Publications | Max Planck Institute for Intelligent Systems

2019

ics Haksar, R., Solowjow, F., Trimpe, S., Schwager, M. Controlling Heterogeneous Stochastic Growth Processes on Lattices with Limited Resources In Proceedings of the 58th IEEE International Conference on Decision and Control (CDC) , 58th IEEE International Conference on Decision and Control (CDC), December 2019 (proceedings) Accepted

Fast and Resource-Efficient Control of Wireless Cyber-Physical Systems

Baumann, D.

KTH Royal Institute of Technology, Stockholm, Febuary 2019 (phdthesis)

ics

ics Baumann, D. Fast and Resource-Efficient Control of Wireless Cyber-Physical Systems KTH Royal Institute of Technology, Stockholm, Febuary 2019 (phdthesis)

Learning Transferable Representations

Rojas-Carulla, M.

University of Cambridge, UK, 2019 (phdthesis)

ei Rojas-Carulla, M. Learning Transferable Representations University of Cambridge, UK, 2019 (phdthesis)

Sample-efficient deep reinforcement learning for continuous control

Gu, S.

University of Cambridge, UK, 2019 (phdthesis)

ei Gu, S. Sample-efficient deep reinforcement learning for continuous control University of Cambridge, UK, 2019 (phdthesis)

Formally justified and modular Bayesian inference for probabilistic programs

Ścibior*, A.

University of Cambridge, UK, 2019 (phdthesis)

ei Ścibior*, A. Formally justified and modular Bayesian inference for probabilistic programs University of Cambridge, UK, 2019 (phdthesis)

Spatial Filtering based on Riemannian Manifold for Brain-Computer Interfacing

Xu, J.

Technical University of Munich, Germany, 2019 (mastersthesis)

ei Xu, J. Spatial Filtering based on Riemannian Manifold for Brain-Computer Interfacing Technical University of Munich, Germany, 2019 (mastersthesis)

Pragmatism and Variable Transformations in Causal Modelling

Weichwald, S.

ETH Zurich, 2019 (phdthesis)

ei Weichwald, S. Pragmatism and Variable Transformations in Causal Modelling ETH Zurich, 2019 (phdthesis)

Novel X-ray lenses for direct and coherent imaging

Sanli, U. T.

Universität Stuttgart, Stuttgart, 2019 (phdthesis)

mms

mms Sanli, U. T. Novel X-ray lenses for direct and coherent imaging Universität Stuttgart, Stuttgart, 2019 (phdthesis)

Quantification of tumor heterogeneity using PET/MRI and machine learning

Katiyar, P.

Eberhard Karls Universität Tübingen, Germany, 2019 (phdthesis)

ei Katiyar, P. Quantification of tumor heterogeneity using PET/MRI and machine learning Eberhard Karls Universität Tübingen, Germany, 2019 (phdthesis)

Advances in Probabilistic Modelling: Sparse Gaussian Processes, Autoencoders, and Few-shot Learning

Bauer, M.

University of Cambridge, UK, 2019 (phdthesis)

ei Bauer, M. Advances in Probabilistic Modelling: Sparse Gaussian Processes, Autoencoders, and Few-shot Learning University of Cambridge, UK, 2019 (phdthesis)

Actively Learning Dynamical Systems with Gaussian Processes

Buisson-Fenet, M.

Mines ParisTech, PSL Research University, 2019 (mastersthesis)

Abstract

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

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

2016

Non-parametric Models for Structured Data and Applications to Human Bodies and Natural Scenes

Lehrmann, A.

ETH Zurich, July 2016 (phdthesis)

Abstract

The purpose of this thesis is the study of non-parametric models for structured data and their fields of application in computer vision. We aim at the development of context-sensitive architectures which are both expressive and efficient. Our focus is on directed graphical models, in particular Bayesian networks, where we combine the flexibility of non-parametric local distributions with the efficiency of a global topology with bounded treewidth. A bound on the treewidth is obtained by either constraining the maximum indegree of the underlying graph structure or by introducing determinism. The non-parametric distributions in the nodes of the graph are given by decision trees or kernel density estimators. The information flow implied by specific network topologies, especially the resultant (conditional) independencies, allows for a natural integration and control of contextual information. We distinguish between three different types of context: static, dynamic, and semantic. In four different approaches we propose models which exhibit varying combinations of these contextual properties and allow modeling of structured data in space, time, and hierarchies derived thereof. The generative character of the presented models enables a direct synthesis of plausible hypotheses. Extensive experiments validate the developed models in two application scenarios which are of particular interest in computer vision: human bodies and natural scenes. In the practical sections of this work we discuss both areas from different angles and show applications of our models to human pose, motion, and segmentation as well as object categorization and localization. Here, we benefit from the availability of modern datasets of unprecedented size and diversity. Comparisons to traditional approaches and state-of-the-art research on the basis of well-established evaluation criteria allows the objective assessment of our contributions.

2016

ps Lehrmann, A. Non-parametric Models for Structured Data and Applications to Human Bodies and Natural Scenes ETH Zurich, July 2016 (phdthesis)

Proceedings of the Thirty-Second Conference on Uncertainty in Artificial Intelligence (UAI)

Ihler, A. T., Janzing, D.

pages: 869, AUAI Press, June 2016 (proceedings)

ei Ihler, A. T., Janzing, D. Proceedings of the Thirty-Second Conference on Uncertainty in Artificial Intelligence (UAI) pages: 869, AUAI Press, June 2016 (proceedings)

Advances in computational imaging: Benchmarking Deblurring Algorithms, Deep Neural Inpainting, Depth Estimation from Light Fields

Köhler, R.

Eberhard Karls Universität Tübingen, Germany, 2016 (phdthesis)

ei Köhler, R. Advances in computational imaging: Benchmarking Deblurring Algorithms, Deep Neural Inpainting, Depth Estimation from Light Fields Eberhard Karls Universität Tübingen, Germany, 2016 (phdthesis)

Tractable Structured Prediction using the Permutohedral Lattice

Kiefel, M.

ETH Zurich, 2016 (phdthesis)

ei Kiefel, M. Tractable Structured Prediction using the Permutohedral Lattice ETH Zurich, 2016 (phdthesis)

Untersuchung des Beitrages von Elektron-Magnon Streuungen zur ultraschnellen Entmagnetisierung nach Femtosekunden Laserbestrahlung ferromagnetischer Filme

Haag, M.

Universität Stuttgart, Stuttgart, 2016 (phdthesis)

mms

mms Haag, M. Untersuchung des Beitrages von Elektron-Magnon Streuungen zur ultraschnellen Entmagnetisierung nach Femtosekunden Laserbestrahlung ferromagnetischer Filme Universität Stuttgart, Stuttgart, 2016 (phdthesis)

Statische und dynamische Magnetisierungseigenschaften nanoskaliger Überstrukturen

Gräfe, J.

Universität Stuttgart, Stuttgart (und Cuvillier Verlag, Göttingen), 2016 (phdthesis)

mms

mms Gräfe, J. Statische und dynamische Magnetisierungseigenschaften nanoskaliger Überstrukturen Universität Stuttgart, Stuttgart (und Cuvillier Verlag, Göttingen), 2016 (phdthesis)

Gepinnte Bahnmomente in magnetischen Heterostrukturen

Audehm, P.

Universität Stuttgart, Stuttgart (und Cuvillier Verlag, Göttingen), 2016 (phdthesis)

mms

mms Audehm, P. Gepinnte Bahnmomente in magnetischen Heterostrukturen Universität Stuttgart, Stuttgart (und Cuvillier Verlag, Göttingen), 2016 (phdthesis)

Austauschgekoppelte Moden in magnetischen Vortexstrukturen

Dieterle, G.

Universität Stuttgart, Stuttgart, 2016 (phdthesis)

mms

mms Dieterle, G. Austauschgekoppelte Moden in magnetischen Vortexstrukturen Universität Stuttgart, Stuttgart, 2016 (phdthesis)

Density matrix calculations for the ultrafast demagnetization after femtosecond laser pulses

Weng, Weikai

Universität Stuttgart, Stuttgart, 2016 (mastersthesis)

mms

mms Weng, Weikai Density matrix calculations for the ultrafast demagnetization after femtosecond laser pulses Universität Stuttgart, Stuttgart, 2016 (mastersthesis)

Electric field manipulation of perpendicular magnetic anisotropy in microstructured Cobalt-Iron-Boron Magnesium Oxide thin film systems

Bauch, J.

Universität Stuttgart, Stuttgart, 2016 (mastersthesis)

mms

mms Bauch, J. Electric field manipulation of perpendicular magnetic anisotropy in microstructured Cobalt-Iron-Boron Magnesium Oxide thin film systems Universität Stuttgart, Stuttgart, 2016 (mastersthesis)

Deep Learning for Diabetic Retinopathy Diagnostics

Balles, Lukas

Heidelberg University, 2016 (mastersthesis)

Balles, Lukas Deep Learning for Diabetic Retinopathy Diagnostics Heidelberg University, 2016 (mastersthesis)

Helium und Hydrogen Isotope Adsorption and Separation in Metal-Organic Frameworks

Zaiser, Ingrid

Universität Stuttgart, Stuttgart (und Cuvillier Verlag, Göttingen), 2016 (phdthesis)

mms

mms Zaiser, Ingrid Helium und Hydrogen Isotope Adsorption and Separation in Metal-Organic Frameworks Universität Stuttgart, Stuttgart (und Cuvillier Verlag, Göttingen), 2016 (phdthesis)

2014

Pole Balancing with Apollo

Holger Kaden

Eberhard Karls Universität Tübingen, December 2014 (mastersthesis)

2014

am Holger Kaden Pole Balancing with Apollo Eberhard Karls Universität Tübingen, December 2014 (mastersthesis)

Modeling the polygenic architecture of complex traits

Rakitsch, Barbara

Eberhard Karls Universität Tübingen, November 2014 (phdthesis)

ei Rakitsch, Barbara Modeling the polygenic architecture of complex traits Eberhard Karls Universität Tübingen, November 2014 (phdthesis)

Learning Coupling Terms for Obstacle Avoidance

Rai, A.

École polytechnique fédérale de Lausanne, August 2014 (mastersthesis)

am Rai, A. Learning Coupling Terms for Obstacle Avoidance École polytechnique fédérale de Lausanne, August 2014 (mastersthesis)

Object Tracking in Depth Images Using Sigma Point Kalman Filters

Issac, J.

Karlsruhe Institute of Technology, July 2014 (mastersthesis)

am Issac, J. Object Tracking in Depth Images Using Sigma Point Kalman Filters Karlsruhe Institute of Technology, July 2014 (mastersthesis)

Modeling the Human Body in 3D: Data Registration and Human Shape Representation

Tsoli, A.

Brown University, Department of Computer Science, May 2014 (phdthesis)

ps Tsoli, A. Modeling the Human Body in 3D: Data Registration and Human Shape Representation Brown University, Department of Computer Science, May 2014 (phdthesis)

Probabilistic Object Tracking on the GPU Project Page [BibTex]

Probabilistic Object Tracking on the GPU

Pfreundt, C.

Karlsruhe Institute of Technology, March 2014 (mastersthesis)

am Pfreundt, C. Probabilistic Object Tracking on the GPU Karlsruhe Institute of Technology, March 2014 (mastersthesis)

Probabilistic Object Tracking on the GPU Project Page [BibTex]

A Novel Causal Inference Method for Time Series

Shajarisales, N.

Eberhard Karls Universität Tübingen, Germany, Eberhard Karls Universität Tübingen, Germany, 2014 (mastersthesis)

ei Shajarisales, N. A Novel Causal Inference Method for Time Series Eberhard Karls Universität Tübingen, Germany, Eberhard Karls Universität Tübingen, Germany, 2014 (mastersthesis)

A global analysis of extreme events and consequences for the terrestrial carbon cycle

Zscheischler, J.

Diss. No. 22043, ETH Zurich, Switzerland, ETH Zurich, Switzerland, 2014 (phdthesis)

ei Zscheischler, J. A global analysis of extreme events and consequences for the terrestrial carbon cycle Diss. No. 22043, ETH Zurich, Switzerland, ETH Zurich, Switzerland, 2014 (phdthesis)

Learning objective functions for autonomous motion generation

Kalakrishnan, M.

University of Southern California, University of Southern California, Los Angeles, CA, 2014 (phdthesis)

am Kalakrishnan, M. Learning objective functions for autonomous motion generation University of Southern California, University of Southern California, Los Angeles, CA, 2014 (phdthesis)

Development of advanced methods for improving astronomical images

Schmeißer, N.

Eberhard Karls Universität Tübingen, Germany, Eberhard Karls Universität Tübingen, Germany, 2014 (diplomathesis)

ei Schmeißer, N. Development of advanced methods for improving astronomical images Eberhard Karls Universität Tübingen, Germany, Eberhard Karls Universität Tübingen, Germany, 2014 (diplomathesis)

The Feasibility of Causal Discovery in Complex Systems: An Examination of Climate Change Attribution and Detection

Lacosse, E.

Graduate Training Centre of Neuroscience, University of Tübingen, Germany, Graduate Training Centre of Neuroscience, University of Tübingen, Germany, 2014 (mastersthesis)

ei Lacosse, E. The Feasibility of Causal Discovery in Complex Systems: An Examination of Climate Change Attribution and Detection Graduate Training Centre of Neuroscience, University of Tübingen, Germany, Graduate Training Centre of Neuroscience, University of Tübingen, Germany, 2014 (mastersthesis)

Causal Discovery in the Presence of Time-Dependent Relations or Small Sample Size

Huang, B.

Graduate Training Centre of Neuroscience, University of Tübingen, Germany, Graduate Training Centre of Neuroscience, University of Tübingen, Germany, 2014 (mastersthesis)

ei Huang, B. Causal Discovery in the Presence of Time-Dependent Relations or Small Sample Size Graduate Training Centre of Neuroscience, University of Tübingen, Germany, Graduate Training Centre of Neuroscience, University of Tübingen, Germany, 2014 (mastersthesis)

Analysis of Distance Functions in Graphs

Alamgir, M.

University of Hamburg, Germany, University of Hamburg, Germany, 2014 (phdthesis)

ei Alamgir, M. Analysis of Distance Functions in Graphs University of Hamburg, Germany, University of Hamburg, Germany, 2014 (phdthesis)

Data-driven autonomous manipulation

Pastor, P.

University of Southern California, University of Southern California, Los Angeles, CA, 2014 (phdthesis)

am Pastor, P. Data-driven autonomous manipulation University of Southern California, University of Southern California, Los Angeles, CA, 2014 (phdthesis)

Schalten der Polarität magnetischer Vortexkerne durch eine Zwei-Frequenzen Anregung und mittels direkter Einkopplung eines Stroms

Sproll, M.

Universität Stuttgart, Stuttgart (und Cuvillier Verlag, Göttingen), Stuttgart, 2014 (phdthesis)

mms

mms Sproll, M. Schalten der Polarität magnetischer Vortexkerne durch eine Zwei-Frequenzen Anregung und mittels direkter Einkopplung eines Stroms Universität Stuttgart, Stuttgart (und Cuvillier Verlag, Göttingen), Stuttgart, 2014 (phdthesis)

Vortex-Kern-Korrelation in gekoppelten Systemen

Jüllig, P.

Universität Stuttgart, Stuttgart, 2014 (phdthesis)

mms

mms Jüllig, P. Vortex-Kern-Korrelation in gekoppelten Systemen Universität Stuttgart, Stuttgart, 2014 (phdthesis)

Realization of a new Magnetic Scanning X-ray Microscope and Investigation of Landau Structures under Pulsed Field Excitation

Weigand, M.

Universität Stuttgart, Stuttgart (und Cuvillier Verlag, Göttingen), 2014 (phdthesis)

mms

mms Weigand, M. Realization of a new Magnetic Scanning X-ray Microscope and Investigation of Landau Structures under Pulsed Field Excitation Universität Stuttgart, Stuttgart (und Cuvillier Verlag, Göttingen), 2014 (phdthesis)

Magnetism of unconventional nanoscaled materials: An X-ray circular dichroism and muon spin rotation study

Tietze, T.

Universität Stuttgart, Stuttgart, 2014 (phdthesis)

mms

mms Tietze, T. Magnetism of unconventional nanoscaled materials: An X-ray circular dichroism and muon spin rotation study Universität Stuttgart, Stuttgart, 2014 (phdthesis)

Nanoporous Materials for Hydrogen Storage and H2/D2 Isotope Separation

Oh, H.

Universität Stuttgart, Stuttgart, 2014 (phdthesis)

mms

mms Oh, H. Nanoporous Materials for Hydrogen Storage and H2/D2 Isotope Separation Universität Stuttgart, Stuttgart, 2014 (phdthesis)

2006

Advances in Neural Information Processing Systems 18: Proceedings of the 2005 Conference

Weiss, Y., Schölkopf, B., Platt, J.

Proceedings of the 19th Annual Conference on Neural Information Processing Systems (NIPS 2005), pages: 1676, MIT Press, Cambridge, MA, USA, 19th Annual Conference on Neural Information Processing Systems (NIPS), May 2006 (proceedings)

Abstract

The annual Neural Information Processing Systems (NIPS) conference is the flagship meeting on neural computation. It draws a diverse group of attendees--physicists, neuroscientists, mathematicians, statisticians, and computer scientists. The presentations are interdisciplinary, with contributions in algorithms, learning theory, cognitive science, neuroscience, brain imaging, vision, speech and signal processing, reinforcement learning and control, emerging technologies, and applications. Only twenty-five percent of the papers submitted are accepted for presentation at NIPS, so the quality is exceptionally high. This volume contains the papers presented at the December 2005 meeting, held in Vancouver.

Web [BibTex]

2006

ei Weiss, Y., Schölkopf, B., Platt, J. Advances in Neural Information Processing Systems 18: Proceedings of the 2005 Conference Proceedings of the 19th Annual Conference on Neural Information Processing Systems (NIPS 2005), pages: 1676, MIT Press, Cambridge, MA, USA, 19th Annual Conference on Neural Information Processing Systems (NIPS), May 2006 (proceedings)

Web [BibTex]

Kernel PCA for Image Compression

Huhle, B.

Biologische Kybernetik, Eberhard-Karls-Universität, Tübingen, Germany, April 2006 (diplomathesis)

ei Huhle, B. Kernel PCA for Image Compression Biologische Kybernetik, Eberhard-Karls-Universität, Tübingen, Germany, April 2006 (diplomathesis)

Gaussian Process Models for Robust Regression, Classification, and Reinforcement Learning

Kuss, M.

Biologische Kybernetik, Technische Universität Darmstadt, Darmstadt, Germany, March 2006, passed with distinction, published online (phdthesis)

ei Kuss, M. Gaussian Process Models for Robust Regression, Classification, and Reinforcement Learning Biologische Kybernetik, Technische Universität Darmstadt, Darmstadt, Germany, March 2006, passed with distinction, published online (phdthesis)