand is a Group Leader in BioMedical Data Science at the Center for Computational and Theoretical Biology (CCTB) at Julius-Maximilians-Universität Würzburg. He holds a PhD in Biology and Informatics from the same university, completed at the Graduate School of Life Sciences. His research focuses on developing algorithms and tools for biomedical data analysis, with a current emphasis on multi-modal methods and machine learning model interpretability. Positions: 2020–present: Group Leader, BioMedical Data Science, CCTB 2019–2020: Group Leader, Computational Cardiology, Universitätsklinikum Würzburg 2018–2019: PostDoc, MIT, Boston Research Interests: His work spans bioinformatics, computational biology, medical imaging analysis, and machine learning applications in healthcare. Key projects include deep learning models for cardiac MRI segmentation and integrative genomics in ocean ecosystems. Publications: Over 25 peer-reviewed articles since 2013, with recent contributions on prostate cancer detection via PET/CT, influenza RNA visualization, and cardiac function modeling in large animal studies. Education: Bachelor of Biology (2009–2012), University of Würzburg Master of Biology (2012–2014), University of Würzburg Bachelor of Informatics (2011–2015), University of Würzburg PhD (2014–2017), Graduate School of Life Sciences, University of Würzburg Bachelor of Computational Mathematics (2020–2023), University of Würzburg Labs/Teams: Leads the BioMedical Data Science group at CCTB, collaborating with institutions worldwide on projects like myocardial pathology segmentation benchmarks (MyoPS) and ecological trait data standards.

پروفایل رسمی دانشگاه

Daniel Ruffinelliمشاهده پروفایل

پژوهشگر

University of MannheimGermany

Dr. Daniel Ruffinelli is a Researcher at the Data and Web Science Group (DWS) at the University of Mannheim, affiliated with the School of Business Informatics and Mathematics. His research focuses on Natural Language Processing (NLP), particularly using interpretability methods to study how Large Language Models (LLMs) represent natural language internally. He also works on representation learning and machine learning, with prior PhD research on knowledge graph embeddings under Prof. Rainer Gemulla. Teaching responsibilities include advanced courses on Text Analytics, Information Retrieval, and Deep Learning, alongside tutorials for Machine Learning, Data Mining, and Large Scale Data Management courses. He has advised numerous MSc and BSc theses since 2018. Key research highlights include contributions to knowledge graph embeddings (e.g., pre-training strategies and evaluation methodologies) and the development of KGxBoard, an explainable leaderboard system for knowledge graph completion models. Notable recognition includes the Outstanding Paper Award at RepL4NLP@ACL 2019. His work bridges interpretability techniques with foundational AI research, emphasizing reproducibility through tools like LibKGE, a knowledge graph embedding library.

پروفایل رسمی دانشگاه

Sebastian Padóمشاهده پروفایل

استاد

University of StuttgartGermany

Sebastian Padó is a Professor and Chair of Theoretical Computational Linguistics at the Institute for Natural Language Processing (IMS) of the University of Stuttgart. He serves as Study Dean for Natural Language Processing and Computational Linguistics within Faculty 5 (Computer Science, Electrical Engineering, and Information Technology). His research focuses on computational semantics, leveraging data-driven approaches to model meaning in language, with applications in political discourse analysis, emotion analysis, and cross-lingual NLP. He leads projects such as CEAT (Emotion Analysis via Appraisal Theory), FIBISS (Fact-Checking in Biomedical Information), and MARDY (Argument Dynamics Modeling). Collaborations include institutions like the University of Tübingen, University of Pisa, and University of Zagreb. His work bridges computational linguistics with social sciences, addressing topics like political positioning, media bias detection, and historical text analysis. Padó oversees the Department of Theoretical Computational Linguistics, managing research and teaching activities. His group's contributions span semantic modeling, neural network interpretability, and interdisciplinary applications in digital humanities. He actively publishes in top venues, with recent work on multilingual models, political text analysis, and transformer architectures. Key achievements include developing methods for emotion analysis in literature and news, creating datasets on political debates (e.g., DEbateNet-mig15), and advancing frame semantics through distributional models. His lab also explores explainable AI techniques for NLP systems, emphasizing transparency and ethical considerations.

پروفایل رسمی دانشگاه

Dmitry Ustalovمشاهده پروفایل

پژوهشگر

University of MannheimGermany

Dmitry Ustalov is a Post-Doctoral Researcher at the University of Mannheim's Data and Web Science Group, specializing in Natural Language Processing and Computational Semantics. He joined the group in 2017 and defended his Kandidat Nauk (PhD) thesis in February 2018. His research focuses on word sense induction/disambiguation, thesaurus construction, and leveraging crowdsourcing for linguistic resource development. He contributes to projects like Watset (graph clustering), Hyperstar (hypernymy prediction), and Mechanical Tsar (crowdsourcing engine). He coordinates the RUSSE workshop on Russian semantic evaluation and teaches courses on Text Analytics and Web Mining. His work involves collaborations with institutions like the Russian Presidential Academy of National Economy and Public Administration (RANEPA) and the University of Bremen. Funded by the DFG-funded JOIN-T project, his research emphasizes multilingual systems, semantic evaluation, and interpretable NLP methods. Key technical contributions include algorithms for synset induction, hypernym detection, and semantic frame analysis. His work bridges theoretical NLP advancements with practical applications in lexical resource creation and crowdsourced data annotation.

پروفایل رسمی دانشگاه

Johannes Betzمشاهده پروفایل

استاد

Technical University of MunichGermany

Prof. Dr. Johannes Betz is a Rudolf Mößbauer Professor at the Technical University of Munich (TUM), leading the Chair of Autonomous Vehicle Systems within the Department of Mobility Systems. His research focuses on software development for autonomous vehicles, emphasizing algorithms for environmental perception, path planning, and control to enable safe, efficient autonomous operation. He holds a B.Eng. and M.Sc. in Automotive Engineering from Coburg University and the University of Bayreuth, followed by a Ph.D. in Engineering from TUM (2019). Notable achievements include founding the TUM Autonomous Motorsport Team, which won the Indy Autonomous Challenge ($1M prize), and extensive postdoc work at TUM and the University of Pennsylvania. Education: B.Eng., Automotive Engineering, Coburg University of Applied Sciences (2013) M.Sc., Automotive Engineering, University of Bayreuth (2013) Ph.D. in Engineering, Technical University of Munich (2019) Research Interests: Autonomous vehicle software architecture Real-time trajectory and behavior planning Adaptive control for high-performance systems Simulation and validation frameworks Ethics of autonomous decision-making Awards: IEEE ITS Young Professional Travel Fellowship (2022) 1st Place, Indy Autonomous Challenge (2021) New Generation Star Project Award (2024) Outstanding Reviewer Award (2024) Labs & Teams: TUM Autonomous Motorsport Team (race competition leader) AVS Lab (Autonomous Vehicle Systems)

پروفایل رسمی دانشگاه

Simon Hegelichمشاهده پروفایل

استاد

Technical University of MunichGermany

Prof. Simon Hegelich is a Professor of Political Data Science at the TUM School of Social Sciences and Technology, Technische Universität München (TUM). He combines political science with computer science to create Political Data Science, focusing on digitalization's political implications and applying machine learning, data mining, and simulations. His research explores topics like social bot detection, algorithmic bias, and the impact of social media on political communication. Prof. Hegelich holds a PhD and habilitation from the University of Münster. Before joining TUM, he served as Managing Director of the FoKoS research center (2011–2016). His work spans ethical AI applications, misinformation mitigation, and digital policy frameworks. Notable projects include the Social Media Forensics initiative analyzing political bots and the 2017 German Federal Elections social media report. His publications address AI-generated content ethics, pandemic discourse analysis, and algorithmic transparency. Key themes include filter bubbles, microtargeting, and the societal consequences of big data. Recent work critiques AI limitations while advocating for responsible tech governance.

پروفایل رسمی دانشگاه

Frank Petzoldمشاهده پروفایل

استاد

Technical University of MunichGermany

Prof. Frank Petzold is a Full Professor at the Chair of Architectural Informatics within the Department of Architecture at the Technical University of Munich (TUM). His academic career includes roles as Vice Dean of the Department of Architecture (2010–2012) and Dean of the Faculty of Architecture at Bauhaus-University Weimar (2008–2009). He holds a Doctorate in Computer Science from Bauhaus-University Weimar (2001) and has been a core member of the Munich Data Science Institute (MDSI) since 2021. His research focuses on digital methods in architectural design, BIM integration, AI-driven generative design, and sustainable urban planning. Key affiliations include the Leonhard Obermeyer Center for Digital Methods (co-founder, 2014) and leadership roles in DARL (Deans' Association for Architecture, 2015–present). Research interests span computational design tools, digital twin technologies, and AI applications in construction. Notable contributions include the TUM2TWIN benchmark dataset and frameworks for automated design decision support. He serves on editorial boards for journals like the International Journal of Architectural Computing and chairs Bavaria’s 'Digital Construction and Planning' platform. His work bridges academic research with industry applications, emphasizing interdisciplinary collaboration and digital innovation in built environment disciplines. Education: Doctorate in Computer Science, Bauhaus-University Weimar (2001) Affiliations: Munich Data Science Institute, TUM Georg Nemetschek Institute, German Association of Computing in Civil Engineering Committees: DARL, Task Group AKIM (Construction Industry), Bavarian Digitalization Center (Z.DB) Publications emphasize BIM interoperability, generative design systems, and urban sustainability. Current projects explore AI for building lifecycle assessments, digital twin applications, and crowd-safety simulations in early design stages.

پروفایل رسمی دانشگاه

Peter Schüfflerمشاهده پروفایل

استاد

Technical University of MunichGermany

Prof. Peter Schüffler is a Professor of Computational Pathology at the Technical University of Munich (TUM), holding joint appointments in the TUM School of Medicine and Health and the TUM School of Computation, Information and Technology. His research focuses on applying machine learning to digital pathology, including cancer detection, prognostic marker identification, and AI-driven diagnostic tools. He earned an MSc in Bioinformatics from Saarland University and a PhD in Machine Learning for Medical Image Analysis from ETH Zurich. As a postdoc and senior ML scientist at Memorial Sloan Kettering Cancer Center, he co-founded Paige, a digital pathology company. He joined TUM in 2021. Education: MSc in Bioinformatics and Computational Biology, Saarland University and Max Planck Institute (MPI Saarbrücken) PhD in Machine Learning for Medical Image Analysis, ETH Zurich (2015) Research Interests: His work spans machine learning applications in pathology, including AI-driven diagnosis, automated quality assurance, and ergonomic systems for pathologists. Key areas include: Cancer detection and segmentation in pathology images Prognostic marker discovery for treatment success Efficient visualization of digital histopathology slides Integration of AI into clinical and educational workflows Awards: Best Paper Award (2014): Computer Aided Crohn's Disease Severity Assessment in MRI Outstanding Paper Award (2013): Crohn's Disease Severity Assessment Model Advising & Grants: No specific student advisees or grants are listed in the provided text. Labs/Teams: Co-founder of Paige, a leader in AI-driven digital pathology systems. Active in TUM's computational pathology research groups.

پروفایل رسمی دانشگاه

Bernhard Kainzمشاهده پروفایل

استاد

University of Erlangen–NurembergGermany

Prof. Bernhard Kainz is a Professor at Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU), leading the Department Artificial Intelligence in Biomedical Engineering (AIBE). He holds a W3-Professorship for Image Data Exploration and Analysis. His research focuses on developing intelligent algorithms for healthcare applications, particularly in medical imaging and real-time diagnostics. Key interests include self-driving medical image acquisition systems, normative learning through population data integration, and interpretable AI decision-making in clinical settings. Teaching: Real-time computing, Machine Learning, Image Analysis, Computer Graphics, and Visualization His work bridges technical innovation with clinical needs, addressing challenges like democratizing rare medical expertise through AI and enhancing patient care through explainable AI systems. Active in research collaborations, he contributes to FAU's interdisciplinary environment, leveraging partnerships with institutions like Fraunhofer and Helmholtz.

پروفایل رسمی دانشگاه

Dario Zancaمشاهده پروفایل

پژوهشگر

University of Erlangen–NurembergGermany

Dario Zanca is a Postdoctoral Researcher in the Department of Artificial Intelligence in Biomedical Engineering (AIBE) at Friedrich-Alexander-Universität Erlangen-Nürnberg. He is affiliated with the Machine Learning and Data Analytics (MaD) Lab and focuses on visual perception, eye movement analysis, and machine learning applications. His work bridges computational models of human attention with neural network behavior, contributing datasets like FixaTons and CapMIT1003. Research areas include: Biologically-inspired visual attention models Eye tracking and gaze analysis in clinical and computational contexts Deep learning interpretability and explainable AI Time series analysis and predictive process monitoring Key contributions include tools like the SaccadeAnalysisMatlabApp for gaze data processing and participation in initiatives like the PolarBearVidID dataset for wildlife behavior analysis. His interdisciplinary projects span healthcare, robotics, and environmental science, emphasizing real-world applications of AI.

پروفایل رسمی دانشگاه

Barbara Hammerمشاهده پروفایل

استاد

Bielefeld UniversityGermany

Prof. Dr. Barbara Hammer is a full professor of Machine Learning at Bielefeld University, Faculty of Engineering, and leads the Machine Learning Group at the Center for Cognitive Interaction Technology (CITEC). She is actively involved in multiple interdisciplinary research centers including the Bielefeld Center for Data Science (BiCDaS), the Research Institute for Cognition and Robotics, and the Institute for Bioinformatics Infrastructure (BIBI). She holds leadership roles in major research initiatives such as the TRR 318 'Constructing Explainability', the graduate school Data-NinJA on Trustworthy AI, and the research network SAIL on sustainable AI systems. Her research focuses on intelligent data analysis , explainable and trustworthy AI , and machine learning in dynamic environments . She investigates foundational algorithms for learning from complex, non-Euclidean, and evolving data streams, with applications in urban infrastructure (especially water systems), life sciences, and socio-technical systems. Her work bridges algorithmic innovation with societal impact, particularly in fairness, ethics, and human-AI interaction. The recent publications highlight a strong trend towards explainability in dynamic environments , concept drift detection and explanation , fairness in streaming data , and real-world applications in critical infrastructure . Her team develops both theoretical frameworks and practical tools, such as EPyT-Flow for water network simulation, and contributes to high-impact AI challenges in health, environment, and industry. ERC Synergy Grant – Smart Water Futures LAMARR Fellow She advises several PhD and Master’s students and leads numerous funded projects from the European Union, DFG, and national agencies. Her leadership extends to editorial roles, including on the IEEE TPAMI editorial board. She is also deeply involved in academic governance, serving on examination boards, habilitation committees, and interdisciplinary research centers, reflecting her central role in shaping AI research and education at Bielefeld and beyond.

پروفایل رسمی دانشگاه

Holger Hermannsمشاهده پروفایل

استاد

Saarland UniversityGermany

Holger Hermanns is a Full Professor of Computer Science at Saarland University, Germany, where he leads the Dependable Systems and Software group. He is co-spokesperson of the Center for Perspicuous Computing (SFB/TRR 248) and has been a scientific director at Schloss Dagstuhl – Leibniz Center for Informatics since 2025. He is a member of Academia Europaea and holds an ERC Advanced Grant (POWVER) and a Proof-of-Concept Grant (LEOpowver) . His leadership roles include former Dean of the Faculty of Mathematics and Computer Science and active service in major academic organizations such as the ETAPS Association (Vice President) and Friends of Dagstuhl (President, 2013–2023). Education: Researcher and academic positions at Universität Erlangen-Nürnberg (1993–1998), Universiteit Twente (1998–2006), and INRIA Grenoble Rhône-Alpes (2007–2010). His research focuses on modeling and verification of concurrent systems , stochastic behavioral modeling , energy informatics , and proactive algorithmic accountability . He is a leading figure in probabilistic model checking, formal methods for cyber-physical systems, and software dependability. His work bridges theory and practical applications in satellite systems, AI safety, and environmental monitoring. The recent publications reflect a strong trend toward AI accountability , software doping detection , formal verification of machine learning systems , and dependable satellite network design . His team develops tools like RTLola and Momba, integrating formal methods into real-world systems. There is a growing emphasis on interdisciplinary work, particularly in human oversight of AI and ethical algorithmic design. Scientific Awards and Recognition: ERC Advanced Grant POWVER ERC Proof-of-Concept Grant LEOpowver Member, Academia Europaea (2013) Dutch Vernieuwingsimpuls (2001) Preis des Fakultätentages Informatik (2013) ERC Advanced Investigators Grant (2016) Otto Mønsted-Guest Professorship (2013) Hermanns has advised numerous students and researchers, though specific names are not listed. He leads major research grants, including ERC projects and collaborative efforts within SFB/TRR 248. His leadership extends to program committees of top conferences such as CAV, CONCUR, TACAS, and QEST, and he has chaired LICS and ICALP. He is affiliated with the Dependable Systems and Software lab at Saarland Informatics Campus and contributes to the Schloss Dagstuhl ecosystem as scientific director and former president of its support association. His recent work is increasingly centered on the AI Act , algorithmic transparency, and the formal foundations of trustworthy AI.

پروفایل رسمی دانشگاه