Toward Explainable AI and Applications
Klaus- ̈ller !!et al.!!
Towards Explaining:
Copyright By PowCoder代写 加微信 powcoder
Machine Learning = black box?
Interpreting with class prototypes
Examples of Class Prototypes
Building more natural prototypes
Montavon, Samek, Müller arxiv 2017
Building Prototypes using a generator
Building Prototypes using a generator
Types of Interpretation
Approaches to interpretability
Explaining single Predictions Pixel-wise
Goodbye Blackbox ML!
[Bach, Binder, Klauschen, Montavon, Müller & Samek, PLOS ONE 2015, Montavon et al Pattern Recognition 2017]
Explaining nonlinear decisions is difficult
Explaining single decisions is difficult
Explaining Neural Network Predictions
Layer-wise relevance Propagation (LRP, Bach et al 15) first method to explain nonlinear classifiers
– based on generic theory (related to Taylor decomposition – deep taylor decomposition M et al 17) – applicable to any NN with monotonous activation, BoW models, Fisher Vectors, SVMs etc.
Explanation: “Which pixels contribute how much to the classification” (Bach et al 2015) (what makes this image to be classified as a car)
Sensitivity / Saliency: “Which pixels lead to increase/decrease of prediction score when changed” (what makes this image to be classified more/less as a car) (Baehrens et al 10, Simonyan et al 14)
Deconvolution: “Matching input pattern for the classified object in the image” (Zeiler & Fergus 2014) (relation to f(x) not specified)
Each method solves a different problem!!!
Explaining Neural Network Predictions
Classification
large activation
ladybug dog
Explaining Neural Network Predictions
Explanation
ladybug dog
Initialization
Explaining Neural Network Predictions
Explanation
ladybug dog
Theoretical interpretation
Deep Taylor Decomposition
depends on the activations and the weights
Explaining Neural Network Predictions
Explanation
large relevance
ladybug dog
Relevance Conservation Property
Best Practice for LRP
Explaining Predictions Pixel-wise
Neural networks
Kernel methods
Some Digestion on Explaining
Sensitivity analysis is often not the question that you would like to ask!
LRP can ‘say’ positive and negative things
Positive and Negative Evidence: LRP distinguishes between positive evidence, supporting the classification decision, and negative evidence, speaking against the prediction
LRP indicates what speaks for class ‘3’ and speaks against class ‘9’
Measuring the Quality of Explanation (Samek et al 2015)
Is this a good explanation ?
Sort pixel scores
flip pixels
evaluate f(x)
Measure decrease of f(x)
Measuring the Quality of Explanation
LRP outperforms Sensitivity and Deconvolution on all three datasets.
Application: Comparing Classifiers
Image Fisher Vector DNN
Large values indicate importance of context
Unmasking Clever
Is the Generalization Error all we need?
Application: Comparing Classifiers (Lapuschkin et al CVPR 2016)
Explaining problem solving strategies in scale
© 2018 für • All Rights Reserved
Spectral Relevance
Analysis (SpRAy)
Lapuschkin et al. Nat Comms, March 11th 2019
Application: Faces
What makes you look sad ?
What makes you look old ?
What makes
you look attractive ?
Application: Document Classification
Application: Understand the model
– reimplement model of (Santoro et al., 2017)
– test accuracy of 91,0% – CLEVR dataset
model understands the question and correctly identifies the object of interest
(Arras et al., 2018)
Understanding learning models for complex gaming scenarios
Analysing Breakout: LRP vs. Sensitivity
sensitivity
XAI for unsupervised learning
Anomaly Detection
Support Vector Data description
Explaining one-class
[Kaufmann, Müller, Montavon 2018, 2019]
Clustering
Neon: Neuralization Propagation
Neuralizing k-means
K-means on VGG-16 Features
Gaining insights
Toward Quantum Chemical Insight
[Schütt et al. Nat Comm. 2017, Schütt et al JCP 2018]
Machine Learning for morpho-molecular Integration
Interpretable ML
Bach et al., PLoS1 2015
Klauschen et al., US Patent #9558550 Klauschen et al., Sem Cancer Biol 2018 Binder et al., in revision
Machine learning based integration of morphological and molecular tumor profiles
MICROSCOPIC AND MOLECUAR DATA
PREDICTION
INTEGRATION/ INTERPRETATION
red: carcinoma,
green: TILs,
blue: molecular property
in-house data base
„novel insight“
TCGA data base
molecular features
Heterogenity of E-Cadherin-Expression
Morphology ML-Prediction: Validation: IHC
Binder et al., in revision.
Semi-final Conclusion
• explaining & interpreting nonlinear models is essential
• orthogonal to improving DNNs and other models
• need for opening the blackbox …
• understanding nonlinear models is essential for Sciences & AI • new theory: LRP is based on deep taylor expansion
• tool for gaining insight
www.heatmapping.org
Thank you for your attention
Tutorial Paper
Montavon et al., “Methods for interpreting and understanding deep neural networks”, Digital Signal Processing, 73:1-5, 2018
Samek, W., Montavon, G., Lapuschkin, S., Anders, C.J. and Müller, K.R., 2021. Explaining deep neural networks and beyond: A review of methods and applications. Proc of the IEEE, 109(3), pp.247-278.
: Samek, Montavon, Vedaldi, Hansen, Müller (eds.), Explainable AI: Interpreting, Explaining and Visualizing Deep Learning. LNAI 11700, Springer (2019)
Keras Explanation Toolbox
https://github.com/albermax/innvestigate
Further Reading I
Alber, M., Lapuschkin, S., Seegerer, P., Hägele, M., Schütt, K.T., Montavon, G., Samek, W., Müller, K.R., Dähne, S. and Kindermans, P.J., 2019. iNNvestigate neural networks!. Journal of Machine Learning Research, 20(93), pp.1-8.
Bach, S., Binder, A., Montavon, G., Klauschen, F., Müller, K. R., & Samek, W. (2015). On pixel-wise explanations for non-linear classifier decisions by layer-wise relevance propagation. PloS one, 10, e0130140 (7).
Baehrens, D., Schroeter, T., Harmeling, S., Kawanabe, M., Hansen, K., & Müller, K. R. (2010). How to explain individual classification decisions. The Journal of Machine Learning Research, 11, 1803-1831.
Binder et al. (2021). Machine Learning for morpho-molecular Integration, Nature Machine Intelligence, 3 (4), 355–366
Blankertz, B., Curio, G. and Müller, K.R., 2002. Classifying single trial EEG: Towards brain computer interfacing. In Advances in neural information processing systems (pp. 157-164).
Blankertz, B., Dornhege, G., Krauledat, M., Müller, K.R. and Curio, G., 2007. The non-invasive Berlin brain–computer interface: fast acquisition of effective performance in untrained subjects. NeuroImage, 37(2), pp.539-550.
Blankertz, B., Tomioka, R., Lemm, S., Kawanabe, M. and Muller, K.R., 2007. Optimizing spatial filters for robust EEG single-trial analysis. IEEE Signal processing magazine, 25(1), pp.41-56.
Blankertz, B., Lemm, S., Treder, M., Haufe, S. and Müller, K.R., 2011. Single-trial analysis and classification of ERP components—a tutorial. NeuroImage, 56(2), pp.814-825.
Blum, L. C., & Reymond, J. L. (2009). 970 million druglike small molecules for virtual screening in the chemical universe database GDB-13. Journal of the American Chemical Society, 131(25), 8732-8733.
Brockherde, F., Vogt, L., Li, L., Tuckerman, M.E., Burke, K. and Müller, K.R., 2017. Bypassing the Kohn- Sham equations with machine learning. Nature communications, 8(1), p.872.
Further Reading II
Chmiela, S., Tkatchenko, A., Sauceda, H. E., Poltavsky, I., Schütt, K. T., & Müller, K. R. (2017). Machine learning of accurate energy-conserving molecular force fields. Science Advances, 3(5), e1603015.
Chmiela, S., Sauceda, H.E., Müller, K.R. and Tkatchenko, A., 2018. Towards exact molecular dynamics simulations with machine-learned force fields. Nature communications, 9(1), p.3887.
Dornhege, G., Millan, J.D.R., Hinterberger, T., McFarland, D.J. and Müller, K.R. eds., 2007. Toward brain- computer interfacing. MIT press.
Hansen, K., Montavon, G., Biegler, F., Fazli, S., Rupp, M., Scheffler, M., von Lilienfeld, A.O., Tkatchenko, A., and Müller, K.-R. “Assessment and validation of machine learning methods for predicting molecular atomization energies.” Journal of Chemical Theory and Computation 9, no. 8 (2013): 3404-3419.
Hansen, K., Biegler, F., Ramakrishnan, R., Pronobis, W., von Lilienfeld, O. A., Müller, K. R., & Tkatchenko, A. (2015). Machine Learning Predictions of Molecular Properties: Accurate Many-Body Potentials and Nonlocality in Chemical Space, J. Phys. Chem. Lett. 6, 2326−2331.
Horst, F., Lapuschkin, S., Samek, W., Müller, K.R. and Schöllhorn, W.I., 2019. Explaining the unique nature of individual gait patterns with deep learning. Scientific reports, 9(1), p.2391.
Kauffmann, J., Müller, K.R. and Montavon, G., 2020. Towards explaining anomalies: A deep taylor decomposition of one-class models. Pattern Recognition, 101, p.107198.
Keith, J.A., Vassilev-Galindo, V., Cheng, B., Chmiela, S., Gastegger, M., Müller, K.R. and Tkatchenko, A., 2021. Combining machine learning and computational chemistry for predictive insights into chemical systems. Chemical Reviews.
Further Reading III
Klauschen, F., Müller, K.R., Binder, A., Bockmayr, M., Hägele, M., Seegerer, P., Wienert, S., Pruneri, G., de Maria, S., Badve, S. and Michiels, S., 2018, October. Scoring of tumor-infiltrating lymphocytes: From visual estimation to machine learning. Seminars in cancer biology (Vol. 52, pp. 151-157).
Lemm, S., Blankertz, B., Dickhaus, T. and Müller, K.R., 2011. Introduction to machine learning for brain imaging. Neuroimage, 56(2), pp.387-399.
Lapuschkin, S., Binder, A., Montavon, G., Müller, K.-R. & Samek, W. (2016). Analyzing Classifiers: Fisher Vectors and Deep Neural Networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2912-2920 (2016).
Lapuschkin, S., Wäldchen, S., Binder, A., Montavon, G., Samek, W. and Müller, K.R., 2019. Unmasking Clever Hans predictors and assessing what machines really learn. Nature communications, 10, p.1096.
von Lilienfeld, O.A., Müller, K.R. and Tkatchenko, A., 2020. Exploring chemical compound space with quantum- based machine learning. Nature Reviews Chemistry, 4(7), pp.347-358.
Müller, K. R., Mika, S., Rätsch, G., Tsuda, K., & Schölkopf, B. (2001). An introduction to kernel-based learning algorithms. IEEE Transactions on Neural Networks, 12(2), 181-201.
Montavon, G., Braun, M. L., & Müller, K. R. (2011). Kernel analysis of deep networks. The Journal of Machine Learning Research, 12, 2563-2581.
Montavon, Grégoire, Katja Hansen, , , , , , Anatole V. Lilienfeld, Klaus- ̈ller. “Learning invariant representations of molecules for atomization energy prediction. Advances in Neural Information Processing Systems, pp. 440-448 (2012).
Montavon, G., Orr, G. & Müller, K. R. (2012). Neural Networks: Tricks of the Trade, Springer LNCS 7700. Berlin Heidelberg.
Montavon, Grégoire, , , -Mayagoitia, Katja Hansen, , Klaus- ̈ller, and O. Anatole von Lilienfeld. “Machine learning of molecular electronic properties in chemical compound space.” of Physics 15, no. 9 (2013): 095003.
Further Reading IV
Montavon, G., Lapuschkin, S., Binder, A., Samek, W. and Müller, K.R., Explaining nonlinear classification decisions with deep taylor decomposition. Pattern Recognition, 65, 211-222 (2017)
Montavon, G., Samek, W., & Müller, K. R., Methods for interpreting and understanding deep neural networks, Digital Signal Processing, 73:1-5, (2018).
Rupp, M., Tkatchenko, A., Müller, K. R., & von Lilienfeld, O. A. (2012). Fast and accurate modeling of molecular atomization energies with machine learning. Physical review letters, 108(5), 058301.
K. T. Schütt, H. Glawe, F. Brockherde, A. Sanna, K. R. Müller, and E. K. U. Gross, How to represent crystal structures for machine learning: Towards fast prediction of electronic properties Phys. Rev. B 89, 205118 (2014)
K.T. Schütt, F Arbabzadah, S Chmiela, KR Müller, A Tkatchenko, Quantum-chemical insights from deep tensor neural networks, Nature Communications 8, 13890 (2017)
K.T. Schütt, H.E. Sauceda, , P.J. Kindermans, , A. Tkatchenko and K.R. Müller, SchNet–A deep learning architecture for molecules and materials. The Journal of Chemical Physics, 148(24), p.241722. (2018)
Samek, W., Binder, A., Montavon, G., Lapuschkin, S. and Müller, K.R., Evaluating the visualization of what a deep neural network has learned. IEEE transactions on neural networks and learning systems, 28(11), pp.2660- 2673 (2017)
Samek, W., Montavon, G., Vedaldi, A., Hansen, L.K., Müller, K.R. (eds.), Explainable AI: Interpreting, Explaining and Visualizing Deep Learning. LNAI 11700, Springer (2019)
Samek, W., Montavon, G., Lapuschkin, S., Anders, C.J. and Müller, K.R., 2021. Explaining deep neural networks and beyond: A review of methods and applications. Proceedings of the IEEE, 109(3), pp.247-278.
Unke, O.T., Chmiela, S., Sauceda, H.E., Gastegger, M., Poltavsky, I., Schütt, K.T., Tkatchenko, A. and Müller, K.R., 2021. Machine learning force fields. Chemical Reviews.
Unke, O.T., Chmiela, S., Gastegger, M., Schütt, K.T., Sauceda, H.E. and Müller, K.R., 2021. Spookynet: Learning force fields with electronic degrees of freedom and nonlocal effects. Nature Communications.
Won, D.O., Müller, K.R. and Lee, S.W., 2020. An adaptive deep reinforcement learning framework enables curling robots with human-like performance in real-world conditions. Science Robotics, 5(46) eabb9764
程序代写 CS代考 加微信: powcoder QQ: 1823890830 Email: powcoder@163.com