Publications

Hannah Selder, Florian Fischer, Per Ola Kristensson, und Arthur Fleig. What Makes a Model Breathe? Understanding Reinforcement Learning Reward Function Design in Biomechanical User Simulation. Proceedings of the Extended Abstracts of the CHI Conference on Human Factors in Computing Systems, 1–10, ACM, April 2025. [PUMA: Biomechanical Design Function Reinforcement Reward User_Simulation xack learning] URL

Saeed Karami, Farid Saberi-Movahed, Prayag Tiwari, Pekka Marttinen, und Sahar Vahdati. Unsupervised feature selection based on variance–covariance subspace distance. Neural Networks, (166):188-203, 2023. [PUMA: Feature Regularization Subspace distance learning selection xack] URL

Akshay Akshay, Masoud Abedi, Navid Shekarchizadeh, Fiona C Burkhard, Mitali Katoch, Alex Bigger-Allen, Rosalyn M Adam, Katia Monastyrskaya, und Ali Hashemi Gheinani. MLcps: machine learning cumulative performance score for classification problems. GigaScience, (12):giad108, Dezember 2023. [PUMA: MLcps cumulative learning machine performance yaff xack] URL

Niklas Deckers, und Martin Potthast. WARC-DL: Scalable Web Archive Processing for Deep Learning. 2022. [PUMA: Archive Processing Scalable WARC-DL xack learning deep web] URL

Dianzhao Li, und Ostap Okhrin. A platform-agnostic deep reinforcement learning framework for effective Sim2Real transfer towards autonomous driving. Commun Eng, (3)1:147, Springer Science and Business Media LLC, Oktober 2024. [PUMA: Sim2Real autonomous deep driving framework learning platform-agnostic reinforcement xack]

Sunna Torge, Waldemar Hahn, Lalith Manjunath, und René Jäkel. Named Entity Recognition for Specific Domains - Take Advantage of Transfer Learning. International Journal of Information Science and Technology, Vol 6 No 3 (2022), International Journal of Information Science and Technology, 2022. [PUMA: Advantage Domains Entity Recognition Specific Transfer xack learning] URL

Martin Bogdan. Learning algorithms for spiking neural networks: should one use learning algorithms from ANN/DL or neurological plausible learning? - A thought-provoking impulse. XLIII Jornadas de Automática: libro de actas: 7, 8 y 9 de septiembre de 2022, Logroño (La Rioja), 201--207, Servizo de Publicacións da UDC, September 2022. [PUMA: algorithms learning networks neural neurological plausible spiking xack]

Lena Jurkschat, Gregor Wiedemann, Maximilian Heinrich, Mattes Ruckdeschel, und Sunna Torge. Few-Shot Learning for Argument Aspects of the Nuclear Energy Debate. In Nicoletta Calzolari, Frederic Bechet, Philippe Blache, Khalid Choukri, Christopher Cieri, Thierry Declerck, Sara Goggi, Hitoshi Isahara, Bente Maegaard, Joseph Mariani, Helene Mazo, Jan Odijk, und Stelios Piperidis (Hrsg.), 2022 Language Resources and Evaluation Conference, LREC 2022, 663--672, European Language Resources Association (ELRA), 2022. [PUMA: FIS_scads argument aspect-based aspects, classification discourse, energy few-shot frames, mining, nuclear text xack learning]

Lucas Lange, Maurice-Maximilian Heykeroth, und Erhard Rahm. Assessing the Impact of Image Dataset Features on Privacy-Preserving Machine Learning. arXiv preprint arXiv:2409.01329, arXiv, September 2024. [PUMA: (cs.CR) (cs.CV) (cs.LG) Computer Cryptography FOS Pattern Recognition Security Vision area_bigdata area_responsibleai ep information learning machine sciences xack yaff]

Vincent D. Friedrich, Peter Pennitz, Emanuel Wyler, Julia M. Adler, Dylan Postmus, Kristina Müller, Luiz Gustavo Teixeira Alves, Julia Prigann, Fabian Pott, Daria Vladimirova, Thomas Hoefler, Cengiz Goekeri, Markus Landthaler, Christine Goffinet, Antoine-Emmanuel Saliba, Markus Scholz, Martin Witzenrath, Jakob Trimpert, Holger Kirsten, und Geraldine Nouailles. Neural network-assisted humanisation of COVID-19 hamster transcriptomic data reveals matching severity states in human disease. eBioMedicine, (108):105312, 2024. [PUMA: COVID-19, Cross-species Disease Hamster RNA-seq, Single-cell analysis, learning matching, model, state topic_mathfoundation yaff xack deep] URL

Suryanarayana Maddu, Bevan L. Cheeseman, Ivo F. Sbalzarini, und Christian L. Müller. Stability selection enables robust learning of partial differential equations from limited noisy data. arXiv, 2019. [PUMA: (cs.LG) (math.NA) (physics.data-an) Analysis Computer FOS Mathematics Numerical Physical Probability Statistics data information learning machine sciences xack] URL

Veronika Scholz, Peter Winkler, Andreas Hornig, Maik Gude, und Angelos Filippatos. Structural damage identification of composite rotors based on fully connected neural networks and convolutional neural networks. Sensors (Basel), (21)6:2005, MDPI AG, März 2021. [PUMA: (SHM) composite composites; connected convolutional dense fully health machine monitoring neural rotors; structural xack learning networks]

Akshay Akshay, Mitali Katoch, Navid Shekarchizadeh, Masoud Abedi, Ankush Sharma, Fiona C Burkhard, Rosalyn M Adam, Katia Monastyrskaya, und Ali Hashemi Gheinani. Machine Learning Made Easy (MLme): a comprehensive toolkit for machine learning-driven data analysis. Gigascience, (13)Januar 2024. [PUMA: AutoML analysis classification data learning machine problems topic_federatedlearn visualization xack yaff]

Akshay Akshay, Masoud Abedi, Navid Shekarchizadeh, Fiona C Burkhard, Mitali Katoch, Alex Bigger-Allen, Rosalyn M Adam, Katia Monastyrskaya, und Ali Hashemi Gheinani. MLcps: machine learning cumulative performance score for classification problems. Gigascience, (12)Dezember 2022. [PUMA: Python classification evaluation learning machine model package problems score topic_federatedlearn unified xack yaff]

Akshay Akshay, Mitali Katoch, Masoud Abedi, Navid Shekarchizadeh, Mustafa Besic, Fiona C Burkhard, Alex Bigger-Allen, Rosalyn M Adam, Katia Monastyrskaya, und Ali Hashemi Gheinani. SpheroScan: a user-friendly deep learning tool for spheroid image analysis. Gigascience, (12)Oxford University Press (OUP), Dezember 2022. [PUMA: 3D Image Mask R-CNN analysis deep high-throughput image learning screening segmentation spheroids topic_federatedlearn xack yaff]

Alina Mailach, und Norbert Siegmund. Socio-Technical Anti-Patterns in Building ML-Enabled Software: Insights from Leaders on the Forefront. 2023 IEEE/ACM 45th International Conference on Software Engineering (ICSE), 690--702, IEEE, Mai 2023. [PUMA: Biological Economics Manuals Pipelines Production Software learning modeling system systems topic_software xack yaff machine]