AsjaFischerAkademischer Rat (Assistant Professor)

Computer Science Institute
University of Bonn

Profiles: LinkedIn, Google Scholar, DBLP

Room A108
Römerstr. 164, 53117 Bonn
University of Bonn, Computer Science
asja.fischer@gmail.com

Short CV


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


2017

  • D. Arpit, S. J. e}, N. Ballas, D. Krueger, E. Bengio, M. S. Kanwal, T. Maharaj, A. Fischer, A. Courville, Y. Bengio, and S. Lacoste-Julien, “A closer look at memorization in deep networks,” in Proceedings of the 34th international conference on machine learning, 2017, pp. 233-242.
    [BibTeX] [Download PDF]
    @InProceedings{pmlr-v70-arpit17a,
    title = {A Closer Look at Memorization in Deep Networks},
    author = {Devansh Arpit and Stanis{\l}aw Jastrz{\k{e}}bski and Nicolas Ballas and David Krueger and Emmanuel Bengio and Maxinder S. Kanwal and Tegan Maharaj and Asja Fischer and Aaron Courville and Yoshua Bengio and Simon Lacoste-Julien},
    booktitle = {Proceedings of the 34th International Conference on Machine Learning},
    pages = {233--242},
    year = {2017},
    editor = {Doina Precup and Yee Whye Teh},
    volume = {70},
    series = {Proceedings of Machine Learning Research},
    publisher = {PMLR},
    url = {http://proceedings.mlr.press/v70/arpit17a/arpit17a.pdf},
    }

  • D. Lukovnikov, A. Fischer, S. Auer, and J. Lehmann, “Neural network-based question answering over knowledge graphs on word and character level,” in Proceedings of the 26th international conference on world wide web, 2017.
    [BibTeX] [Download PDF]
    @InProceedings{lukovnikov2017www,
    Title = {Neural Network-based Question Answering over Knowledge Graphs on Word and Character Level},
    Author = {Lukovnikov, Denis and Fischer, Asja and Auer, Soeren and Lehmann, Jens},
    Booktitle = {Proceedings of the 26th international conference on World Wide Web},
    Year = {2017},
    Keywords = {2017 group_aksw sys:relevantFor:infai boa sys:relevantFor:bis lehmann MOLE},
    Url = {http://jens-lehmann.org/files/2017/www_nn_factoid_qa.pdf}
    }

  • D. Krueger, N. Ballas, S. Jastrzebski, D. Arpit, M. S. Kanwal, T. Maharaj, E. Bengio, A. Fischer, and A. Courville, “Deep nets don’t learn via memorization,” , 2017.
    [BibTeX] [Download PDF]
    @article{krueger2017deep,
    title={Deep Nets Don't Learn via Memorization},
    author={Krueger, David and Ballas, Nicolas and Jastrzebski, Stanislaw and Arpit, Devansh and Kanwal, Maxinder S and Maharaj, Tegan and Bengio, Emmanuel and Fischer, Asja and Courville, Aaron},
    year={2017},
    url={https://openreview.net/pdf?id=rJv6ZgHYg}
    }

  • Y. Bengio, T. Mesnard, A. Fischer, S. Zhang, and Y. Wu, “Stdp-compatible approximation of back-propagation in an energy-based model,” Neural computation, 2017.
    [BibTeX] [Download PDF]
    @article{bengio2017stdp,
    title={STDP-Compatible Approximation of Back-Propagation in an Energy-Based Model},
    author={Bengio, Yoshua and Mesnard, Thomas and Fischer, Asja and Zhang, Saizheng and Wu, Yuhuai},
    journal={Neural Computation},
    year={2017},
    publisher={MIT Press One Rogers St., Cambridge, MA 02142-1209 USA journals-info@ mit. edu},
    url={http://www.mitpressjournals.org/doi/full/10.1162/NECO_a_00934}
    }

  • B. Weghenkel, A. Fischer, and L. Wiskott, “Graph-based predictable feature analysis,” Machine learning, pp. 1-22, 2017.
    [BibTeX]
    @article{weghenkel2017graph,
    title={Graph-based predictable feature analysis},
    author={Weghenkel, Bj{\"o}rn and Fischer, Asja and Wiskott, Laurenz},
    journal={Machine Learning},
    pages={1--22},
    year={2017},
    publisher={Springer US}
    url={ttp://rdcu.be/vDAj}
    }

  • S. Kosovan, J. Lehmann, and A. Fischer, “Dialogue response generation using neural networks with attention and background knowledge,” in Proceedings of the computer science conference for university of bonn students (cscubs) 2017, 2017.
    [BibTeX] [Download PDF]
    @inproceedings{kosovan-2017-cscubs-dialogues,
    added-at = {2017-08-31T16:24:45.000+0200},
    author = {Kosovan, Sofiia and Lehmann, Jens and Fischer, Asja},
    biburl = {https://www.bibsonomy.org/bibtex/2382e99967e196356de3f52f06df22115/aksw},
    booktitle = {Proceedings of the Computer Science Conference for University of Bonn Students (CSCUBS) 2017},
    interhash = {919e1cac53865a68cbefe447f521bd50},
    intrahash = {382e99967e196356de3f52f06df22115},
    keywords = {2017 group_aksw lehmann mole},
    notes = {Best Paper Award},
    timestamp = {2017-08-31T16:24:45.000+0200},
    title = {Dialogue Response Generation using Neural Networks with Attention and Background Knowledge},
    url = {http://jens-lehmann.org/files/2017/cscubs_dialogues.pdf},
    year = 2017
    }

2016

  • J. Bornschein, S. Shabanian, A. Fischer, and Y. Bengio, “Bidirectional helmholtz machines,” in Proceedings of the 33rd international conference on machine learning, 2016, pp. 2511-2519.
    [BibTeX] [Download PDF]
    @InProceedings{pmlr-v48-bornschein16,
    title = {Bidirectional Helmholtz Machines},
    author = {Jorg Bornschein and Samira Shabanian and Asja Fischer and Yoshua Bengio},
    booktitle = {Proceedings of The 33rd International Conference on Machine Learning},
    pages = {2511--2519},
    year = {2016},
    editor = {Maria Florina Balcan and Kilian Q. Weinberger},
    volume = {48},
    series = {Proceedings of Machine Learning Research},
    publisher = {PMLR},
    pdf = {http://proceedings.mlr.press/v48/bornschein16.pdf},
    url = {http://proceedings.mlr.press/v48/bornschein16.pdf}
    }

  • J. Melchior, A. Fischer, and L. Wiskott, “How to center deep boltzmann machines,” Journal of machine learning research, vol. 17, iss. 99, pp. 1-61, 2016.
    [BibTeX] [Download PDF]
    @article{melchior2016center,
    title={How to center deep Boltzmann machines},
    author={Melchior, Jan and Fischer, Asja and Wiskott, Laurenz},
    journal={Journal of Machine Learning Research},
    volume={17},
    number={99},
    pages={1--61},
    year={2016},
    url={http://www.jmlr.org/papers/volume17/14-237/14-237.pdf}
    }

2015

  • O. Krause, A. Fischer, and C. Igel, “Population monte carlo meets contrastive divergence learning,” in Machine learning reports, , 2015, pp. 93-94.
    [BibTeX] [Download PDF]
    @incollection{krause2015population,
    title={Population Monte Carlo meets contrastive divergence learning},
    author={Krause, Oswin and Fischer, Asja and Igel, Christian},
    booktitle={Machine Learning Reports},
    pages={93--94},
    year={2015},
    url={https://arxiv.org/pdf/1510.01624.pdf}
    }

  • Y. Bengio and A. Fischer, “Early inference in energy-based models approximates back-propagation,” Arxiv preprint arxiv:1510.02777, 2015.
    [BibTeX] [Download PDF]
    @article{bengio2015early,
    title={Early Inference in Energy-Based Models Approximates Back-Propagation},
    author={Bengio, Yoshua and Fischer, Asja},
    journal={arXiv preprint arXiv:1510.02777},
    year={2015},
    url={https://arxiv.org/pdf/1510.02777.pdf}
    }

  • A. Fischer, “Training restricted boltzmann machines,” Ki-künstliche intelligenz, vol. 29, iss. 4, pp. 441-444, 2015.
    [BibTeX] [Download PDF]
    @article{fischer2015training,
    title={Training restricted boltzmann machines},
    author={Fischer, Asja},
    journal={KI-K{\"u}nstliche Intelligenz},
    volume={29},
    number={4},
    pages={441--444},
    year={2015},
    publisher={Springer Berlin Heidelberg},
    url={https://link.springer.com/article/10.1007/s13218-015-0371-2}
    }

  • A. Fischer and C. Igel, “A bound for the convergence rate of parallel tempering for sampling restricted boltzmann machines,” Theoretical computer science, vol. 598, pp. 102-117, 2015.
    [BibTeX] [Download PDF]
    @article{fischer2015bound,
    title={A bound for the convergence rate of parallel tempering for sampling restricted Boltzmann machines},
    author={Fischer, Asja and Igel, Christian},
    journal={Theoretical Computer Science},
    volume={598},
    pages={102--117},
    year={2015},
    publisher={Elsevier},
    url={https://www.researchgate.net/profile/Christian_Igel/publication/277943390_A_bound_for_the_convergence_rate_of_parallel_tempering_for_sampling_restricted_Boltzmann_machines/links/55f09fb908aef559dc46d80c.pdf}
    }

  • D. Lee, S. Zhang, A. Fischer, and Y. Bengio, “Difference target propagation,” in Joint european conference on machine learning and knowledge discovery in databases, 2015, pp. 498-515.
    [BibTeX] [Download PDF]
    @inproceedings{lee2015difference,
    title={Difference target propagation},
    author={Lee, Dong-Hyun and Zhang, Saizheng and Fischer, Asja and Bengio, Yoshua},
    booktitle={Joint European Conference on Machine Learning and Knowledge Discovery in Databases},
    pages={498--515},
    year={2015},
    organization={Springer, Cham},
    url={https://arxiv.org/pdf/1412.7525.pdf}
    }

  • Y. Bengio, A. Fischer, T. Mesnard, S. Zhang, and Y. Wu, “From stdp towards biologically plausible deep learning,” in Deep learning workshop, international conference on machine learning (icml), 2015.
    [BibTeX] [Download PDF]
    @inproceedings{bengio2015stdp,
    title={From STDP towards biologically plausible deep learning},
    author={Bengio, Yoshua and Fischer, Asja and Mesnard, Thomas and Zhang, Saizheng and Wu, Yuhai},
    booktitle={Deep Learning Workshop, International Conference on Machine Learning (ICML)},
    year={2015},
    url={https://8109f4a4-a-62cb3a1a-s-sites.googlegroups.com/site/deeplearning2015/bengio-et-al.pdf?attachauth=ANoY7cqm5VGjZwmnnAeqlKXkKboPLiQ2NovstAQ8aL-BLCTzjUibuZ7bucTkBXypONjrxieXOwMT6psd0K9z5xu4csy6_mAhOlAx3Jvblyz0g9Y4jKuqH8y2DUucWPg32jgWssAHqmv8AYUQisPwyXK2HjEEx9bfaDnISOv1-I1jYqVl1dv5jTIgFLGjG2Ivydyblgi6N0oLw_iS1fjMipe0-7kc_zExfQ%3D%3D&attredirects=0}
    }

  • Y. Bengio, T. Mesnard, A. Fischer, S. Zhang, and Y. Wu, “Stdp as presynaptic activity times rate of change of postsynaptic activity,” Arxiv preprint arxiv:1509.05936, 2015.
    [BibTeX] [Download PDF]
    @article{bengio2015stdp,
    title={STDP as presynaptic activity times rate of change of postsynaptic activity},
    author={Bengio, Yoshua and Mesnard, Thomas and Fischer, Asja and Zhang, Saizheng and Wu, Yuhuai},
    journal={arXiv preprint arXiv:1509.05936},
    year={2015},
    url={https://arxiv.org/pdf/1509.05936.pdf}
    }

  • O. Krause, A. Fischer, and C. Igel, “Population-contrastive-divergence: does consistency help with rbm training?,” Arxiv preprint arxiv:1510.01624, 2015.
    [BibTeX] [Download PDF]
    @article{krause2015population,
    title={Population-Contrastive-Divergence: Does Consistency help with RBM training?},
    author={Krause, Oswin and Fischer, Asja and Igel, Christian},
    journal={arXiv preprint arXiv:1510.01624},
    year={2015},
    url= {http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.710.1085&rep=rep1&type=pdf#page=93}
    }

2014

  • A. Fischer and C. Igel, “Training restricted boltzmann machines: an introduction,” Pattern recognition, vol. 47, iss. 1, pp. 25-39, 2014.
    [BibTeX] [Download PDF]
    @article{fischer2014training,
    title={Training restricted Boltzmann machines: an introduction},
    author={Fischer, Asja and Igel, Christian},
    journal={Pattern Recognition},
    volume={47},
    number={1},
    pages={25--39},
    year={2014},
    publisher={Pergamon},
    url={http://image.diku.dk/igel/paper/TRBMAI.pdf}
    }

2013

  • K. Brügge, A. Fischer, and C. Igel, “The flip-the-state transition operator for restricted boltzmann machines,” Machine learning, vol. 93, iss. 1, pp. 53-69, 2013.
    [BibTeX] [Download PDF]
    @article{brugge2013flip,
    title={The flip-the-state transition operator for restricted Boltzmann machines},
    author={Br{\"u}gge, Kai and Fischer, Asja and Igel, Christian},
    journal={Machine learning},
    volume={93},
    number={1},
    pages={53--69},
    year={2013},
    publisher={Springer US},
    url={ http://image.diku.dk/igel/paper/TFTSTOfRBMs.pdf}
    }

  • O. Krause, A. Fischer, T. Glasmachers, and C. Igel, “Approximation properties of DBNs with binary hidden units and real-valued visible units,” in Proceedings of the 30th international conference on machine learning, 2013, pp. 419-426.
    [BibTeX]
    @InProceedings{pmlr-v28-krause13,
    title = {Approximation properties of {DBNs} with binary hidden units and real-valued visible units},
    author = {Oswin Krause and Asja Fischer and Tobias Glasmachers and Christian Igel},
    booktitle = {Proceedings of the 30th International Conference on Machine Learning},
    pages = {419--426},
    year = {2013},
    editor = {Sanjoy Dasgupta and David McAllester},
    volume = {28},
    number = {1},
    series = {Proceedings of Machine Learning Research},
    publisher = {PMLR},
    pdf = {http://proceedings.mlr.press/v28/krause13.pdf},
    }

2012

  • A. Fischer and C. Igel, “An introduction to restricted boltzmann machines,” Progress in pattern recognition, image analysis, computer vision, and applications, pp. 14-36, 2012.
    [BibTeX] [Download PDF]
    @article{fischer2012introduction,
    title={An introduction to restricted Boltzmann machines},
    author={Fischer, Asja and Igel, Christian},
    journal={Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications},
    pages={14--36},
    year={2012},
    publisher={Springer Berlin/Heidelberg},
    url={https://www.researchgate.net/profile/Asja_Fischer/publication/243463621_An_Introduction_to_Restricted_Boltzmann_Machines/links/0a85e5320cc4851d83000000.pdf}
    }

2011

  • A. Fischer and C. Igel, “Bounding the bias of contrastive divergence learning,” Neural computation, vol. 23, iss. 3, pp. 664-673, 2011.
    [BibTeX] [Download PDF]
    @article{fischer2011bounding,
    title={Bounding the bias of contrastive divergence learning},
    author={Fischer, Asja and Igel, Christian},
    journal={Neural computation},
    volume={23},
    number={3},
    pages={664--673},
    year={2011},
    publisher={MIT Press 238 Main St., Suite 500, Cambridge, MA 02142-1046, USA email: journals-info@ mit. edu},
    url={https://www.researchgate.net/profile/Christian_Igel/publication/49687633_Bounding_the_Bias_of_Contrastive_Divergence_Learning/links/00b495256986be013c000000.pdf}
    }

  • A. Fischer and C. Igel, “Training rbms based on the signs of the cd approximation of the log-likelihood derivatives.,” in Esann, 2011.
    [BibTeX] [Download PDF]
    @inproceedings{fischer2011training,
    title={Training RBMs based on the signs of the CD approximation of the log-likelihood derivatives.},
    author={Fischer, Asja and Igel, Christian},
    booktitle={ESANN},
    year={2011},
    url={https://pdfs.semanticscholar.org/8710/8a10fe4160c714f8dd4612d2f85660fdbdad.pdf}
    }

2010

  • A. Fischer and C. Igel, “Challenges in training restricted boltzmann machines,” New challenges in neural computation (nc2), iss. 04, pp. 11-24, 2010.
    [BibTeX] [Download PDF]
    @article{fischer2010challenges,
    title={Challenges in training restricted Boltzmann machines},
    author={Fischer, Asja and Igel, Christian},
    journal={New Challenges in Neural Computation (NC2)},
    number={04},
    pages={11--24},
    year={2010},
    url={https://www.techfak.uni-bielefeld.de/~fschleif/mlr/mlr_04_2010.pdf#page=13}
    }

  • A. Fischer and C. Igel, “Empirical analysis of the divergence of gibbs sampling based learning algorithms for restricted boltzmann machines,” in International conference on artificial neural networks, 2010, pp. 208-217.
    [BibTeX] [Download PDF]
    @inproceedings{fischer2010empirical,
    title={Empirical analysis of the divergence of Gibbs sampling based learning algorithms for restricted Boltzmann machines},
    author={Fischer, Asja and Igel, Christian},
    booktitle={International Conference on Artificial Neural Networks},
    pages={208--217},
    year={2010},
    organization={Springer, Berlin, Heidelberg},
    url={http://image.diku.dk/igel/paper/EAotDoGSBLAfRBM.pdf}
    }