Publications | Max Planck Institute for Intelligent Systems

Predicting the behavior of complex systems is of great importance in many fields such as engineering, economics or meteorology. The evolution of such systems often follows a certain structure, which can be induced, for example from the laws of physics or of market forces. Mathematically, this structure is often captured by differential equations. The internal functional dependencies, however, are usually unknown. Hence, using machine learning approaches that recreate this structure directly from data is a promising alternative to designing physics-based models. In particular, for high dimensional systems with nonlinear effects, this can be a challenging task. Learning dynamical systems is different from the classical machine learning tasks, such as image processing, and necessitates different tools. Indeed, dynamical systems can be actuated, often by applying torques or voltages. Hence, the user has a power of decision over the system, and can drive it to certain states by going through the dynamics. Actuating this system generates data, from which a machine learning model of the dynamics can be trained. However, gathering informative data that is representative of the whole state space remains a challenging task. The question of active learning then becomes important: which control inputs should be chosen by the user so that the data generated during an experiment is informative, and enables efficient training of the dynamics model? In this context, Gaussian processes can be a useful framework for approximating system dynamics. Indeed, they perform well on small and medium sized data sets, as opposed to most other machine learning frameworks. This is particularly important considering data is often costly to generate and process, most of all when producing it involves actuating a complex physical system. Gaussian processes also yield a notion of uncertainty, which indicates how sure the model is about its predictions. In this work, we investigate in a principled way how to actively learn dynamical systems, by selecting control inputs that generate informative data. We model the system dynamics by a Gaussian process, and use information-theoretic criteria to identify control trajectories that maximize the information gain. Thus, the input space can be explored efficiently, leading to a data-efficient training of the model. We propose several methods, investigate their theoretical properties and compare them extensively in a numerical benchmark. The final method proves to be efficient at generating informative data. Thus, it yields the lowest prediction error with the same amount of samples on most benchmark systems. We propose several variants of this method, allowing the user to trade off computations with prediction accuracy, and show it is versatile enough to take additional objectives into account.

ics

[BibTex]

ics Buisson-Fenet, M. Actively Learning Dynamical Systems with Gaussian Processes Mines ParisTech, PSL Research University, 2019 (mastersthesis)

[BibTex]

2017

Human Shape Estimation using Statistical Body Models

Loper, M. M.

University of Tübingen, May 2017 (thesis)

Abstract

Human body estimation methods transform real-world observations into predictions about human body state. These estimation methods benefit a variety of health, entertainment, clothing, and ergonomics applications. State may include pose, overall body shape, and appearance. Body state estimation is underconstrained by observations; ambiguity presents itself both in the form of missing data within observations, and also in the form of unknown correspondences between observations. We address this challenge with the use of a statistical body model: a data-driven virtual human. This helps resolve ambiguity in two ways. First, it fills in missing data, meaning that incomplete observations still result in complete shape estimates. Second, the model provides a statistically-motivated penalty for unlikely states, which enables more plausible body shape estimates. Body state inference requires more than a body model; we therefore build obser- vation models whose output is compared with real observations. In this thesis, body state is estimated from three types of observations: 3D motion capture markers, depth and color images, and high-resolution 3D scans. In each case, a forward process is proposed which simulates observations. By comparing observations to the results of the forward process, state can be adjusted to minimize the difference between simulated and observed data. We use gradient-based methods because they are critical to the precise estimation of state with a large number of parameters. The contributions of this work include three parts. First, we propose a method for the estimation of body shape, nonrigid deformation, and pose from 3D markers. Second, we present a concise approach to differentiating through the rendering process, with application to body shape estimation. And finally, we present a statistical body model trained from human body scans, with state-of-the-art fidelity, good runtime performance, and compatibility with existing animation packages.

Official Version [BibTex]

2017

ps Loper, M. M. Human Shape Estimation using Statistical Body Models University of Tübingen, May 2017 (thesis)

Official Version [BibTex]

Nonparametric Disturbance Correction and Nonlinear Dual Control

Klenske, E. D.

(24098), ETH Zurich, 2017 (phdthesis)

ei pn sf

DOI [BibTex]

ei pn sf Klenske, E. D. Nonparametric Disturbance Correction and Nonlinear Dual Control (24098), ETH Zurich, 2017 (phdthesis)

DOI [BibTex]

Learning Inference Models for Computer Vision

Jampani, V.

MPI for Intelligent Systems and University of Tübingen, 2017 (phdthesis)

Abstract

Computer vision can be understood as the ability to perform 'inference' on image data. Breakthroughs in computer vision technology are often marked by advances in inference techniques, as even the model design is often dictated by the complexity of inference in them. This thesis proposes learning based inference schemes and demonstrates applications in computer vision. We propose techniques for inference in both generative and discriminative computer vision models. Despite their intuitive appeal, the use of generative models in vision is hampered by the difficulty of posterior inference, which is often too complex or too slow to be practical. We propose techniques for improving inference in two widely used techniques: Markov Chain Monte Carlo (MCMC) sampling and message-passing inference. Our inference strategy is to learn separate discriminative models that assist Bayesian inference in a generative model. Experiments on a range of generative vision models show that the proposed techniques accelerate the inference process and/or converge to better solutions. A main complication in the design of discriminative models is the inclusion of prior knowledge in a principled way. For better inference in discriminative models, we propose techniques that modify the original model itself, as inference is simple evaluation of the model. We concentrate on convolutional neural network (CNN) models and propose a generalization of standard spatial convolutions, which are the basic building blocks of CNN architectures, to bilateral convolutions. First, we generalize the existing use of bilateral filters and then propose new neural network architectures with learnable bilateral filters, which we call `Bilateral Neural Networks'. We show how the bilateral filtering modules can be used for modifying existing CNN architectures for better image segmentation and propose a neural network approach for temporal information propagation in videos. Experiments demonstrate the potential of the proposed bilateral networks on a wide range of vision tasks and datasets. In summary, we propose learning based techniques for better inference in several computer vision models ranging from inverse graphics to freely parameterized neural networks. In generative vision models, our inference techniques alleviate some of the crucial hurdles in Bayesian posterior inference, paving new ways for the use of model based machine learning in vision. In discriminative CNN models, the proposed filter generalizations aid in the design of new neural network architectures that can handle sparse high-dimensional data as well as provide a way for incorporating prior knowledge into CNNs.

pdf [BibTex]

ps Jampani, V. Learning Inference Models for Computer Vision MPI for Intelligent Systems and University of Tübingen, 2017 (phdthesis)

pdf [BibTex]

Development and Evaluation of a Portable BCI System for Remote Data Acquisition

Emde, T.

Graduate School of Neural Information Processing, Eberhard Karls Universität Tübingen, Germany, 2017 (mastersthesis)

[BibTex]

ei Emde, T. Development and Evaluation of a Portable BCI System for Remote Data Acquisition Graduate School of Neural Information Processing, Eberhard Karls Universität Tübingen, Germany, 2017 (mastersthesis)

[BibTex]

Brain-Computer Interfaces for patients with Amyotrophic Lateral Sclerosis

Fomina, T.

Eberhard Karls Universität Tübingen, Germany, 2017 (phdthesis)

[BibTex]

ei Fomina, T. Brain-Computer Interfaces for patients with Amyotrophic Lateral Sclerosis Eberhard Karls Universität Tübingen, Germany, 2017 (phdthesis)

[BibTex]

Causal models for decision making via integrative inference

Geiger, P.

University of Stuttgart, Germany, 2017 (phdthesis)

[BibTex]

ei Geiger, P. Causal models for decision making via integrative inference University of Stuttgart, Germany, 2017 (phdthesis)

[BibTex]

Capturing Hand-Object Interaction and Reconstruction of Manipulated Objects

Tzionas, D.

University of Bonn, 2017 (phdthesis)

Abstract

Hand motion capture with an RGB-D sensor gained recently a lot of research attention, however, even most recent approaches focus on the case of a single isolated hand. We focus instead on hands that interact with other hands or with a rigid or articulated object. Our framework successfully captures motion in such scenarios by combining a generative model with discriminatively trained salient points, collision detection and physics simulation to achieve a low tracking error with physically plausible poses. All components are unified in a single objective function that can be optimized with standard optimization techniques. We initially assume a-priori knowledge of the object's shape and skeleton. In case of unknown object shape there are existing 3d reconstruction methods that capitalize on distinctive geometric or texture features. These methods though fail for textureless and highly symmetric objects like household articles, mechanical parts or toys. We show that extracting 3d hand motion for in-hand scanning effectively facilitates the reconstruction of such objects and we fuse the rich additional information of hands into a 3d reconstruction pipeline. Finally, although shape reconstruction is enough for rigid objects, there is a lack of tools that build rigged models of articulated objects that deform realistically using RGB-D data. We propose a method that creates a fully rigged model consisting of a watertight mesh, embedded skeleton and skinning weights by employing a combination of deformable mesh tracking, motion segmentation based on spectral clustering and skeletonization based on mean curvature flow.

Thesis link (url) Project Page [BibTex]

ps Tzionas, D. Capturing Hand-Object Interaction and Reconstruction of Manipulated Objects University of Bonn, 2017 (phdthesis)

Thesis link (url) Project Page [BibTex]

Evaluation of the passive dynamics of compliant legs with inertia

Györfi, B.

University of Applied Science Pforzheim, Germany, 2017 (mastersthesis)

dlg

[BibTex]

dlg Györfi, B. Evaluation of the passive dynamics of compliant legs with inertia University of Applied Science Pforzheim, Germany, 2017 (mastersthesis)

[BibTex]

Learning Optimal Configurations for Modeling Frowning by Transcranial Electrical Stimulation

Sücker, K.

Graduate School of Neural Information Processing, Eberhard Karls Universität Tübingen, Germany, 2017 (mastersthesis)

[BibTex]

ei Sücker, K. Learning Optimal Configurations for Modeling Frowning by Transcranial Electrical Stimulation Graduate School of Neural Information Processing, Eberhard Karls Universität Tübingen, Germany, 2017 (mastersthesis)

[BibTex]

Understanding FORC using synthetic micro-structured systems with variable coupling- and coercivefield distributions

Groß, Felix

Universität Stuttgart, Stuttgart, 2017 (mastersthesis)

mms

[BibTex]

mms Groß, Felix Understanding FORC using synthetic micro-structured systems with variable coupling- and coercivefield distributions Universität Stuttgart, Stuttgart, 2017 (mastersthesis)

[BibTex]

Using FORC to understand the microstructure-micromagnetism relationship in supermagnets

Ilse, S. E.

Universität Stuttgart, Stuttgart, 2017 (mastersthesis)

mms

[BibTex]

mms Ilse, S. E. Using FORC to understand the microstructure-micromagnetism relationship in supermagnets Universität Stuttgart, Stuttgart, 2017 (mastersthesis)

[BibTex]

Adsorption von Wasserstoffmolekülen in nanoporösen Gerüststrukturen

Kotzur, Nadine

Universität Stuttgart, Stuttgart, 2017 (mastersthesis)

mms

[BibTex]

mms Kotzur, Nadine Adsorption von Wasserstoffmolekülen in nanoporösen Gerüststrukturen Universität Stuttgart, Stuttgart, 2017 (mastersthesis)

[BibTex]

Tailored magnetic properties of exchange-spring and ultra hard nanomagnets

Son, K.

Universität Stuttgart, Stuttgart, 2017 (phdthesis)

mms

link (url) [BibTex]

mms Son, K. Tailored magnetic properties of exchange-spring and ultra hard nanomagnets Universität Stuttgart, Stuttgart, 2017 (phdthesis)

link (url) [BibTex]

Voltage induced near interface changes of the magnetocrystalline anisotropy energy: A study by X-ray resonant techniques in combination with conventional magnetometry

Boltje, D.

Universität Stuttgart, Stuttgart, 2017 (mastersthesis)

mms

[BibTex]

mms Boltje, D. Voltage induced near interface changes of the magnetocrystalline anisotropy energy: A study by X-ray resonant techniques in combination with conventional magnetometry Universität Stuttgart, Stuttgart, 2017 (mastersthesis)

[BibTex]

2013

Camera-specific Image Denoising

Schober, M.

Eberhard Karls Universität Tübingen, Germany, October 2013 (diplomathesis)

ei pn

PDF [BibTex]

2013

ei pn Schober, M. Camera-specific Image Denoising Eberhard Karls Universität Tübingen, Germany, October 2013 (diplomathesis)

PDF [BibTex]

Statistics on Manifolds with Applications to Modeling Shape Deformations

Freifeld, O.

Brown University, August 2013 (phdthesis)

Abstract

Statistical models of non-rigid deformable shape have wide application in many fields, including computer vision, computer graphics, and biometry. We show that shape deformations are well represented through nonlinear manifolds that are also matrix Lie groups. These pattern-theoretic representations lead to several advantages over other alternatives, including a principled measure of shape dissimilarity and a natural way to compose deformations. Moreover, they enable building models using statistics on manifolds. Consequently, such models are superior to those based on Euclidean representations. We demonstrate this by modeling 2D and 3D human body shape. Shape deformations are only one example of manifold-valued data. More generally, in many computer-vision and machine-learning problems, nonlinear manifold representations arise naturally and provide a powerful alternative to Euclidean representations. Statistics is traditionally concerned with data in a Euclidean space, relying on the linear structure and the distances associated with such a space; this renders it inappropriate for nonlinear spaces. Statistics can, however, be generalized to nonlinear manifolds. Moreover, by respecting the underlying geometry, the statistical models result in not only more effective analysis but also consistent synthesis. We go beyond previous work on statistics on manifolds by showing how, even on these curved spaces, problems related to modeling a class from scarce data can be dealt with by leveraging information from related classes residing in different regions of the space. We show the usefulness of our approach with 3D shape deformations. To summarize our main contributions: 1) We define a new 2D articulated model -- more expressive than traditional ones -- of deformable human shape that factors body-shape, pose, and camera variations. Its high realism is obtained from training data generated from a detailed 3D model. 2) We define a new manifold-based representation of 3D shape deformations that yields statistical deformable-template models that are better than the current state-of-the- art. 3) We generalize a transfer learning idea from Euclidean spaces to Riemannian manifolds. This work demonstrates the value of modeling manifold-valued data and their statistics explicitly on the manifold. Specifically, the methods here provide new tools for shape analysis.

pdf Project Page [BibTex]

ps Freifeld, O. Statistics on Manifolds with Applications to Modeling Shape Deformations Brown University, August 2013 (phdthesis)

pdf Project Page [BibTex]

Modelling and Learning Approaches to Image Denoising

Burger, HC.

Eberhard Karls Universität Tübingen, Germany, 2013 (phdthesis)

[BibTex]

ei Burger, HC. Modelling and Learning Approaches to Image Denoising Eberhard Karls Universität Tübingen, Germany, 2013 (phdthesis)

[BibTex]

Linear mixed models for genome-wide association studies

Lippert, C.

University of Tübingen, Germany, 2013 (phdthesis)

[BibTex]

ei Lippert, C. Linear mixed models for genome-wide association studies University of Tübingen, Germany, 2013 (phdthesis)

[BibTex]

Leveraging Weak Supervision for Video Understanding

Garcia Cifuentes, C.

University College London, 2013 (phdthesis)

link (url) [BibTex]

Garcia Cifuentes, C. Leveraging Weak Supervision for Video Understanding University College London, 2013 (phdthesis)

link (url) [BibTex]

Modeling and Learning Complex Motor Tasks: A case study on Robot Table Tennis

Mülling, K.

Technical University Darmstadt, Germany, 2013 (phdthesis)

[BibTex]

ei Mülling, K. Modeling and Learning Complex Motor Tasks: A case study on Robot Table Tennis Technical University Darmstadt, Germany, 2013 (phdthesis)

[BibTex]

Intention Inference and Decision Making with Hierarchical Gaussian Process Dynamics Models

Wang, Z.

Technical University Darmstadt, Germany, 2013 (phdthesis)

[BibTex]

ei Wang, Z. Intention Inference and Decision Making with Hierarchical Gaussian Process Dynamics Models Technical University Darmstadt, Germany, 2013 (phdthesis)

[BibTex]

Quantum kinetic theory for demagnetization after femtosecond laser pulses

Teeny, N.

Universität Stuttgart, Stuttgart, 2013 (mastersthesis)

mms

[BibTex]

mms Teeny, N. Quantum kinetic theory for demagnetization after femtosecond laser pulses Universität Stuttgart, Stuttgart, 2013 (mastersthesis)

[BibTex]

Ab-initio modeling of ultrafast demagnetization after laser irradiation in nickel, iron and cobalt

Illg, C.

Universität Stuttgart, Stuttgart, 2013 (phdthesis)

mms

link (url) [BibTex]

mms Illg, C. Ab-initio modeling of ultrafast demagnetization after laser irradiation in nickel, iron and cobalt Universität Stuttgart, Stuttgart, 2013 (phdthesis)

link (url) [BibTex]

2003

Real-Time Face Detection

Kienzle, W.

Biologische Kybernetik, Eberhard-Karls-Universitaet Tuebingen, Tuebingen, Germany, October 2003 (diplomathesis)

[BibTex]

2003

ei Kienzle, W. Real-Time Face Detection Biologische Kybernetik, Eberhard-Karls-Universitaet Tuebingen, Tuebingen, Germany, October 2003 (diplomathesis)

[BibTex]

m-Alternative Forced Choice—Improving the Efficiency of the Method of Constant Stimuli

Jäkel, F.

Biologische Kybernetik, Graduate School for Neural and Behavioural Sciences, Tübingen, 2003 (diplomathesis)

[BibTex]

ei Jäkel, F. m-Alternative Forced Choice—Improving the Efficiency of the Method of Constant Stimuli Biologische Kybernetik, Graduate School for Neural and Behavioural Sciences, Tübingen, 2003 (diplomathesis)

[BibTex]

Ab-initio Clusterentwicklung zur Untersuchung der Stabilität monoatomarer magnetischer Ketten auf glatten Kristalloberflächen

Singer, R.

Universität Stuttgart, Stuttgart, 2003 (mastersthesis)

mms

[BibTex]

mms Singer, R. Ab-initio Clusterentwicklung zur Untersuchung der Stabilität monoatomarer magnetischer Ketten auf glatten Kristalloberflächen Universität Stuttgart, Stuttgart, 2003 (mastersthesis)

[BibTex]

Theorie magneto-optischer Effekte im Röntgenbereich und Anwendung auf niedrigdimensionale magnetische Systeme

Ederer, C.

Universität Stuttgart, Stuttgart, 2003 (phdthesis)

mms

link (url) [BibTex]

mms Ederer, C. Theorie magneto-optischer Effekte im Röntgenbereich und Anwendung auf niedrigdimensionale magnetische Systeme Universität Stuttgart, Stuttgart, 2003 (phdthesis)

link (url) [BibTex]

Ab-initio statistical mechanics for ordering and segregation at the (110) surface of Ni90\textpercent-Al

Drautz, R.

Universität Stuttgart, Stuttgart, 2003 (phdthesis)

mms

link (url) [BibTex]

mms Drautz, R. Ab-initio statistical mechanics for ordering and segregation at the (110) surface of Ni90\textpercent-Al Universität Stuttgart, Stuttgart, 2003 (phdthesis)

link (url) [BibTex]

Untersuchung zur Fremdatomsegregation und zum Vorbenetzungsphasenübergang an Korngrenzen in Cu Poly- und Bikristallen durch Messungen der Korngrenzendiffusion

Lohmann, M.

Westfälische Wilhems-Universität Münster, Münster, 2003 (phdthesis)

mms

[BibTex]

mms Lohmann, M. Untersuchung zur Fremdatomsegregation und zum Vorbenetzungsphasenübergang an Korngrenzen in Cu Poly- und Bikristallen durch Messungen der Korngrenzendiffusion Westfälische Wilhems-Universität Münster, Münster, 2003 (phdthesis)

[BibTex]

Magnetische Streuung an Grenz- und Viellagenschichten

Geissler, J.

Bayerische Julius-Maximilians-Universität Würzburg, Würzburg, 2003 (phdthesis)

mms

[BibTex]

mms Geissler, J. Magnetische Streuung an Grenz- und Viellagenschichten Bayerische Julius-Maximilians-Universität Würzburg, Würzburg, 2003 (phdthesis)

[BibTex]

Elektronentheorie der Dissipation bei ultraschneller Spindynamik

Steiauf, D.

Universität Stuttgart, Stuttgart, 2003 (mastersthesis)

mms

[BibTex]

mms Steiauf, D. Elektronentheorie der Dissipation bei ultraschneller Spindynamik Universität Stuttgart, Stuttgart, 2003 (mastersthesis)

[BibTex]

XANES und MEXAFS an magnetischen Übergangsmetalloxiden: Entwicklung eines digitalen Lock-In XMCD Experimentes mit Phasenschieber

Weigand, F.

Bayerische Julius-Maximilians-Universität Würzburg, Würzburg, 2003 (phdthesis)

mms

[BibTex]

mms Weigand, F. XANES und MEXAFS an magnetischen Übergangsmetalloxiden: Entwicklung eines digitalen Lock-In XMCD Experimentes mit Phasenschieber Bayerische Julius-Maximilians-Universität Würzburg, Würzburg, 2003 (phdthesis)

[BibTex]

Untersuchungen zur mikroskopischen Ursache der magnetokristallinen Anisotropie mit Hilfe des magnetischen Röntgenzirkulardichroismus und der resonanten magnetischen Röntgenreflektometrie

Goering, E.

Bayerische Julius-Maximilians-Universität Würzburg, Würzburg, 2003 (phdthesis)

mms

[BibTex]

mms Goering, E. Untersuchungen zur mikroskopischen Ursache der magnetokristallinen Anisotropie mit Hilfe des magnetischen Röntgenzirkulardichroismus und der resonanten magnetischen Röntgenreflektometrie Bayerische Julius-Maximilians-Universität Würzburg, Würzburg, 2003 (phdthesis)

[BibTex]

Theorie der Spinstrukturen dünner Seitenerdmetall-Schichten: Ab-initio Berechnung von Kristallfeldparametern an Oberflächen und thermodynamische Störungstheorie

Welsch, F.

Universität Stuttgart, Stuttgart, 2003 (phdthesis)

mms

[BibTex]

mms Welsch, F. Theorie der Spinstrukturen dünner Seitenerdmetall-Schichten: Ab-initio Berechnung von Kristallfeldparametern an Oberflächen und thermodynamische Störungstheorie Universität Stuttgart, Stuttgart, 2003 (phdthesis)

[BibTex]

2001

Variationsverfahren zur Untersuchung von Grundzustandseigenschaften des Ein-Band Hubbard-Modells

Eichhorn, J.

Biologische Kybernetik, Technische Universität Dresden, Dresden/Germany, May 2001 (diplomathesis)

Abstract

Using different modifications of a new variational approach, statical groundstate properties of the one-band Hubbard model such as energy and staggered magnetisation are calculated. By taking into account additional fluctuations, the method ist gradually improved so that a very good description of the energy in one and two dimensions can be achieved. After a detailed discussion of the application in one dimension, extensions for two dimensions are introduced. By use of a modified version of the variational ansatz in particular a description of the quantum phase transition for the magnetisation should be possible.

PostScript [BibTex]