Inhalt des Dokuments
Grégoire Montavon
Room: 4.059
gregoire.montavon@tu-berlin.de [1]
Sekr. MAR 4-1
Marchstr. 23
D-10587 Berlin
Grégoire Montavon received a Masters degree in Communication Systems from École Polytechnique Fédérale de Lausanne in 2009 and a Ph.D. degree in Machine Learning from the Technische Universität Berlin in 2013. He is currently a Research Associate in the Machine Learning Group at TU Berlin. His research interests are neural networks, machine learning and data analysis.
Research
2015-2018: Explaining machine learning decisions
The goal of this
project is to develop methods to explain the decisions (e.g.
classifications) of machine learning models in terms of input
variables (i.e. which input variables are relevant for the model's
decision). Techniques that have been developed include the deep
Taylor decomposition, that operates by performing a first-order
Taylor expansion at each neuron of a deep network. These expansions
are then recombined to produce a relevance propagation
algorithm, where the model's decision is redistributed from layer
to layer until the input is reached. www.heatmapping.org [2]
2012-2013: Machine learning in the chemical compound space
The project
consists of using machine learning to dramatically accelerate the
calculation of molecular properties (e.g. atomization energy or
polarizability) for large collections of molecules. These properties
are usually obtained from complex physics simulations, that must be
performed for each molecule individually. The machine learning speedup
is mainly based on exploiting similarity between molecules, and on
automatically extracting a more compact task representation.
www.quantum-machine.org [3]
Teaching
Winter semester 2018/19
- Teaching assistant for Machine Learning 1 [4]
- Teaching assistant for Machine Learning 2 [5]
- Organizer for Deep Neural Networks [6]
- Organizer for Seminar Hot Topics in Machine Learning [7]
Summer semester 2018
Publications
| 2018-08-13 | M Alber, S Lapuschkin,
P Seegerer, M Hägele, KT Schütt, G Montavon, W Samek, KR Müller, S
Dähne, PJ Kindermans. iNNvestigate neural networks!
[8] |
| 2018-06-11 | C Anders, G Montavon,
W Samek, KR Müller. Understanding Patch-Based Learning by Explaining
Predictions [9] |
| 2018-05-16 | J Kauffmann, KR
Müller, G Montavon. Towards Explaining Anomalies: A Deep Taylor
Decomposition of One-Class Models [10] |
| 2017-07-17 | F Horn, L Arras, G
Montavon, KR Müller, W Samek. Exploring text datasets by visualizing
relevant words [11] |
| 2012 | G Montavon, G Orr, KR
Müller. Neural Networks: Tricks of the Trade, 2nd Edn [12], Springer
LNCS |
| 2012 | G
Montavon, KR Müller. Deep Boltzmann Machines and the Centering Trick
[13] in Neural Networks: Tricks of the Trade, 2nd Edn, Springer
LNCS (preprint [14], code
[15]) |
| 2018 | G Montavon, W Samek, KR
Müller. Methods for Interpreting and Understanding Deep Neural
Networks [16] Digital Signal Processing |
| 2017 | L Arras, F Horn, G Montavon,
KR Müller, W Samek. "What is Relevant in a Text Document?":
An Interpretable Machine Learning Approach [17] PLOS ONE |
| 2017 | G
Montavon, S Lapuschkin, A Binder, W Samek, KR Müller. Explaining
NonLinear Classification Decisions with Deep Taylor Decomposition
[18] Pattern Recognition |
| 2016 | W Samek, A Binder, G Montavon, S
Lapuschkin, KR Müller. Evaluating the Visualization of What a Deep
Neural Network has Learned [19] IEEE Transactions on Neural Networks and Learning Systems (TNNLS) |
| 2015 | S Bach, A Binder, G Montavon, F
Klauschen, KR Müller, W Samek. On Pixel-wise Explanations for
Non-Linear Classifier Decisions by Layer-wise Relevance Propagation
[20] PLOS ONE |
| 2013 | G Montavon, M Rupp, V Gobre, A
Vazquez-Mayagoitia, K Hansen, A Tkatchenko, KR Müller, OAv
Lilienfeld. Machine Learning of Molecular Electronic Properties in
Chemical Compound Space [21] New Journal of Physics (NJP) |
| 2013 | K
Hansen, G Montavon, F Biegler, S Fazli, M Rupp, M Scheffler, OAv
Lilienfeld, A Tkatchenko, KR Müller. Assessment and Validation of
Machine Learning Methods for Predicting Molecular Atomization Energies
[22] Journal of Chemical Theory and Computation (JCTC) |
| 2013 | G Montavon, M Braun, T Krueger,
KR Müller. Analyzing Local Structure in Kernel-based Learning:
Explanation, Complexity and Reliability Assessment [23] IEEE Signal Processing Magazine |
| 2011 | G
Montavon, M Braun, KR Müller. Kernel Analysis of Deep Networks
[24] Journal of Machine Learning Research (JMLR) |
| 2016 | G
Montavon, KR Müller, M Cuturi. Wasserstein Training of Restricted
Boltzmann Machines [25] Advances in Neural Information Processing Systems (NIPS) (code [26]) |
| 2016 | F Arbabzadah, G Montavon, KR
Müller, W Samek. Identifying Individual Facial Expressions by
Deconstructing a Neural Network [27] German Conference on Pattern Recognition (GCPR) |
| 2016 | A Binder, G Montavon, S Bach, KR
Müller, W Samek. Layer-wise Relevance Propagation for Neural Networks
with Local Renormalization Layers [28] International Conference on Artificial Neural Networks (ICANN) |
| 2016 | S Lapuschkin, A Binder, G
Montavon, KR Müller, W Samek. Analyzing Classifiers: Fisher Vectors
and Deep Neural Networks [29] IEEE Conference on Computer Vision and Pattern Recognition (CVPR) |
| 2016 | A Binder, S Bach, G Montavon, KR
Müller, W Samek. Layer-wise Relevance Propagation for Deep Neural
Network Architectures [30] International Conference on Information Science and Applications (ICISA) |
| 2012 | G Montavon, K Hansen, S Fazli, M
Rupp, F Biegler, A Ziehe, A Tkatchenko, OAv Lilienfeld, KR Müller.
Learning Invariant Representations of Molecules for Atomization Energy
Prediction [31] Advances in Neural Information Processing Systems (NIPS) |
| 2012 | G Montavon, M Braun, KR Müller.
Deep Boltzmann Machines as Feed-Forward Hierarchies [32] International Conference on Artificial Intelligence and Statistics (AISTATS) |
| 2010 | G Montavon, M Braun, KR Müller.
Layer-Wise Analysis of Deep Networks with Gaussian Kernels [33] Advances in Neural Information Processing Systems (NIPS) |
| 2017 | L Arras, G Montavon, KR
Müller, W Samek. Explaining Recurrent Neural Network Predictions in
Sentiment Analysis [34] EMNLP Workshop on Computational Approaches to Subjectivity, Sentiment & Social Media Analysis |
| 2016 | W Samek, G Montavon, A
Binder, S Lapuschkin, KR Müller. Interpreting the Predictions of
Complex ML Models by Layer-wise Relevance Propagation [35] NIPS Workshop on Interpretable ML for Complex Systems |
| 2016 | L Arras, F Horn, G Montavon,
KR Müller, W Samek. Explaining Predictions of Non-Linear Classifiers
in NLP [36] ACL Workshop on Representation Learning for NLP |
| 2016 | G Montavon, S Bach, A Binder,
W Samek, KR Müller. Deep Taylor Decomposition of Neural Networks
[37] ICML Workshop on Visualization for Deep Learning |
| 2016 | A Binder, W
Samek, G Montavon, S Bach, KR Müller. Analyzing and Validating Neural
Networks Predictions [38] ICML Workshop on Visualization for Deep Learning |
| 2016 | S
Lapuschkin, A Binder, G Montavon, KR Müller, W Samek The Layer-wise
Relevance Propagation Toolbox for Artificial Neural Networks [39] Journal of Machine Learning Research, Software Track (JMLR/MLOSS) |
| 2013 | G Montavon, KR Müller.
Neural Networks for Computational Chemistry: Pitfalls and
Recommendations [40] MRS Online Proceedings Library |
| 2009 | G Montavon. Deep Learning for
Spoken Language Identification [41] NIPS Workshop on Deep Learning for Speech Recognition and Related Applications |
| 2013 | G Montavon. On Layer-Wise
Representations in Deep Neural Networks [42] PhD Thesis, Technische Universität Berlin, Germany |
| 2009 | G Montavon. A Machine Learning
Approach to Classification of Low Resolution Histological Samples
[43] Master Thesis, École Polytechnique Fédérale de Lausanne, Switzerland |