Prof. Dr. Asja Fischer left SDA. The profile below reflects the status at the point of her departure and is no longer updated.
Full Professor
Faculty of Mathematics
Ruhr-Universität Bochum
Profiles: LinkedIn, Google Scholar, DBLP
Office: IB 3/153
Universitätsstraße 150
44801 Bochum, Germany
Short CV
Note: I recently moved to Ruhr-University Bochum where I am Assistant Professor for Machine Learning now! I am still looking for a PhD student 🙂
Dr. Asja Fischer is a Assistant Professor at the Computer Science Department III of the University of Bonn. Before, she was a post-doctoral researcher at the Montreal Institute for Machine Learning (MILA). Between 2010 and end of 2014, Asja was employed both at the Institute for Neural Computation at the Ruhr-University Bochum and the Department of Computer Science at the University of Copenhagen working on her PhD in Machine Learning, which she defended in Copenhagen in 2014. Before, she studied Biology. Bioinformatics, Mathematics and Cognitive Science at the Ruhr-University Bochum, the Universidade de Lisboa and the University of Osnabrück.
Research Interests
- Machine Learning
- Deep Learning
- Probabilistic Models
- Sampling Techniques
- Big Data
Teaching
Winter 2017
- Lecture “Knowledge Graph Analysis”
- Exercise “Knowledge Graph Analysis”
- Seminar “Knowledge Graph Analysis”
Summer 2017
- Lab “Deep Learning”
- Seminar “Deep Learning”
Winter 2016
- Lecture “Knowledge Graph Analysis”
- Exercise “Knowledge Graph Analysis”
- Seminar “Knowledge Graph Analysis”
Publications
2022
Marginal Tail-Adaptive Normalizing Flows Inproceedings
In: International Conference on Machine Learning, ICML 2022, 17-23 July 2022, Baltimore, Maryland, USA, pp. 12020–12048, PMLR, 2022.
Bringing Light Into the Dark: A Large-Scale Evaluation of Knowledge Graph Embedding Models Under a Unified Framework Journal Article
In: IEEE Trans. Pattern Anal. Mach. Intell., vol. 44, no. 12, pp. 8825–8845, 2022.
2021
Insertion-based Tree Decoding Inproceedings
In: Findings of the Association for Computational Linguistics: ACL/IJCNLP 2021, Online Event, August 1-6, 2021, pp. 3201–3213, Association for Computational Linguistics, 2021.
On the convergence of the Metropolis algorithm with fixed-order updates for multivariate binary probability distributions Inproceedings
In: The 24th International Conference on Artificial Intelligence and Statistics, AISTATS 2021, April 13-15, 2021, Virtual Event, pp. 469–477, PMLR, 2021.
Thresholded Adaptive Validation: Tuning the Graphical Lasso for Graph Recovery Inproceedings
In: The 24th International Conference on Artificial Intelligence and Statistics, AISTATS 2021, April 13-15, 2021, Virtual Event, pp. 1864–1872, PMLR, 2021.
Detecting Compositionally Out-of-Distribution Examples in Semantic Parsing Inproceedings
In: Findings of the Association for Computational Linguistics: EMNLP 2021, Virtual Event / Punta Cana, Dominican Republic, 16-20 November, 2021, pp. 591–598, Association for Computational Linguistics, 2021.
SmoothLRP: Smoothing LRP by Averaging over Stochastic Input Variations Inproceedings
In: 29th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, ESANN 2021, Online event (Bruges, Belgium), October 6-8, 2021, 2021.
Improving Breadth-Wise Backpropagation in Graph Neural Networks Helps Learning Long-Range Dependencies Inproceedings
In: Proceedings of the 38th International Conference on Machine Learning, ICML 2021, 18-24 July 2021, Virtual Event, pp. 7180–7191, PMLR, 2021.
ŐRUS-NER: A Multimodal Named Entity Recognition Framework for Noisy Data Inproceedings
In: Advances in Intelligent Data Analysis XIX - 19th International Symposium on Intelligent Data Analysis, IDA 2021, Porto, Portugal, April 26-28, 2021, Proceedings, pp. 89–100, Springer, 2021.
ORUS-NER: A Multimodal Named Entity Recognition Framework for Noisy Data Inproceedings
In: Advances in Intelligent Data Analysis XIX - 19th International Symposium on Intelligent Data Analysis, IDA 2021, Porto, Portugal, April 26-28, 2021, Proceedings, pp. 89–100, Springer, 2021.
Approaches to Uncertainty Quantification in Federated Deep Learning Inproceedings
In: Machine Learning and Principles and Practice of Knowledge Discovery in Databases - International Workshops of ECML PKDD 2021, Virtual Event, September 13-17, 2021, Proceedings, Part I, pp. 128–145, Springer, 2021.
Introduction to neural network-based question answering over knowledge graphs Journal Article
In: WIREs Data Mining Knowl. Discov., vol. 11, no. 3, 2021.
2020
Leveraging Frequency Analysis for Deep Fake Image Recognition Inproceedings
In: Proceedings of the 37th International Conference on Machine Learning, ICML 2020, 13-18 July 2020, Virtual Event, pp. 3247–3258, PMLR, 2020.
Leveraging Frequency Analysis for Deep Fake Image Recognition Inproceedings
In: Proceedings of the 37th International Conference on Machine Learning, ICML 2020, 13-18 July 2020, Virtual Event, pp. 3247–3258, PMLR, 2020.
Algorithms for Estimating the Partition Function of Restricted Boltzmann Machines (Extended Abstract) Inproceedings
In: Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence, IJCAI 2020, pp. 5045–5049, ijcai.org, 2020.
Detecting Adversarial Examples for Speech Recognition via Uncertainty Quantification Inproceedings
In: Interspeech 2020, 21st Annual Conference of the International Speech Communication Association, Virtual Event, Shanghai, China, 25-29 October 2020, pp. 4661–4665, ISCA, 2020.
Algorithms for estimating the partition function of restricted Boltzmann machines Journal Article
In: Artif. Intell., vol. 278, 2020.
Mimicking the radiologists'workflow: Estimating pediatric hand bone age with stacked deep neural networks Journal Article
In: Medical Image Anal., vol. 64, pp. 101743, 2020.
2019
On the Relation Between the Sharpest Directions of DNN Loss and the SGD Step Length Inproceedings
In: 7th International Conference on Learning Representations, ICLR 2019, New Orleans, LA, USA, May 6-9, 2019, OpenReview.net, 2019.
Incorporating Literals into Knowledge Graph Embeddings Inproceedings
In: The Semantic Web - ISWC 2019 - 18th International Semantic Web Conference, Auckland, New Zealand, October 26-30, 2019, Proceedings, Part I, pp. 347–363, Springer, 2019.
Pretrained Transformers for Simple Question Answering over Knowledge Graphs Inproceedings
In: The Semantic Web - ISWC 2019 - 18th International Semantic Web Conference, Auckland, New Zealand, October 26-30, 2019, Proceedings, Part I, pp. 470–486, Springer, 2019.
Learning to Rank Query Graphs for Complex Question Answering over Knowledge Graphs Inproceedings
In: The Semantic Web - ISWC 2019 - 18th International Semantic Web Conference, Auckland, New Zealand, October 26-30, 2019, Proceedings, Part I, pp. 487–504, Springer, 2019.
2018
Improving Response Selection in Multi-Turn Dialogue Systems by Incorporating Domain Knowledge Inproceedings
In: Proceedings of the 22nd Conference on Computational Natural Language Learning, CoNLL 2018, Brussels, Belgium, October 31 - November 1, 2018, pp. 497–507, Association for Computational Linguistics, 2018.
Width of Minima Reached by Stochastic Gradient Descent is Influenced by Learning Rate to Batch Size Ratio Inproceedings
In: Artificial Neural Networks and Machine Learning - ICANN 2018 - 27th International Conference on Artificial Neural Networks, Rhodes, Greece, October 4-7, 2018, Proceedings, Part III, pp. 392–402, Springer, 2018.
Finding Flatter Minima with SGD Inproceedings
In: 6th International Conference on Learning Representations, ICLR 2018, Vancouver, BC, Canada, April 30 - May 3, 2018, Workshop Track Proceedings, OpenReview.net, 2018.
On the regularization of Wasserstein GANs Inproceedings
In: 6th International Conference on Learning Representations, ICLR 2018, Vancouver, BC, Canada, April 30 - May 3, 2018, Conference Track Proceedings, OpenReview.net, 2018.
Population-Contrastive-Divergence: Does consistency help with RBM training? Journal Article
In: Pattern Recognit. Lett., vol. 102, pp. 1–7, 2018.
2017
Deep Nets Don't Learn via Memorization Inproceedings
In: 5th International Conference on Learning Representations, ICLR 2017, Toulon, France, April 24-26, 2017, Workshop Track Proceedings, OpenReview.net, 2017.
A Closer Look at Memorization in Deep Networks Inproceedings
In: Proceedings of the 34th International Conference on Machine Learning, ICML 2017, Sydney, NSW, Australia, 6-11 August 2017, pp. 233–242, PMLR, 2017.
Neural Network-based Question Answering over Knowledge Graphs on Word and Character Level Inproceedings
In: Proceedings of the 26th International Conference on World Wide Web, WWW 2017, Perth, Australia, April 3-7, 2017, pp. 1211–1220, ACM, 2017.
Graph-based predictable feature analysis Journal Article
In: Mach. Learn., vol. 106, no. 9-10, pp. 1359–1380, 2017.
STDP-Compatible Approximation of Backpropagation in an Energy-Based Model Journal Article
In: Neural Comput., vol. 29, no. 3, pp. 555–577, 2017.
2016
Bidirectional Helmholtz Machines Inproceedings
In: Proceedings of the 33nd International Conference on Machine Learning, ICML 2016, New York City, NY, USA, June 19-24, 2016, pp. 2511–2519, JMLR.org, 2016.
How to Center Deep Boltzmann Machines Journal Article
In: J. Mach. Learn. Res., vol. 17, pp. 99:1–99:61, 2016.
2015
Difference Target Propagation Inproceedings
In: Machine Learning and Knowledge Discovery in Databases - European Conference, ECML PKDD 2015, Porto, Portugal, September 7-11, 2015, Proceedings, Part I, pp. 498–515, Springer, 2015.
Training Restricted Boltzmann Machines Journal Article
In: Künstliche Intell., vol. 29, no. 4, pp. 441–444, 2015.
A bound for the convergence rate of parallel tempering for sampling restricted Boltzmann machines Journal Article
In: Theor. Comput. Sci., vol. 598, pp. 102–117, 2015.
2014
Training restricted Boltzmann machines: An introduction Journal Article
In: Pattern Recognit., vol. 47, no. 1, pp. 25–39, 2014.
2013
Approximation properties of DBNs with binary hidden units and real-valued visible units Inproceedings
In: Proceedings of the 30th International Conference on Machine Learning, ICML 2013, Atlanta, GA, USA, 16-21 June 2013, pp. 419–426, JMLR.org, 2013.
The flip-the-state transition operator for restricted Boltzmann machines Journal Article
In: Mach. Learn., vol. 93, no. 1, pp. 53–69, 2013.
2012
An Introduction to Restricted Boltzmann Machines Inproceedings
In: Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications - 17th Iberoamerican Congress, CIARP 2012, Buenos Aires, Argentina, September 3-6, 2012. Proceedings, pp. 14–36, Springer, 2012.
2011
Training RBMs based on the signs of the CD approximation of the log-likelihood derivatives Inproceedings
In: 19th European Symposium on Artificial Neural Networks, ESANN 2011, Bruges, Belgium, April 27-29, 2011, Proceedings, 2011.
Bounding the Bias of Contrastive Divergence Learning Journal Article
In: Neural Comput., vol. 23, no. 3, pp. 664–673, 2011.
2010
Empirical Analysis of the Divergence of Gibbs Sampling Based Learning Algorithms for Restricted Boltzmann Machines Inproceedings
In: Artificial Neural Networks - ICANN 2010 - 20th International Conference, Thessaloniki, Greece, September 15-18, 2010, Proceedings, Part III, pp. 208–217, Springer, 2010.