Inst. Softwaretechnik und Theoretische Informatik

248 Items

Recent Submissions
Large-scale approximate EM-style learning and inference in generative graphical models for sparse coding

Shelton, Jacquelyn Ann (2018)

We propose a nonparametric procedure to achieve fast inference in generative graphical models when the number of latent states is very large. The approach is based on iterative latent variable preselection, where we alternate between learning a `selection function' to reveal the relevant latent variables, and using this to obtain a compact approximation of the posterior distribution for EM; thi...

Data processing on heterogeneous hardware

Heimel, Max (2018)

The primary objective of data processing research on modern hardware is to understand how to utilize emerging technology to process data efficiently. Over the last decades, Software Engineers and Computer Scientists have made significant progress towards this goal, providing highly-tuned algorithms, systems & mechanisms for a wide variety of different device types. However, while we mostly unde...

Shaping the selection of fields of study in Afghanistan through educational data mining approaches

Sherzad, Abdul Rahman (2018)

Every year around 250000 high school graduates participate in ‘Kankor’, the Afghan national university entrance exam, while the seating capacity of the country’s 36 public universities is one-fourth of that number. Currently, public and private sectors lack advisory systems to guide the increasing number of participants to choose their fields of study. This is further exacerbated by the fact th...

Learning representations of atomistic systems with deep neural networks

Schütt, Kristof (2018)

Learning Representations of Atomistic Systems with Deep Neural Networks Deep Learning has been shown to learn efficient representations for structured data such as image, text or audio. However, with the rise of applying machine learning to quantum chemistry, research has been largely focused on the development of hand-crafted descriptors of atomistic systems. In this thesis, we propose novel n...

Lernen von Sensormesswerten zur Verbesserung von Fahrerassistenzsystemen am Beispiel eines adaptiven Kurvenwarners

Heinrichs, Robert (2018)

Today, Advanced Driver Assistance Systems are a central part of vehicles and improve safety and comfort. Especially in the safety area, Advanced Driver Assistance Systems have a significant positive impact, which is visible in accident statistics. With sensors and actuators Advanced Driver Assistance Systems can capture the vehicles state and its surroundings, and can intervene if necessary, s...

Burst-dependent bidirectional plasticity in the cerebellum Is driven by presynaptic NMDA receptors

Bouvier, Guy ; Higgins, David ; Spolidoro, Maria ; Carrel, Damien ; Mathieu, Benjamin ; Léna, Clément ; Dieudonné, Stéphane ; Barbour, Boris ; Brunel, Nicolas ; Casado, Mariano (2016-03-24)

Numerous studies have shown that cerebellar function is related to the plasticity at the synapses between parallel fibers and Purkinje cells. How specific input patterns determine plasticity outcomes, as well as the biophysics underlying plasticity of these synapses, remain unclear. Here, we characterize the patterns of activity that lead to postsynaptically expressed LTP using both in vivo and...

Functional consequences of inhibitory plasticity: homeostasis, the excitation-inhibition balance and beyond

Sprekeler, Henning (2017-05-10)

Computational neuroscience has a long-standing tradition of investigating the consequences of excitatory synaptic plasticity. In contrast, the functions of inhibitory plasticity are still largely nebulous, particularly given the bewildering diversity of interneurons in the brain. Here, we review recent computational advances that provide first suggestions for the functional roles of inhibitory ...

Psychological needs as motivators for security and privacy actions on smartphones

Kraus, Lydia ; Wechsung, Ina ; Möller, Sebastian (2017-06)

Much work has been conducted to investigate the obstacles that keep users from using mitigations against security and privacy threats on smartphones. By contrast, we conducted in-depth interviews (N = 19) to explore users’ motivations for voluntarily applying security and privacy actions on smartphones. Our work focuses on analyzing intrinsic motivation in terms of psychological need fulfillmen...

Dorsolateral prefrontal cortex contributes to the impaired behavioral adaptation in alcohol dependence

Beylergil, Sinem Balta ; Beck, Anne ; Deserno, Lorenz ; Lorenz, Robert C. ; Rapp, Michael A. ; Schlagenhauf, Florian ; Heinz, Andreas ; Obermayer, Klaus (2017-04-17)

Substance-dependent individuals often lack the ability to adjust decisions flexibly in response to the changes in reward contingencies. Prediction errors (PEs) are thought to mediate flexible decision-making by updating the reward values associated with available actions. In this study, we explored whether the neurobiological correlates of PEs are altered in alcohol dependence. Behavioral, and ...

Explaining nonlinear classification decisions with deep Taylor decomposition

Montavon, Grégoire ; Lapuschkin, Sebastian ; Binder, Alexander ; Samek, Wojciech ; Müller, Klaus-Robert (2017-05)

Nonlinear methods such as Deep Neural Networks (DNNs) are the gold standard for various challenging machine learning problems such as image recognition. Although these methods perform impressively well, they have a significant disadvantage, the lack of transparency, limiting the interpretability of the solution and thus the scope of application in practice. Especially DNNs act as black boxes du...

Machine learning of accurate energy-conserving molecular force fields

Chmiela, Stefan ; Tkatchenko, Alexandre ; Sauceda, Huziel E. ; Poltavsky, Igor ; Schütt, Kristof T. ; Müller, Klaus-Robert (2017)

Using conservation of energy - a fundamental property of closed classical and quantum mechanical systems - we develop an efficient gradient-domain machine learning (GDML) approach to construct accurate molecular force fields using a restricted number of samples from ab initio molecular dynamics (AIMD) trajectories. The GDML implementation is able to reproduce global potential energy surfaces of...

A rapid prototyping environment for cooperative Advanced Driver Assistance Systems

Massow, Kay ; Radusch, Ilja (2018-03-20)

Advanced Driver Assistance Systems (ADAS) were strong innovation drivers in recent years, towards the enhancement of traffic safety and efficiency. Today’s ADAS adopt an autonomous approach with all instrumentation and intelligence on board of one vehicle. However, to further enhance their benefit, ADAS need to cooperate in the future, using communication technologies. The resulting combination...

Knowledge-intensive, high-performance relation extraction

Krause, Sebastian (2018)

Research on information extraction (IE) from texts has attracted much attention for at least the past two decades. This is not surprising given its significance for applications such as personal digital assistants. Information extraction and its subtask relation extraction play a central role in data processing pipelines that make hidden knowledge such as the content of news articles available ...

Real-time robustness evaluation of regression based myoelectric control against arm position change and donning/doffing

Hwang, Han-Jeong ; Hahne, Janne Mathias ; Müller, Klaus-Robert (2017)

There are some practical factors, such as arm position change and donning/doffing, which prevent robust myoelectric control. The objective of this study is to precisely characterize the impacts of the two representative factors on myoelectric controllability in practical control situations, thereby providing useful references that can be potentially used to find better solutions for clinically ...

Learning from label proportions in brain-computer interfaces

Hübner, David ; Verhoeven, Thibault ; Schmid, Konstantin ; Müller, Klaus-Robert ; Tangermann, Michael ; Kindermans, Pieter-Jan (2017)

Objective Using traditional approaches, a brain-computer interface (BCI) requires the collection of calibration data for new subjects prior to online use. Calibration time can be reduced or eliminated e.g., by subject-to-subject transfer of a pre-trained classifier or unsupervised adaptive classification methods which learn from scratch and adapt over time. While such heuristics work well in p...

Universal exact algorithm for globally augmented MAP inference in structured prediction

Bauer, Alexander (2017)

The ultimate goal of discriminative learning is to train a prediction system by optimizing a desired measure of performance. Unlike in the standard learning scenario with univariate real-valued outputs, in structured prediction we aim at predicting a structured label corresponding to complex objects such as sequences, alignments, sets, or graphs. Here, structural support vector machine (SSVM) e...

Visualization-driven data aggregation

Jugel, Uwe (2017)

Visual analysis of high-volume numerical data is traditionally required for understanding sensor data in manufacturing and engineering scenarios. Today, the visual analysis of any kind of big data has become ubiquitous and is a most-wanted feature for data analysis tools. It is vital for commerce, finance, sales, and an ever-growing number of industries, whose data are traditionally stored in r...

Secure remote service execution for web media streaming

Mikityuk, Alexandra (2017)

Through continuous advancements in streaming and Web technologies over the past decade, the Web has become a platform for media delivery. Web standards like HTML5 have been designed accordingly, allowing for the delivery of applications, high-quality streaming video, and hooks for interoperable content protection. Efficient video encoding algorithms such as AVC/HEVC and streaming protocols ...

Structural graph theory meets algorithms: covering and connectivity problems in graphs

Akhoondian Amiri, Saeed (2017)

Structural graph theory proved itself a valuable tool for designing efficient algorithms for hard problems over recent decades. We exploit structural graph theory to provide novel techniques and algorithms for covering and connectivity problems. First, we focus on the Local model of distributed computing. In the Local model, minimizing the number of communication rounds is the main goal. We ex...

Zero training for BCI – Reality for BCI systems based on event-related potentials

Tangermann, Michael ; Kindermans, Pieter-Jan ; Schreuder, Martijn ; Schrauwen, Benjamin ; Müller, Klaus-Robert (2013)

This contribution reviews how usability in Brain- Computer Interfaces (BCI) can be enhanced. As an example, an unsupervised signal processing approach is presented, which tackles usability by an algorithmic improvement from the field of machine learning. The approach completely omits the necessity of a calibration recording for BCIs based on event-related potential (ERP) paradigms. The positive...