Header logo is


2019


Towards Geometric Understanding of Motion
Towards Geometric Understanding of Motion

Ranjan, A.

University of Tübingen, December 2019 (phdthesis)

Abstract

The motion of the world is inherently dependent on the spatial structure of the world and its geometry. Therefore, classical optical flow methods try to model this geometry to solve for the motion. However, recent deep learning methods take a completely different approach. They try to predict optical flow by learning from labelled data. Although deep networks have shown state-of-the-art performance on classification problems in computer vision, they have not been as effective in solving optical flow. The key reason is that deep learning methods do not explicitly model the structure of the world in a neural network, and instead expect the network to learn about the structure from data. We hypothesize that it is difficult for a network to learn about motion without any constraint on the structure of the world. Therefore, we explore several approaches to explicitly model the geometry of the world and its spatial structure in deep neural networks.

The spatial structure in images can be captured by representing it at multiple scales. To represent multiple scales of images in deep neural nets, we introduce a Spatial Pyramid Network (SpyNet). Such a network can leverage global information for estimating large motions and local information for estimating small motions. We show that SpyNet significantly improves over previous optical flow networks while also being the smallest and fastest neural network for motion estimation. SPyNet achieves a 97% reduction in model parameters over previous methods and is more accurate.

The spatial structure of the world extends to people and their motion. Humans have a very well-defined structure, and this information is useful in estimating optical flow for humans. To leverage this information, we create a synthetic dataset for human optical flow using a statistical human body model and motion capture sequences. We use this dataset to train deep networks and see significant improvement in the ability of the networks to estimate human optical flow.

The structure and geometry of the world affects the motion. Therefore, learning about the structure of the scene together with the motion can benefit both problems. To facilitate this, we introduce Competitive Collaboration, where several neural networks are constrained by geometry and can jointly learn about structure and motion in the scene without any labels. To this end, we show that jointly learning single view depth prediction, camera motion, optical flow and motion segmentation using Competitive Collaboration achieves state-of-the-art results among unsupervised approaches.

Our findings provide support for our hypothesis that explicit constraints on structure and geometry of the world lead to better methods for motion estimation.

ps

PhD Thesis [BibTex]

2019


PhD Thesis [BibTex]


Controlling Heterogeneous Stochastic Growth Processes on Lattices with Limited Resources
Controlling Heterogeneous Stochastic Growth Processes on Lattices with Limited Resources

Haksar, R., Solowjow, F., Trimpe, S., Schwager, M.

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

ics

PDF [BibTex]

PDF [BibTex]


no image
Robot Learning for Muscular Robots

Büchler, D.

Technical University Darmstadt, Germany, December 2019 (phdthesis)

ei

[BibTex]

[BibTex]


no image
Real Time Probabilistic Models for Robot Trajectories

Gomez-Gonzalez, S.

Technical University Darmstadt, Germany, December 2019 (phdthesis)

ei

[BibTex]

[BibTex]


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

Baumann, D.

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

ics

PDF [BibTex]

PDF [BibTex]


no image
Learning Transferable Representations

Rojas-Carulla, M.

University of Cambridge, UK, 2019 (phdthesis)

ei

[BibTex]

[BibTex]


no image
Sample-efficient deep reinforcement learning for continuous control

Gu, S.

University of Cambridge, UK, 2019 (phdthesis)

ei

[BibTex]


no image
X-ray microscopic characterization of high-Tc-supercoductors using image processing

Bihler, M.

Universität Stuttgart, Stuttgart, 2019 (mastersthesis)

mms

[BibTex]


no image
Spatial Filtering based on Riemannian Manifold for Brain-Computer Interfacing

Xu, J.

Technical University of Munich, Germany, 2019 (mastersthesis)

ei

[BibTex]

[BibTex]


no image
Novel X-ray lenses for direct and coherent imaging

Sanli, U. T.

Universität Stuttgart, Stuttgart, 2019 (phdthesis)

mms

link (url) DOI [BibTex]

link (url) DOI [BibTex]


no image
Quantification of tumor heterogeneity using PET/MRI and machine learning

Katiyar, P.

Eberhard Karls Universität Tübingen, Germany, 2019 (phdthesis)

ei

[BibTex]

[BibTex]


no image
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

[BibTex]

[BibTex]

2016


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

ps

pdf [BibTex]


no image
Statische und dynamische Magnetisierungseigenschaften nanoskaliger Überstrukturen

Gräfe, J.

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

mms

[BibTex]

[BibTex]


no image
Gepinnte Bahnmomente in magnetischen Heterostrukturen

Audehm, P.

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

mms

[BibTex]

[BibTex]


no image
Austauschgekoppelte Moden in magnetischen Vortexstrukturen

Dieterle, G.

Universität Stuttgart, Stuttgart, 2016 (phdthesis)

mms

[BibTex]

[BibTex]


no image
Density matrix calculations for the ultrafast demagnetization after femtosecond laser pulses

Weng, Weikai

Universität Stuttgart, Stuttgart, 2016 (mastersthesis)

mms

[BibTex]

[BibTex]


no image
Deep Learning for Diabetic Retinopathy Diagnostics

Balles, Lukas

Heidelberg University, 2016 (mastersthesis)

[BibTex]

[BibTex]


no image
Helium und Hydrogen Isotope Adsorption and Separation in Metal-Organic Frameworks

Zaiser, Ingrid

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

mms

[BibTex]

[BibTex]

2007


no image
Reaction graph kernels for discovering missing enzymes in the plant secondary metabolism

Saigo, H., Hattori, M., Tsuda, K.

NIPS Workshop on Machine Learning in Computational Biology, December 2007 (talk)

Abstract
Secondary metabolic pathway in plant is important for finding druggable candidate enzymes. However, there are many enzymes whose functions are still undiscovered especially in organism-specific metabolic pathways. We propose reaction graph kernels for automatically assigning the EC numbers to unknown enzymatic reactions in a metabolic network. Experiments are carried out on KEGG/REACTION database and our method successfully predicted the first three digits of the EC number with 83% accuracy.We also exhaustively predicted missing enzymatic functions in the plant secondary metabolism pathways, and evaluated our results in biochemical validity.

ei

Web [BibTex]

2007


Web [BibTex]


no image
Positional Oligomer Importance Matrices

Sonnenburg, S., Zien, A., Philips, P., Rätsch, G.

NIPS Workshop on Machine Learning in Computational Biology, December 2007 (talk)

Abstract
At the heart of many important bioinformatics problems, such as gene finding and function prediction, is the classification of biological sequences, above all of DNA and proteins. In many cases, the most accurate classifiers are obtained by training SVMs with complex sequence kernels, for instance for transcription starts or splice sites. However, an often criticized downside of SVMs with complex kernels is that it is very hard for humans to understand the learned decision rules and to derive biological insights from them. To close this gap, we introduce the concept of positional oligomer importance matrices (POIMs) and develop an efficient algorithm for their computation. We demonstrate how they overcome the limitations of sequence logos, and how they can be used to find relevant motifs for different biological phenomena in a straight-forward way. Note that the concept of POIMs is not limited to interpreting SVMs, but is applicable to general k−mer based scoring systems.

ei

Web [BibTex]

Web [BibTex]


no image
Machine Learning Algorithms for Polymorphism Detection

Schweikert, G., Zeller, G., Weigel, D., Schölkopf, B., Rätsch, G.

NIPS Workshop on Machine Learning in Computational Biology, December 2007 (talk)

ei

Web [BibTex]

Web [BibTex]


no image
An Automated Combination of Kernels for Predicting Protein Subcellular Localization

Zien, A., Ong, C.

NIPS Workshop on Machine Learning in Computational Biology, December 2007 (talk)

Abstract
Protein subcellular localization is a crucial ingredient to many important inferences about cellular processes, including prediction of protein function and protein interactions.We propose a new class of protein sequence kernels which considers all motifs including motifs with gaps. This class of kernels allows the inclusion of pairwise amino acid distances into their computation. We utilize an extension of the multiclass support vector machine (SVM)method which directly solves protein subcellular localization without resorting to the common approach of splitting the problem into several binary classification problems. To automatically search over families of possible amino acid motifs, we optimize over multiple kernels at the same time. We compare our automated approach to four other predictors on three different datasets, and show that we perform better than the current state of the art. Furthermore, our method provides some insights as to which features are most useful for determining subcellular localization, which are in agreement with biological reasoning.

ei

Web [BibTex]

Web [BibTex]


no image
Challenges in Brain-Computer Interface Development: Induction, Measurement, Decoding, Integration

Hill, NJ.

Invited keynote talk at the launch of BrainGain, the Dutch BCI research consortium, November 2007 (talk)

Abstract
I‘ll present a perspective on Brain-Computer Interface development from T{\"u}bingen. Some of the benefits promised by BCI technology lie in the near foreseeable future, and some further away. Our motivation is to make BCI technology feasible for the people who could benefit from what it has to offer soon: namely, people in the "completely locked-in" state. I‘ll mention some of the challenges of working with this user group, and explain the specific directions they have motivated us to take in developing experimental methods, algorithms, and software.

ei

[BibTex]

[BibTex]


no image
Some Theoretical Aspects of Human Categorization Behavior: Similarity and Generalization

Jäkel, F.

Biologische Kybernetik, Eberhard-Karls-Universität Tübingen, Tübingen, Germany, November 2007, passed with "ausgezeichnet", summa cum laude, published online (phdthesis)

ei

PDF [BibTex]

PDF [BibTex]


no image
Statistical Learning Theory Approaches to Clustering

Jegelka, S.

Biologische Kybernetik, Eberhard-Karls-Universität Tübingen, Tübingen, Germany, November 2007 (diplomathesis)

ei

PDF [BibTex]

PDF [BibTex]


no image
Policy Learning for Robotics

Peters, J.

14th International Conference on Neural Information Processing (ICONIP), November 2007 (talk)

ei

Web [BibTex]

Web [BibTex]


no image
Hilbert Space Representations of Probability Distributions

Gretton, A.

2nd Workshop on Machine Learning and Optimization at the ISM, October 2007 (talk)

Abstract
Many problems in unsupervised learning require the analysis of features of probability distributions. At the most fundamental level, we might wish to determine whether two distributions are the same, based on samples from each - this is known as the two-sample or homogeneity problem. We use kernel methods to address this problem, by mapping probability distributions to elements in a reproducing kernel Hilbert space (RKHS). Given a sufficiently rich RKHS, these representations are unique: thus comparing feature space representations allows us to compare distributions without ambiguity. Applications include testing whether cancer subtypes are distinguishable on the basis of DNA microarray data, and whether low frequency oscillations measured at an electrode in the cortex have a different distribution during a neural spike. A more difficult problem is to discover whether two random variables drawn from a joint distribution are independent. It turns out that any dependence between pairs of random variables can be encoded in a cross-covariance operator between appropriate RKHS representations of the variables, and we may test independence by looking at a norm of the operator. We demonstrate this independence test by establishing dependence between an English text and its French translation, as opposed to French text on the same topic but otherwise unrelated. Finally, we show that this operator norm is itself a difference in feature means.

ei

PDF Web [BibTex]

PDF Web [BibTex]


no image
Regression with Intervals

Kashima, H., Yamazaki, K., Saigo, H., Inokuchi, A.

International Workshop on Data-Mining and Statistical Science (DMSS2007), October 2007, JSAI Incentive Award. Talk was given by Hisashi Kashima. (talk)

ei

Web [BibTex]

Web [BibTex]


no image
MR-Based PET Attenuation Correction: Method and Validation

Hofmann, M., Steinke, F., Scheel, V., Brady, M., Schölkopf, B., Pichler, B.

Joint Molecular Imaging Conference, September 2007 (talk)

Abstract
PET/MR combines the high soft tissue contrast of Magnetic Resonance Imaging (MRI) and the functional information of Positron Emission Tomography (PET). For quantitative PET information, correction of tissue photon attenuation is mandatory. Usually in conventional PET, the attenuation map is obtained from a transmission scan, which uses a rotating source, or from the CT scan in case of combined PET/CT. In the case of a PET/MR scanner, there is insufficient space for the rotating source and ideally one would want to calculate the attenuation map from the MR image instead. Since MR images provide information about proton density of the different tissue types, it is not trivial to use this data for PET attenuation correction. We present a method for predicting the PET attenuation map from a given the MR image, using a combination of atlas-registration and recognition of local patterns. Using "leave one out cross validation" we show on a database of 16 MR-CT image pairs that our method reliably allows estimating the CT image from the MR image. Subsequently, as in PET/CT, the PET attenuation map can be predicted from the CT image. On an additional dataset of MR/CT/PET triplets we quantitatively validate that our approach allows PET quantification with an error that is smaller than what would be clinically significant. We demonstrate our approach on T1-weighted human brain scans. However, the presented methods are more general and current research focuses on applying the established methods to human whole body PET/MRI applications.

ei

PDF Web [BibTex]

PDF Web [BibTex]


no image
Advances in Neural Information Processing Systems 19: Proceedings of the 2006 Conference

Schölkopf, B., Platt, J., Hofmann, T.

Proceedings of the Twentieth Annual Conference on Neural Information Processing Systems (NIPS 2006), pages: 1690, MIT Press, Cambridge, MA, USA, 20th Annual Conference on Neural Information Processing Systems (NIPS), September 2007 (proceedings)

Abstract
The annual Neural Information Processing Systems (NIPS) conference is the flagship meeting on neural computation and machine learning. It draws a diverse group of attendees--physicists, neuroscientists, mathematicians, statisticians, and computer scientists--interested in theoretical and applied aspects of modeling, simulating, and building neural-like or intelligent systems. The presentations are interdisciplinary, with contributions in algorithms, learning theory, cognitive science, neuroscience, brain imaging, vision, speech and signal processing, reinforcement learning, 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 2006 meeting, held in Vancouver.

ei

Web [BibTex]

Web [BibTex]


no image
Bayesian methods for NMR structure determination

Habeck, M.

29th Annual Discussion Meeting: Magnetic Resonance in Biophysical Chemistry, September 2007 (talk)

ei

Web [BibTex]

Web [BibTex]


no image
Thinking Out Loud: Research and Development of Brain Computer Interfaces

Hill, NJ.

Invited keynote talk at the Max Planck Society‘s PhDNet Workshop., July 2007 (talk)

Abstract
My principal interest is in applying machine-learning methods to the development of Brain-Computer Interfaces (BCI). This involves the classification of a user‘s intentions or mental states, or regression against some continuous intentional control signal, using brain signals obtained for example by EEG, ECoG or MEG. The long-term aim is to develop systems that a completely paralysed person (such as someone suffering from advanced Amyotrophic Lateral Sclerosis) could use to communicate. Such systems have the potential to improve the lives of many people who would be otherwise completely unable to communicate, but they are still very much in the research and development stages.

ei

PDF [BibTex]

PDF [BibTex]


no image
Error Correcting Codes for the P300 Visual Speller

Biessmann, F.

Biologische Kybernetik, Eberhard-Karls-Universität Tübingen, Tübingen, Germany, July 2007 (diplomathesis)

Abstract
The aim of brain-computer interface (BCI) research is to establish a communication system based on intentional modulation of brain activity. This is accomplished by classifying patterns of brain ac- tivity, volitionally induced by the user. The BCI presented in this study is based on a classical paradigm as proposed by (Farwell and Donchin, 1988), the P300 visual speller. Recording electroencephalo- grams (EEG) from the scalp while presenting letters successively to the user, the speller can infer from the brain signal which letter the user was focussing on. Since EEG recordings are noisy, usually many repetitions are needed to detect the correct letter. The focus of this study was to improve the accuracy of the visual speller applying some basic principles from information theory: Stimulus sequences of the speller have been modified into error-correcting codes. Additionally a language model was incorporated into the probabilistic letter de- coder. Classification of single EEG epochs was less accurate using error correcting codes. However, the novel code could compensate for that such that overall, letter accuracies were as high as or even higher than for classical stimulus codes. In particular at high noise levels, error-correcting decoding achieved higher letter accuracies.

ei

PDF [BibTex]

PDF [BibTex]


no image
Dirichlet Process Mixtures of Factor Analysers

Görür, D., Rasmussen, C.

Fifth Workshop on Bayesian Inference in Stochastic Processes (BSP5), June 2007 (talk)

Abstract
Mixture of factor analysers (MFA) is a well-known model that combines the dimensionality reduction technique of Factor Analysis (FA) with mixture modeling. The key issue in MFA is deciding on the latent dimension and the number of mixture components to be used. The Bayesian treatment of MFA has been considered by Beal and Ghahramani (2000) using variational approximation and by Fokoué and Titterington (2003) using birth-and –death Markov chain Monte Carlo (MCMC). Here, we present the nonparametric MFA model utilizing a Dirichlet process (DP) prior on the component parameters (that is, the factor loading matrix and the mean vector of each component) and describe an MCMC scheme for inference. The clustering property of the DP provides automatic selection of the number of mixture components. The latent dimensionality of each component is inferred by automatic relevance determination (ARD). Identifying the action potentials of individual neurons from extracellular recordings, known as spike sorting, is a challenging clustering problem. We apply our model for clustering the waveforms recorded from the cortex of a macaque monkey.

ei

Web [BibTex]

Web [BibTex]


no image
New BCI approaches: Selective Attention to Auditory and Tactile Stimulus Streams

Hill, N., Raths, C.

Invited talk at the PASCAL Workshop on Methods of Data Analysis in Computational Neuroscience and Brain Computer Interfaces, June 2007 (talk)

Abstract
When considering Brain-Computer Interface (BCI) development for patients in the most severely paralysed states, there is considerable motivation to move away from BCI systems based on either motor cortex activity, or on visual stimuli. Together these account for most of current BCI research. I present the results of our recent exploration of new auditory- and tactile-stimulus-driven BCIs. The talk includes a tutorial on the construction and interpretation of classifiers which extract spatio-temporal features from event-related potential data. The effects and implications of whitening are discussed, and preliminary results on the effectiveness of a low-rank constraint (Tomioka and Aihara 2007) are shown.

ei

PDF Web [BibTex]

PDF Web [BibTex]


no image
Towards Motor Skill Learning in Robotics

Peters, J.

Interactive Robot Learning - RSS workshop, June 2007 (talk)

ei

Web [BibTex]

Web [BibTex]


no image
Transductive Support Vector Machines for Structured Variables

Zien, A., Brefeld, U., Scheffer, T.

International Conference on Machine Learning (ICML), June 2007 (talk)

Abstract
We study the problem of learning kernel machines transductively for structured output variables. Transductive learning can be reduced to combinatorial optimization problems over all possible labelings of the unlabeled data. In order to scale transductive learning to structured variables, we transform the corresponding non-convex, combinatorial, constrained optimization problems into continuous, unconstrained optimization problems. The discrete optimization parameters are eliminated and the resulting differentiable problems can be optimized efficiently. We study the effectiveness of the generalized TSVM on multiclass classification and label-sequence learning problems empirically.

ei

PDF PDF Web [BibTex]

PDF PDF Web [BibTex]


no image
Impact of target-to-target interval on classification performance in the P300 speller

Martens, S., Hill, J., Farquhar, J., Schölkopf, B.

Scientific Meeting "Applied Neuroscience for Healthy Brain Function", May 2007 (talk)

ei

PDF Web [BibTex]

PDF Web [BibTex]


no image
Nonparametric Bayesian Discrete Latent Variable Models for Unsupervised Learning

Görür, D.

Biologische Kybernetik, Technische Universität Berlin, Berlin, Germany, April 2007, published online (phdthesis)

ei

PDF PDF [BibTex]

PDF PDF [BibTex]