Page Content
Thomas Goerttler
- © Thomas Goerttler
Room: MAR 5062
Phone: 314-26756
Fax: 314-73121
Email: thomas.goerttler@ni.tu-berlin.de
Sekretariat MAR 5-6
Marchstraße 23
D-10587 Berlin
Phone: 314-26756
Fax: 314-73121
Email: thomas.goerttler@ni.tu-berlin.de
Sekretariat MAR 5-6
Marchstraße 23
D-10587 Berlin
Co-founder of the Deep Networks Club.
Forschungsinteresse
- Towards Understanding of Deep Learning
- Meta-Learning
- Transfer Learning
- Reinforcement Learning
- Generative Models
| seit 2018 | TU Berlin, Neuronale Informationsverarbeitung | Wissenschaftlicher Mitarbeiter |
| 2017-2018 | Hasso-Plattner Institut, Universität Potsdam Knowledge Discovery and Data Mining | Wissenschaftlicher Mitarbeiter |
| 2015-2017 | HU Berlin, FU Berlin, TU Berlin und FU Bozen | Master in Statistik Abschlussarbeit: "Stabilizing GANs by Manipulating the Prior Distribution" |
| 2012-2015 | Hasso-Plattner Institut, Universität Potsdam | Bachelor in IT-Systems Engineering Abschlussarbeit: "Development and Adaption of Algorithms in iOS to Examine the Stress Niveau of a Human Being" |
| 2021 | Dataset | R. Seidel, D. Zarafeta, M. Siebert, R. Dastgheib Shirazi, S. Seo, T. Goerttler, K. Obermayer Berlin-APC: A Privacy-Friendly Dataset for Automated Passenger Counting in Public Transport TU Berlin |
| 2021 | Workshop paper (peer-reviewed) | L. Müller, M. Ploner, T. Goerttler, K. Obermayer An Interactive Introduction to Model-Agnostic Meta-Learning Workshop on Visualization for AI Explainability at IEEE VIS |
| 2021 | Workshop paper (peer-reviewed) | T. Goerttler, K. Obermayer Exploring the Similarity of Representations in Model-Agnostic Meta-Learning Learning to Learn workshop at ICLR |
| 2019 | Conference paper (peer-reviewed) | T. Goerttler, M. Kloft Learning a Multimodal Prior Distribution for Generative Adversarial Nets Proceedings of the Conference on LWDA, 94-105 |
| 2021 | ICLR Workshop on Learning to Learn (PC member) |
| 2020 | ECML PKDD (PC member) |
| 2018 | CIKM, ICDE, ICDM, JCAI, KDD, SDM, VLDC (all external) |
| 2017 | ASA Data Science Journal (external) |
| WS 2021/22 | TU Berlin | Praktisches Programmieren und Rechneraufbau |
| SS 2021 | TU Berlin | Neural Information Processing Project |
| SS 2021 | TU Berlin | Praktisches Programmieren und Rechneraufbau |
| WS 2020/21 | TU Berlin | Praktisches Programmieren und Rechneraufbau |
| SS 2020 | TU Berlin | Praktisches Programmieren und Rechneraufbau |
| WS 2019/20 | TU Berlin | Praktisches Programmieren und Rechneraufbau |
| SS 2019 | TU Berlin | Neural Information Processing Project |
| SS 2019 | TU Berlin | Praktisches Programmieren und Rechneraufbau |
| WS 2018/19 | TU Berlin | Einführung in die Informatik I |
| SS 2018 | HPI, Universität Potsdam | Smart Data Representation for Big Data Analytics |
| SS 2018 | HPI, Universität Potsdam | Big Data Analytics Lab |
| WS 2017/18 | HPI, Universität Potsdam | Big Data Analytics |
| SS 2016 | HWR Berlin | Advanced Econometrics |
| SS 2016 | HWR Berlin | Introduction to Programming |
| WS 2013/14 | HPI, Universität Potsdam | Mathematik 1, Diskrete Strukturen und Logik |
| 2021 | Masterarbeit | Luis Müller | Inspiring Representation Change in Model-Agnostic Meta-Learning |
| 2021 | Bachelorarbeit | Philipp Pirlet | Comparing Different Learning Strategies of Model-Agnostic Meta-Learning |
| 2021 | Bachelorarbeit | Jakob Hartmann | Learning Three-Check Chess From Self-Play Using Deep Reinforcement Learning |
| 2021 | Masterarbeit | Leonhard Donle | Investigation of detection algorithms for slow oscillations in EEG data (jointly supervised with Cristiana Dimulescu) |
| 2021 | Masterarbeit | Jonas Dippel | Fine-grained Visual Representation Learning |
| 2021 | Masterarbeit | Jasper Ullrich | Improving Sample Efficiency in Deep Reinforcement Learning Using Methods from Continual Learning |
| 2021 | Bachelorarbeit | Feriel Amira | Analysis of Deep Reinforcement Learning on a Cooperative Card Game |
| 2021 | Masterarbeit | Niels Warncke | Transfer Learning for Autoencoders on Audio Data |
| 2021 | Bachelorarbeit | Marco Rosinus Serrano | Investigation of Intrinsic Dimension of Representations in Deep Networks |
| 2020 | Masterarbeit | Shashi Durbha | Quantifying Learned Representation in Deep Neural Networks |
| 2020 | Masterarbeit | Florian Bemmerl | Evaluation of the Transferability in Deep Networks |
| 2020 | Bachelorarbeit | Lukas Schmidt | Analysis of Deep Reinforcement Learning on a Card Game with Imperfect Information |
| 2019 | Lab rotation | Evert de Man | Creating Gradient-Based Saliency Maps in Networks Estimating Passenger Count |
| 2019 | Lab rotation | Liz Weerdmeester | Counting People on Image Sequences Using Convolutional Long Short-Term Memory Networks |
| 2019 | Bachelorarbeit | Anika Apel | Evaluation of Deep Reinforcement Learning on a Partially Observable Card Game |
| 2019 | Bachelorarbeit | Nico Jahn | Counting People on Image Sequences Using Recurrent Neural Networks |
| 2018 | Masterarbeit | Jan Kohstall | Improving Classification Accuracy by Applying Cluster Validation Analysis |
| 2018 | Masterarbeit | Sebastian Rehfeldt | Feature Ranking for Incomplete Datasets by Modeling the Uncertainty of Missing Values (jointly supervised with Arvind Shekar) |
Zusatzinformationen / Extras
Quick Access:
Schnellnavigation zur Seite über Nummerneingabe