Inhalt des Dokuments
Grégoire Montavon
| Address: Grégoire Montavon Sekr. MAR 4-1 Marchstr. 23 D-10587 Berlin Germany |
| Room: MAR
4.059 |
| E-mail: gregoire.montavon@tu-berlin.de
[1] |
| 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 include interpretable machine
learning and deep neural networks.
|
Research
| 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] |
| 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
| Machine Learning 2
[4] |
| Machine
Learning 1 [5] |
| Seminar Big Data
& Scalable ML [6] |
Publications
| 2020-06-05 | T Schnake, O Eberle, J
Lederer, S Nakajima, K T. Schütt, KR Müller, G Montavon. XAI for
Graphs: Explaining Graph Neural Network Predictions by Identifying
Relevant Walks [7] |
| 2020-03-17 | W Samek, G Montavon, S
Lapuschkin, C Anders, KR Müller. Toward Interpretable Machine
Learning: Transparent Deep Neural Networks and Beyond
[8] |
| 2020-03-11 | O
Eberle, J Büttner, F Kräutli, KR Müller, M Valleriani, G Montavon.
Building and Interpreting Deep Similarity Models [9] |
| 2019-05-18 | J Kauffmann, M Esders,
G Montavon, W Samek, KR Müller. From Clustering to Cluster
Explanations via Neural Networks [10] |
| 2019 | W
Samek, G Montavon, A Vedaldi, LK Hansen, KR Müller (Eds.) Explainable
AI: Interpreting, Explaining and Visualizing Deep Learning [11],
Springer LNCS 11700 |
| 2012 | G Montavon, G Orr, KR Müller
(Eds.) Neural Networks: Tricks of the Trade, 2nd Edn [12], Springer
LNCS 7700 |
| 2019 | G Montavon, A Binder, S
Lapuschkin, W Samek, KR Müller. Layer-Wise Relevance Propagation: An
Overview [13] in Explainable AI: Interpreting, Explaining and
Visualizing Deep Learning, Springer LNCS 11700 |
| 2019 | L Arras, J Arjona, M Widrich, G
Montavon, M Gillhofer, KR Müller, S Hochreiter, W Samek. Explaining
and Interpreting LSTMs [14] in Explainable AI: Interpreting,
Explaining and Visualizing Deep Learning, Springer LNCS
11700 |
| 2019 | G
Montavon. Gradient-Based Vs. Propagation-Based Explanations: An
Axiomatic Comparison [15] in Explainable AI: Interpreting, Explaining
and Visualizing Deep Learning, Springer LNCS 11700 |
| 2019 | C Anders, G Montavon, W Samek, KR
Müller. Understanding Patch-Based Learning of Video Data by
Explaining Predictions [16] in Explainable AI: Interpreting,
Explaining and Visualizing Deep Learning, Springer LNCS
11700 |
| 2018 | L
Rieger, P Chormai, G Montavon, LK Hansen, KR Müller. Structuring
Neural Networks for More Explainable Predictions [17] in Explainable and Interpretable Models in Computer Vision and Machine Learning, pp 115-131, Springer SSCML |
| 2012 | G Montavon, KR Müller. Deep
Boltzmann Machines and the Centering Trick [18] in Neural Networks: Tricks of the Trade, 2nd Edn, pp 621-637, Springer LNCS, vol. 7700 |
| 2020 | S Agarwal, N Tosi, D Breuer, S
Padovan, P Kessel, G Montavon.A machine-learning-based surrogate model
of Mars’ thermal evolution [19] Geophysical Journal International, ggaa234 |
| 2020 | P Baumeister, S Padovan, N Tosi,
G Montavon, N Nettelmann, J MacKenzie, M Godolt.Machine learning
inference of the interior structure of low-mass exoplanets [20] The Astrophysical Journal, 118(1):42 |
| 2020 | J Kauffmann, KR Müller, G
Montavon. Towards Explaining Anomalies: A Deep Taylor Decomposition of
One-Class Models [21] Pattern Recognition, 107198 |
| 2019 | P
Jurmeister, M Bockmayr, P Seegerer, T Bockmayr,D Treue, G Montavon, C
Vollbrecht, A Arnold, D Teichmann, K Bressem, U Schüller, Mv Laffert,
KR Müller, D Capper, F Klauschen Machine learning analysis of DNA methylation profiles distinguishes primary lung squamous cell carcinomas from head and neck metastases [22] Science Translational Medicine 11(509):eaaw8513 |
| 2019 | S Lapuschkin, S Wäldchen, A
Binder, G Montavon, W Samek, KR Müller. Unmasking Clever Hans
Predictors and Assessing What Machines Really Learn [23] Nature Communications 10:1096 |
| 2018 | D Heim, G Montavon, P Hufnagl, KR
Müller, F Klauschen. Computational analysis reveals
histotype-dependent molecular profile and actionable mutation effects
across cancers [24] Genome Medicine, 10:83 |
| 2018 | G Montavon, W Samek, KR Müller.
Methods for Interpreting and Understanding Deep Neural Networks
[25] Digital Signal Processing, 73:1-15 |
| 2017 | L Arras, F Horn, G Montavon, KR
Müller, W Samek. "What is Relevant in a Text Document?": An
Interpretable Machine Learning Approach [26] PLOS ONE, 12(8):e0181142 |
| 2017 | G Montavon, S Lapuschkin, A
Binder, W Samek, KR Müller. Explaining NonLinear Classification
Decisions with Deep Taylor Decomposition [27] Pattern Recognition, 65:211–222 |
| 2016 | W Samek, A Binder, G Montavon, S
Lapuschkin, KR Müller. Evaluating the Visualization of What a Deep
Neural Network has Learned [28] IEEE Transactions on Neural Networks and Learning Systems, 28(11):2660-2673 |
| 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
[29] PLOS ONE, 10(7):e0130140 |
| 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 [30] New Journal of Physics, 15 095003 |
| 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
[31] Journal of Chemical Theory and Computation, 9(8):3404-3419 |
| 2013 | G Montavon, M Braun, T Krueger,
KR Müller. Analyzing Local Structure in Kernel-based Learning:
Explanation, Complexity and Reliability Assessment [32] IEEE Signal Processing Magazine, 30(4):62-74 |
| 2011 | G Montavon, M Braun, KR Müller.
Kernel Analysis of Deep Networks [33] Journal of Machine Learning Research, 12:2563-2581 |
| 2016 | G Montavon, KR Müller, M Cuturi.
Wasserstein Training of Restricted Boltzmann Machines [34] Advances in Neural Information Processing Systems (NIPS) (code [35]) |
| 2016 | F
Arbabzadah, G Montavon, KR Müller, W Samek. Identifying Individual
Facial Expressions by Deconstructing a Neural Network [36] 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 [37] 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 [38] 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 [39] 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 [40] Advances in Neural Information Processing Systems (NIPS) |
| 2012 | G
Montavon, M Braun, KR Müller. Deep Boltzmann Machines as Feed-Forward
Hierarchies [41] International Conference on Artificial Intelligence and Statistics (AISTATS) |
| 2010 | G Montavon, M Braun, KR Müller.
Layer-Wise Analysis of Deep Networks with Gaussian Kernels [42] Advances in Neural Information Processing Systems (NIPS) |
| 2019 | M Alber, S Lapuschkin, P
Seegerer, M Hägele, KT Schütt, G Montavon, W Samek, KR Müller, S
Dähne, PJ Kindermans. iNNvestigate neural networks! [43] Journal of Machine Learning Research, Software Track (JMLR/MLOSS) |
| 2017 | L Arras, G Montavon, KR Müller,
W Samek. Explaining Recurrent Neural Network Predictions in Sentiment
Analysis [44] 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 [45] 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 [46] ACL Workshop on Representation Learning for NLP |
| 2016 | G
Montavon, S Bach, A Binder, W Samek, KR Müller. Deep Taylor
Decomposition of Neural Networks [47] ICML Workshop on Visualization for Deep Learning |
| 2016 | A Binder, W Samek, G Montavon, S
Bach, KR Müller. Analyzing and Validating Neural Networks Predictions
[48] 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 [49] Journal of Machine Learning Research, Software Track (JMLR/MLOSS) |
| 2013 | G Montavon, KR Müller. Neural
Networks for Computational Chemistry: Pitfalls and Recommendations
[50] MRS Online Proceedings Library |
| 2009 | G Montavon. Deep Learning for
Spoken Language Identification [51] NIPS Workshop on Deep Learning for Speech Recognition and Related Applications |
| 2013 | G Montavon. On Layer-Wise
Representations in Deep Neural Networks [52] PhD Thesis, Technische Universität Berlin, Germany |
| 2009 | G Montavon. A Machine Learning
Approach to Classification of Low Resolution Histological Samples
[53] Master Thesis, École Polytechnique Fédérale de Lausanne, Switzerland |
| 2018-06-29 | J Kauffmann, G Montavon,
LA Lima, S Nakajima, KR Müller, N Görnitz.Unsupervised Detection and
Explanation of Latent-class Contextual Anomalies
[54] |
| 2017-07-17 | F
Horn, L Arras, G Montavon, KR Müller, W Samek. Exploring text
datasets by visualizing relevant words [55] |
parameter/en/id/66940/?no_cache=1&ask_mail=XzRaAAAC
TmpTb6COD9N7k%2Fl32Wwm1zyw1SbAL6KbqaRKzEA1FqhymA%3D%3D&
amp;ask_name=GREGOIRE%20MONTAVON
ellesLernen1
8954-6
-35289-8
0-28954-6_10
0-28954-6_11
0-28954-6_13
0-28954-6_16
42-35289-8_33
tml
ning-of-restricted-boltzmann-machines
nt-representations-of-molecules-for-atomization-energy-
prediction
montavon12.pdf
is-of-deep-networks-with-gaussian-kernels
ct?fromPage=online&aid=8841670
epspeech.pdf
x/index/docId/4467
thesis.pdf
Zusatzinformationen / Extras
Quick Access:
Schnellnavigation zur Seite über Nummerneingabe
Auxiliary Functions
Copyright TU Berlin 2008