Hauptnavigation

ALLGEMEINES

FORSCHUNG

LEHRE

MITARBEITER

MG_3091Q_small.jpg Email: sebastian.buschjaeger At Symbol tu-dortmund.de
Telefon: 0231/755-8499
Telefax: 0231/755-5105
Raumnummer: JvF25 R118

Zur Person

Sebastian Buschjäger hat Kerninformatik mit Nebenfach Elektrotechnik an der Universität Dortmund studiert und erhielt dort 2016 den Masterabschluss. Seit dem ist er Wissenschaftlicher Mitarbeiter am Lehrstuhl für Künstliche Intelligenz und Mitglied im Sonderforschungsbereich 876, Teilprojekt A1.Er forscht an

  • Machine Learning: Ensemble learning, Model application, Gaussian processes, submodular functions
  • Computerarchitecture: Architecture-dependent optimizations and code generation, custom architectures/FPGAs, embedded devices

Social Media

Github | Twitter | Google Scholar

Lehre

Präsentationen

  • Shrub Ensembles for Online Classification slides, poster, video
  • On-Site Gamma-Hadron Separation with Deep Learning on FPGAs at ECMLPKDD 2020 slides
  • FastInference – Applying Large Models on Small Devices at SFB 876 Summerschool 2020 slides, video
  • Gaussian Model Trees for Traffic Imputation at ICPRAM 2019 slides
  • Realization of Random Forest for Real-Time Evaluation through Tree Framing at ICDM 2018 poster,slides
  • Deep Learning for small devices and FPGAs at 4th International Summerschool for Big Data and Machine Learning 2018: Slides are available here
  • Decision Tree and Random Forest Implementations for Fast Filtering of Sensor Data (ECRTS 2018 Journal2Conference) poster,slides
  • Data Summarization on Embedded Systems at IoT-Streaming Workshop (ECML 2017) slides
  • Introduction to Deep Learning at SFB 876 Summerschool 2017: Slides are available here
  • Deep Learning on FPGAs at SFB 876 Summerschool 2017:Slides are available here

Publikationen

Chen/etal/2022a Kuan-Hsun Chen and Chia-Hui Hsu and Christian Hakert and Sebastian Buschjäger and Chao-Lin Lee and Jenq-Kuen Lee and Katharina Morik and Jian-Jia Chen. Efficient Realization of Decision Trees for Real-Time Inference. In ACM Transactions on Embedded Computing Systems, 2022.
Yayla/etal/2022a Mikail Yayla and Simon Thomann and Sebastian Buschjäger and Katharina Morik and Jian-Jia Chen and Hussam Amrouch. Reliable Binarized Neural Networks on Unreliable Beyond von-Neumann Architecture. In IEEE Transactions on Circuits and Systems I, 2022. Arrow Symbol
Buschjaeger/etal/2021d Buschjäger, Sebastian and Hess, Sibylle and Morik, Katharina J.. Shrub Ensembles for Online Classification. In Proceedings of the Thirty-Sixth AAAI Conference on Artificial Intelligence (AAAI-22), Vol. 36, No. 6, Seiten 6123-6131, AAAI Press, 2022. Arrow Symbol
Buschjaeger/etal/2021c Sebastian Buschjäger and Jian-Jia Chen and Kuan-Hsun Chen and Mario Günzel and Katharina Morik and Rodion Novkin and Lukas Pfahler and Mikail Yayla. Bit Error Tolerance Metrics for Binarized Neural Networks. 2021. Arrow Symbol
Yayla/etal/2021a Yayla, Mikail and Buschjäger, Sebastian and Gupta, Aniket and Chen, Jian-Jia and Henkel, Jorg and Morik, Katharina and Chen, Kuan-Hsun and Amrouch, Hussam. FeFET-based Binarized Neural Networks Under Temperature-dependent Bit Errors. In IEEE Transactions on Computers, 2021. Arrow Symbol
Honysz/etal/2021a Honysz, Philipp-Jan and Buschjäger, Sebastian and Morik, Katharina. GPU-Accelerated Optimizer-Aware Evaluation of Submodular Exemplar Clustering. 2021. Arrow Symbol
Buschjaeger/Morik/2021c Sebastian Buschjäger and Katharina Morik. Improving the Accuracy-Memory Trade-Off of Random Forests Via Leaf-Refinement. 2021. Arrow Symbol
Buschjaeger/etal/2021a Buschjäger, Sebastian and Chen, Jian-Jia and Chen, Kuan-Hsun and Günzel, Mario and Hakert, Christian and Morik, Katharina and Novkin, Rodion and Pfahler, Lukas and Yayla, Mikail. Margin-Maximization in Binarized Neural Networks for Optimizing Bit Error Tolerance. In Proceedings of DATE 2021, 2021. Arrow Symbol
Honysz/etal/2021b Honysz, Philipp-Jan and Schulze-Struchtrup, Alexander and Buschjäger, Sebastian and Morik, Katharina. Providing Meaningful Data Summarizations Using Exemplar-based Clustering in Industry 4.0. 2021. Arrow Symbol
Buschjaeger/Morik/2021a Sebastian Buschjäger and Katharina Morik. There is no Double-Descent in Random Forests. 2021. Arrow Symbol
Buschjaeger/etal/2021b Buschjäger, Sebastian and Honysz, Philipp-Jan and Morik, Katharina. Very Fast Streaming Submodular Function Maximization (Extended Version). 2021. Arrow Symbol
Buschjaeger/Honysz/2020a Buschjäger, Sebastian and Honysz, Philipp-Jan and Morik, Katharina. Generalized Isolation Forest: Some Theory and More Applications -- Extended Abstract. In Proceedings 2020 IEEE 7th International Conference on Data Science and Advanced Analytics (DSAA 2020), IEEE, 2020.
Buschjaeger/etal/2020c Sebastian Buschjäger and Lukas Pfahler and Katharina Morik. Generalized Negative Correlation Learning for Deep Ensembling. 2020. Arrow Symbol
Buschjaeger/etal/2020a Buschjäger, Sebastian and Pfahler, Lukas and Buss, Jens and Morik, Katharina and Rhode, Wolfgang. On-Site Gamma-Hadron Separation with Deep Learning on FPGAs. In Joint European Conference on Machine Learning and Knowledge Discovery in Databases, Springer, 2020. Arrow Symbol
Buschjaeger/etal/2020d Buschjäger, Sebastian and Honysz, Philipp-Jan and Morik, Katharina. Randomized outlier detection with trees. In International Journal of Data Science and Analytics, Seiten 1--14, Springer, 2020. Arrow Symbol
Buschjaeger/etal/2020b Buschjäger, Sebastian and Chen, Jian-Jia and Chen, Kuan-Hsun and Günzel, Mario and Hakert, Christian and Morik, Katharina and Novkin, Rodion and Pfahler, Lukas and Yayla, Mikail. Towards Explainable Bit Error Tolerance of Resistive RAM-Based Binarized Neural Networks. 2020. Arrow Symbol
Buschjaeger/etal/2019a Buschjäger, Sebastian and Liebig, Thomas and Morik, Katharina. Gaussian Model Trees for Traffic Imputation. In Proceedings of the International Conference on Pattern Recognition Applications and Methods (ICPRAM), Seiten 243 - 254, SciTePress, 2019. Arrow Symbol
Hakert/Yayla/2019a Hakert, Christian and Yayla, Mikail and Chen, Kuan-Hsun and Brueggen, Georg von der and Chen, Jian-Jia and Buschjaeger, Sebastian and Morik, Katharina and Genssler, Paul R. and Bauer, Lars and Amrouch, Hussam and Henkel, Joerg. Stack Usage Analysis for Efficient Wear Leveling in Non-Volatile Main Memory Systems. In 1st ACM/IEEE Workshop on Machine Learning for CAD (MLCAD), 2019. Arrow Symbol
Buschjaeger/Morik/2017b Buschjäger, Sebastian and Morik, Katharina. Decision Tree and Random Forest Implementations for Fast Filtering of Sensor Data. In IEEE Transactions on Circuits and Systems I: Regular Papers, Vol. 65-I, No. 1, Seiten 209--222, 2018. Arrow Symbol
Morik/etal/2017a Morik, Katharina and Bockermann, Christian and Buschjäger, Sebastian. Big Data Science. In German journal on Artificial Intelligence (KI 2017), Vol. 32, No. 1, Seiten 27--36, 2017. Arrow Symbol
Buschjaeger/etal/2017a Buschjäger, Sebastian and Morik, Katharina and Schmidt, Maik. Summary Extraction on Data Streams in Embedded Systems. In Proceedings of the ECML Workshop on IoT Large Scale Learning From Data Streams, 2017. Arrow Symbol
Buschjaeger/2016a Buschjäger, Sebastian. Online Gauß-Prozesse zur Regression auf FPGAs. TU Dortmund, 2016. Arrow Symbol
Buschjaeger/etal/2015a Buschjäger, Sebastian and Pfahler, Lukas and Morik, Katharina. Discovering Subtle Word Relation in Large German Corpora. In Proceedings of the 3rd Workshop on the Challenges in the Management of Large Corpora, 2015. Arrow Symbol
Morik/etal/2015a Morik, Katharina and Jung, Alexander and Weckwerth, Jan and Rötner, Stefan and Hess, Sibylle and Buschjäger, Sebastian and Pfahler, Lukas. Untersuchungen zur Analyse von deutschsprachigen Textdaten. No. 2, Technische Universität Dortmund, 2015. Arrow Symbol

Software

Betreute Abschlussarbeiten