Refine
Year of publication
Document Type
- Doctoral Thesis (54) (remove)
Language
- English (54) (remove)
Has Fulltext
- yes (54)
Is part of the Bibliography
- no (54)
Keywords
- FPGA (2)
- ALICE (1)
- Abfrageverarbeitung (1)
- Abstraction (1)
- Agent <Künstliche Intelligenz> (1)
- Agenten (1)
- Agents (1)
- Analog (1)
- Analog Circuits (1)
- Analog Verification (1)
Institute
- Informatik (54) (remove)
Visual perception has increasingly grown important during the last decades in the robotics domain. Mobile robots have to localize themselves in known environments and carry out complex navigation tasks. This thesis presents an appearance-based or view-based approach to robot self-localization and robot navigation using holistic, spherical views obtained by cameras with large fields of view. For view-based methods, it is crucial to have a compressed image representation where different views can be stored and compared efficiently. Our approach relies on the spherical Fourier transform, which transforms a signal defined on the sphere to a small set of coefficients, approximating the original signal by a weighted sum of orthonormal basis functions, the so-called spherical harmonics. The truncated low order expansion of the image signal allows to compare input images efficiently, and the mathematical properties of spherical harmonics also allow for estimating rotation between two views, even in 3D. Since no geometrical measurements need to be done, modest quality of the vision system is sufficient. All experiments shown in this thesis are purely based on visual information to show the applicability of the approach. The research presented on robot self localization was focused on demonstrating the usability of the compressed spherical harmonics representation to solve the well-known kidnapped robot problem. To address this problem, the basic idea is to compare the current view to a set of images from a known environment to obtain a likelihood of robot positions. To localize the robot, one could choose the most probable position from the likelihood map; however, it is more beneficial to apply standard methods to integrate information over time while the robot moves, that is, particle or Kalman filters. The first step was to design a fast expansion method to obtain coefficient vectors directly in image space. This was achieved by back-projecting basis functions on the input image. The next steps were to develop a dissimilarity measure, an estimator for rotations between coefficient vectors, and a rotation-invariant dissimilarity measure, all of them purely based on the compact signal representation. With all these techniques at hand, generating likelihood maps is straightforward, but first experiments indicated strong dependence on illumination conditions. This is obviously a challenge for all holistic methods, in particular for a spherical harmonics approach, since local changes usually affect each single element of the coefficient vector. To cope with illumination changes, we investigated preprocessing steps leading to feature images (e.g. edge images, depth images), which bring together our holistic approach and classical feature-based methods. Furthermore, we concentrated on building a statistical model for typical changes of the coefficient vectors in presence of changes in illumination. This task is more demanding but leads to even better results. The second major topic of this thesis is appearance-based robot navigation. I present a view-based approach called Optical Rails (ORails), which leads a robot along a prerecorded track. The robot navigates in a network of known locations which are denoted as waypoints. At each waypoint, we store a compressed view representation. A visual servoing method is used to reach a current target waypoint based on the appearance and the current camera image. Navigating in a network of views is achieved by reaching a sequence of stopover locations, one after another. The main contribution of this work is a model which allows to deduce the best driving direction of the robot based purely on the coefficient vectors of the current and the target image. It is based on image registration as the classical method by Lucas-Kanade, but has been transferred to the spectral domain, which allows for great speedup. ORails also includes a waypoint selection strategy and a module for steering our nonholonomic robot. As for our self-localization algorithm, dependance on illumination changes is also problematic in ORails. Furthermore, occlusions have to be handled for ORails to work properly. I present a solution based on the optimal expansion, which is able to deal with incomplete image signals. To handle dynamic occlusions, i.e. objects appearing in an arbitrary region of the image, we use the linearity of the expansion process and cut the image into segments. These segments can be treated separately, and finally we merge the results. At this point, we can decide to disregard certain segments. Slicing the view allows for local illumination compensation, which is inherently non-robust if applied to the whole view. In conclusion, this approach allows to handle the most important criticism to holistic view-based approaches, that is, occlusions and illumination changes, and consequently improves the performance of Optical Rails.
Relational data exchange deals with translating relational data according to a given specification. This problem is one of the many tasks that arise in data integration, for example, in data restructuring, in ETL (Extract-Transform-Load) processes used for updating data warehouses, or in data exchange between different, possibly independently created, applications. Systems for relational data exchange exist for several decades now. Motivated by their experiences with one of those systems, Fagin, Kolaitis, Miller, and Popa (2003) studied fundamental and algorithmic issues arising in relational data exchange. One of these issues is how to answer queries that are posed against the target schema (i.e., against the result of the data exchange) so that the answers are consistent with the source data. For monotonic queries, the certain answers semantics proposed by Fagin, Kolaitis, Miller, and Popa (2003) is appropriate. For many non-monotonic queries, however, the certain answers semantics was shown to yield counter-intuitive results. This thesis deals with computing the certain answers for monotonic queries on the one hand, and on the other hand, it deals with the issue of which semantics are appropriate for answering non-monotonic queries, and how hard it is to evaluate non-monotonic queries under these semantics. As shown by Fagin, Kolaitis, Miller, and Popa (2003), computing the certain answers for unions of conjunctive queries - a subclass of the monotonic queries - basically reduces to computing universal solutions, provided the data transformation is specified by a set of tgds (tuple-generating dependencies) and egds (equality-generating dependencies). If M is such a specification and S is a source database, then T is called a solution for S under M if T is a possible result of translating S according to M. Intuitively, universal solutions are most general solutions. Since the above-mentioned work by Fagin, Kolaitis, Miller, and Popa it was unknown whether it is decidable if a source database has a universal solution under a given data exchange specification. In this thesis, we show that this problem is undecidable. More precisely, we construct a specification M that consists of tgds only so that it is undecidable whether a given source database has a universal solution under M. From the proof it also follows that it is undecidable whether the chase procedure - by which universal models can be obtained - terminates on a given source database and the set of tgds in M. The above results in particular strengthen results of Deutsch, Nash, and Remmel (2008). Concerning the issue of which semantics are appropriate for answering non-monotonic queries, we study several semantics for answering such queries. All of these semantics are based on the closed world assumption (CWA). First, the CWA-semantics of Libkin (2006) are extended so that they can be applied to specifications consisting of tgds and egds. The key is to extend the concept of CWA-solution, on which the CWA-semantics are based. CWA-solutions are characterized as universal solutions that are derivable from the source database using a suitably controlled version of the chase procedure. In particular, if CWA-solutions exist, then there is a minimal CWA-solution that is unique up to isomorphism: the core of the universal solutions introduced by Fagin, Kolaitis, and Popa (2003). We show that evaluation of a query under some of the CWA-semantics reduces to computing the certain answers to the query on the minimal CWA-solution. The CWA-semantics resolve some the known problems with answering non-monotonic queries. There are, however, two natural properties that are not possessed by the CWA-semantics. On the one hand, queries may be answered differently with respect to data exchange specifications that are logically equivalent. On the other hand, there are queries whose answer under the CWA-semantics intuitively contradicts the information derivable from the source database and the data exchange specification. To find an alternative semantics, we first test several CWA-based semantics from the area of deductive databases for their suitability regarding non-monotonic query answering in relational data exchange. More precisely, we focus on the CWA-semantics by Reiter (1978), the GCWA-semantics (Minker 1982), the EGCWA-semantics (Yahya, Henschen 1985) and the PWS-semantics (Chan 1993). It turns out that these semantics are either too weak or too strong, or do not possess the desired properties. Finally, based on the GCWA-semantics we develop the GCWA*-semantics which intuitively possesses the desired properties. For monotonic queries, some of the CWA-semantics as well as the GCWA*-semantics coincide with the certain answers semantics, that is, results obtained for the certain answers semantics carry over to those semantics. When studying the complexity of evaluating non-monotonic queries under the above-mentioned semantics, we focus on the data complexity, that is, the complexity when the data exchange specification and the query are fixed. We show that in many cases, evaluating non-monotonic queries is hard: co-NP- or NP-complete, or even undecidable. For example, evaluating conjunctive queries with at least one negative literal under simple specifications may be co-NP-hard. Notice, however, that this result only says that there is such a query and such a specification for which the problem is hard, but not that the problem is hard for all such queries and specifications. On the other hand, we identify a broad class of queries - the class of universal queries - which can be evaluated in polynomial time under the GCWA*-semantics, provided the data exchange specification is suitably restricted. More precisely, we show that universal queries can be evaluated on the core of the universal solutions, independent of the source database and the specification.
Plasticity supports the remarkable adaptability and robustness of cortical processing. It allows the brain to learn and remember patterns in the sensory world, to refine motor control, to predict and obtain reward, or to recover function after injury. Behind this great flexibility hide a range of plasticity mechanisms, affecting different aspects of neuronal communication. However, little is known about the precise computational roles of some of these mechanisms. Here, we show that the interaction between spike-timing dependent plasticity (STDP), intrinsic plasticity and synaptic scaling enables neurons to learn efficient representations of their inputs. In the context of reward-dependent learning, the same mechanisms allow a neural network to solve a working memory task. Moreover, although we make no any apriori assumptions on the encoding used for representing inputs, the network activity resembles that of brain regions known to be associated with working memory, suggesting that reward-dependent learning may be a central force in working memory development. Lastly, we investigated some of the clinical implications of synaptic scaling and showed that, paradoxically, there are situations in which the very mechanisms that normally are required to preserve the balance of the system, may act as a destabilizing factor and lead to seizures. Our model offers a novel explanation for the increased incidence of seizures following chronic inflammation.
At present, there is a huge lag between the artificial and the biological information processing systems in terms of their capability to learn. This lag could be certainly reduced by gaining more insight into the higher functions of the brain like learning and memory. For instance, primate visual cortex is thought to provide the long-term memory for the visual objects acquired by experience. The visual cortex handles effortlessly arbitrary complex objects by decomposing them rapidly into constituent components of much lower complexity along hierarchically organized visual pathways. How this processing architecture self-organizes into a memory domain that employs such compositional object representation by learning from experience remains to a large extent a riddle. The study presented here approaches this question by proposing a functional model of a self-organizing hierarchical memory network. The model is based on hypothetical neuronal mechanisms involved in cortical processing and adaptation. The network architecture comprises two consecutive layers of distributed, recurrently interconnected modules. Each module is identified with a localized cortical cluster of fine-scale excitatory subnetworks. A single module performs competitive unsupervised learning on the incoming afferent signals to form a suitable representation of the locally accessible input space. The network employs an operating scheme where ongoing processing is made of discrete successive fragments termed decision cycles, presumably identifiable with the fast gamma rhythms observed in the cortex. The cycles are synchronized across the distributed modules that produce highly sparse activity within each cycle by instantiating a local winner-take-all-like operation. Equipped with adaptive mechanisms of bidirectional synaptic plasticity and homeostatic activity regulation, the network is exposed to natural face images of different persons. The images are presented incrementally one per cycle to the lower network layer as a set of Gabor filter responses extracted from local facial landmarks. The images are presented without any person identity labels. In the course of unsupervised learning, the network creates simultaneously vocabularies of reusable local face appearance elements, captures relations between the elements by linking associatively those parts that encode the same face identity, develops the higher-order identity symbols for the memorized compositions and projects this information back onto the vocabularies in generative manner. This learning corresponds to the simultaneous formation of bottom-up, lateral and top-down synaptic connectivity within and between the network layers. In the mature connectivity state, the network holds thus full compositional description of the experienced faces in form of sparse memory traces that reside in the feed-forward and recurrent connectivity. Due to the generative nature of the established representation, the network is able to recreate the full compositional description of a memorized face in terms of all its constituent parts given only its higher-order identity symbol or a subset of its parts. In the test phase, the network successfully proves its ability to recognize identity and gender of the persons from alternative face views not shown before. An intriguing feature of the emerging memory network is its ability to self-generate activity spontaneously in absence of the external stimuli. In this sleep-like off-line mode, the network shows a self-sustaining replay of the memory content formed during the previous learning. Remarkably, the recognition performance is tremendously boosted after this off-line memory reprocessing. The performance boost is articulated stronger on those face views that deviate more from the original view shown during the learning. This indicates that the off-line memory reprocessing during the sleep-like state specifically improves the generalization capability of the memory network. The positive effect turns out to be surprisingly independent of synapse-specific plasticity, relying completely on the synapse-unspecific, homeostatic activity regulation across the memory network. The developed network demonstrates thus functionality not shown by any previous neuronal modeling approach. It forms and maintains a memory domain for compositional, generative object representation in unsupervised manner through experience with natural visual images, using both on- ("wake") and off-line ("sleep") learning regimes. This functionality offers a promising departure point for further studies, aiming for deeper insight into the learning mechanisms employed by the brain and their consequent implementation in the artificial adaptive systems for solving complex tasks not tractable so far.
Planning problems, like real-world planning and scheduling problems, are complex tasks. As an efficient strategy for handing such problems is the ‘divide and conquer’ strategy has been identified. Each sub problem is then solved independently. Typically the sub problems are solved in a linear way. This approach enables the generation of sub-optimal plans for a number of real world problems. Today, this approach is widely accepted and has been established e.g. in the organizational structure of companies. But existing interdependencies between the sub problems are not sufficiently regarded, as each problem are solved sequentially and no feedback information is given. The field of coordination has been covered by a number of academic fields, like the distributed artificial intelligence, economics or game theory. An important result is, that there exist no method that leads to optimal results in any given coordination problem. Consequently, a suitable coordination mechanism has to be identified for each single coordination problem. Up to now, there exists no process for the selection of a coordination mechanism, neither in the engineering of distributed systems nor in agent oriented software engineering. Within the scope of this work the ECo process is presented, that address exactly this selection problem. The Eco process contains the following five steps. • Modeling of the coordination problem • Defining the coordination requirements • Selection / Design of the coordination mechanism • Implementation • Evaluation Each of these steps is detailed in the thesis. The modeling has to be done to enable a systemic analysis of the coordination problem. Coordination mechanisms have to respect the given situation and the context in which the coordination has to be done. The requirements imposed by the context of the coordination problem are formalized in the coordination requirements. The selection process is driven by these coordination requirements. Using the requirements as a distinction for the selection of a coordination mechanism is a central aspect of this thesis. Additionally these requirements can be used for documentation of design decisions. Therefore, it is reasonable to annotate the coordination mechanisms with the coordination requirements they fulfill and fail to ease the selection process, for a given situation. For that reason we present a new classification scheme for coordination methods within this thesis that classifies existing coordination methods according to a set of criteria that has been identified as important for the distinction between different coordination methods. The implementation phase of the ECo process is supported by the CoPS process and CoPS framework that has been developed within this thesis, as well. The CoPS process structures the design making that has to be done during the implementation phase. The CoPS framework provides a set of basic features software agents need for realizing the selected coordination method. Within the CoPS process techniques are presented for the design and implementation of conversations between agents that can be applied not only within the context of the coordination of planning systems, but for multiagent systems in general. The ECo-CoPS approach has been successfully validated in two case studies from the logistic domain.
Algorithms and data structures constitute the theoretical foundations of computer science and are an integral part of any classical computer science curriculum. Due to their high level of abstraction, the understanding of algorithms is of crucial concern to the vast majority of novice students. To facilitate the understanding and teaching of algorithms, a new research field termed "algorithm visualisation" evolved in the early 1980's. This field is concerned with innovating techniques and concepts for the development of effective algorithm visualisations for teaching, study, and research purposes. Due to the large number of requirements that high-quality algorithm visualisations need to meet, developing and deploying effective algorithm visualisations from scratch is often deemed to be an arduous, time-consuming task, which necessitates high-level skills in didactics, design, programming and evaluation. A substantial part of this thesis is devoted to the problems and solutions related to the automation of three-dimensional visual simulation of algorithms. The scientific contribution of the research presented in this work lies in addressing three concerns: - Identifying and investigating the issues related to the full automation of visual simulations. - Developing an automation-based approach to minimising the effort required for creating effective visual simulations. - Designing and implementing a rich environment for the visualisation of arbitrary algorithms and data structures in 3D. The presented research in this thesis is of considerable interest to (1) researchers anxious to facilitate the development process of algorithm visualisations, (2) educators concerned with adopting algorithm visualisations as a teaching aid and (3) students interested in developing their own algorithm animations.
Understanding the dynamics of recurrent neural networks is crucial for explaining how the brain processes information. In the neocortex, a range of different plasticity mechanisms are shaping recurrent networks into effective information processing circuits that learn appropriate representations for time-varying sensory stimuli. However, it has been difficult to mimic these abilities in artificial neural models. In the present thesis, we introduce several recurrent network models of threshold units that combine spike timing dependent plasticity with homeostatic plasticity mechanisms like intrinsic plasticity or synaptic normalization. We investigate how these different forms of plasticity shape the dynamics and computational properties of recurrent networks. The networks receive input sequences composed of different symbols and learn the structure embedded in these sequences in an unsupervised manner. Information is encoded in the form of trajectories through a high-dimensional state space reminiscent of recent biological findings on cortical coding. We find that these self-organizing plastic networks are able to represent and "understand" the spatio-temporal patterns in their inputs while maintaining their dynamics in a healthy regime suitable for learning. The emergent properties are not easily predictable on the basis of the individual plasticity mechanisms at work. Our results underscore the importance of studying the interaction of different forms of plasticity on network behavior.
A framework for the analysis and visualization of multielectrode spike trains / von Ovidiu F. Jurjut
(2009)
The brain is a highly distributed system of constantly interacting neurons. Understanding how it gives rise to our subjective experiences and perceptions depends largely on understanding the neuronal mechanisms of information processing. These mechanisms are still poorly understood and a matter of ongoing debate remains the timescale on which the coding process evolves. Recently, multielectrode recordings of neuronal activity have begun to contribute substantially to elucidating how information coding is implemented in brain circuits. Unfortunately, analysis and interpretation of multielectrode data is often difficult because of their complexity and large volume. Here we propose a framework that enables the efficient analysis and visualization of multielectrode spiking data. First, using self-organizing maps, we identified reoccurring multi-neuronal spike patterns that evolve on various timescales. Second, we developed a color-based visualization technique for these patterns. They were mapped onto a three-dimensional color space based on their reciprocal similarities, i.e., similar patterns were assigned similar colors. This innovative representation enables a quick and comprehensive inspection of spiking data and provides a qualitative description of pattern distribution across entire datasets. Third, we quantified the observed pattern expression motifs and we investigated their contribution to the encoding of stimulus-related information. An emphasis was on the timescale on which patterns evolve, covering the temporal scales from synchrony up to mean firing rate. Using our multi-neuronal analysis framework, we investigated data recorded from the primary visual cortex of anesthetized cats. We found that cortical responses to dynamic stimuli are best described as successions of multi-neuronal activation patterns, i.e., trajectories in a multidimensional pattern space. Patterns that encode stimulus-specific information are not confined to a single timescale but can span a broad range of timescales, which are tightly related to the temporal dynamics of the stimuli. Therefore, the strict separation between synchrony and mean firing rate is somewhat artificial as these two represent only extreme cases of a continuum of timescales that are expressed in cortical dynamics. Results also indicate that timescales consistent with the time constants of neuronal membranes and fast synaptic transmission (~10-20 ms) appear to play a particularly salient role in coding, as patterns evolving on these timescales seem to be involved in the representation of stimuli with both slow and fast temporal dynamics.
Driving can be dangerous. Humans become inattentive when performing a monotonous task like driving. Also the risk implied while multi-tasking, like using the cellular phone while driving, can break the concentration of the driver and increase the risk of accidents. Others factors like exhaustion, nervousness and excitement affect the performance of the driver and the response time. Consequently, car manufacturers have developed systems in the last decades which assist the driver under various circumstances. These systems are called driver assistance systems. Driver assistance systems are meant to support the task of driving, and the field of action varies from alerting the driver, with acoustical or optical warnings, to taking control of the car, such as keeping the vehicle in the traffic lane until the driver resumes control. For such a purpose, the vehicle is equipped with on-board sensors which allow the perception of the environment and/or the state of the vehicle. Cameras are sensors which extract useful information about the visual appearance of the environment. Additionally, a binocular system allows the extraction of 3D information. One of the main requirements for most camera-based driver assistance systems is the accurate knowledge of the motion of the vehicle. Some sources of information, like velocimeters and GPS, are of common use in vehicles today. Nevertheless, the resolution and accuracy usually achieved with these systems are not enough for many real-time applications. The computation of ego-motion from sequences of stereo images for the implementation of driving intelligent systems, like autonomous navigation or collision avoidance, constitutes the core of this thesis. This dissertation proposes a framework for the simultaneous computation of the 6 degrees of freedom of ego-motion (rotation and translation in 3D Euclidean space), the estimation of the scene structure and the detection and estimation of independently moving objects. The input is exclusively provided by a binocular system and the framework does not call for any data acquisition strategy, i.e. the stereo images are just processed as they are provided. Stereo allows one to establish correspondences between left and right images, estimating 3D points of the environment via triangulation. Likewise, feature tracking establishes correspondences between the images acquired at different time instances. When both are used together for a large number of points, the result is a set of clouds of 3D points with point-to-point correspondences between clouds. The apparent motion of the 3D points between consecutive frames is caused by a variety of reasons. The most dominant motion for most of the points in the clouds is caused by the ego-motion of the vehicle; as the vehicle moves and images are acquired, the relative position of the world points with respect to the vehicle changes. Motion is also caused by objects moving in the environment. They move independently of the vehicle motion, so the observed motion for these points is the sum of the ego-vehicle motion and the independent motion of the object. A third reason, and of paramount importance in vision applications, is caused by correspondence problems, i.e. the incorrect spatial or temporal assignment of the point-to-point correspondence. Furthermore, all the points in the clouds are actually noisy measurements of the real unknown 3D points of the environment. Solving ego-motion and scene structure from the clouds of points requires some previous analysis of the noise involved in the imaging process, and how it propagates as the data is processed. Therefore, this dissertation analyzes the noise properties of the 3D points obtained through stereo triangulation. This leads to the detection of a bias in the estimation of 3D position, which is corrected with a reformulation of the projection equation. Ego-motion is obtained by finding the rotation and translation between the two clouds of points. This problem is known as absolute orientation, and many solutions based on least squares have been proposed in the literature. This thesis reviews the available closed form solutions to the problem. The proposed framework is divided in three main blocks: 1) stereo and feature tracking computation, 2) ego-motion estimation and 3) estimation of 3D point position and 3D velocity. The first block solves the correspondence problem providing the clouds of points as output. No special implementation of this block is required in this thesis. The ego-motion block computes the motion of the cameras by finding the absolute orientation between the clouds of static points in the environment. Since the cloud of points might contain independently moving objects and outliers generated by false correspondences, the direct computation of the least squares might lead to an erroneous solution. The first contribution of this thesis is an effective rejection rule that detects outliers based on the distance between predicted and measured quantities, and reduces the effects of noisy measurement by assigning appropriate weights to the data. This method is called Smoothness Motion Constraint (SMC). The ego-motion of the camera between two frames is obtained finding the absolute orientation between consecutive clouds of weighted 3D points. The complete ego-motion since initialization is achieved concatenating the individual motion estimates. This leads to a super-linear propagation of the error, since noise is integrated. A second contribution of this dissertation is a predictor/corrector iterative method, which integrates the clouds of 3D points of multiple time instances for the computation of ego-motion. The presented method considerably reduces the accumulation of errors in the estimated ego-position of the camera. Another contribution of this dissertation is a method which recursively estimates the 3D world position of a point and its velocity; by fusing stereo, feature tracking and the estimated ego-motion in a Kalman Filter system. An improved estimation of point position is obtained this way, which is used in the subsequent system cycle resulting in an improved computation of ego-motion. The general contribution of this dissertation is a single framework for the real time computation of scene structure, independently moving objects and ego-motion for automotive applications.
In the context of information theory, the term Mutual Information has first been formulated by Claude Elwood Shannon. Information theory is the consistent mathematical description of technical communication systems. To this day, it is the basis of numerous applications in modern communications engineering and yet became indispensable in this field. This work is concerned with the development of a concept for nonlinear feature selection from scalar, multivariate data on the basis of the mutual information. From the viewpoint of modelling, the successful construction of a realistic model depends highly on the quality of the employed data. In the ideal case, high quality data simply consists of the relevant features for deriving the model. In this context, it is important to possess a suitable method for measuring the degree of the, mostly nonlinear, dependencies between input- and output variables. By means of such a measure, the relevant features could be specifically selected. During the course of this work, it will become evident that the mutual information is a valuable and feasible measure for this task and hence the method of choice for practical applications. Basically and without the claim of being exhaustive, there are two possible constellations that recommend the application of feature selection. On the one hand, feature selection plays an important role, if the computability of a derived system model cannot be guaranteed, due to a multitude of available features. On the other hand, the existence of very few data points with a significant number of features also recommends the employment of feature selection. The latter constellation is closely related to the so called "Curse of Dimensionality". The actual statement behind this is the necessity to reduce the dimensionality to obtain an adequate coverage of the data space. In other word, it is important to reduce the dimensionality of the data, since the coverage of the data space exponentially decreases, for a constant number of data points, with the dimensionality of the available data. In the context of mapping between input- and output space, this goal is ideally reached by selecting only the relevant features from the available data set. The basic idea for this work has its origin in the rather practical field of automotive engineering. It was motivated by the goals of a complex research project in which the nonlinear, dynamic dependencies among a multitude of sensor signals should be identified. The final goal of such activities was to derive so called virtual sensors from identified dependencies among the installed automotive sensors. This enables the real-time computability of the required variable without the expenses of additional hardware. The prospect of doing without additional computing hardware is a strong motive force in particular in automotive engineering. In this context, the major problem was to find a feasible method to capture the linear- as well as the nonlinear dependencies. As mentioned before, the goal of this work is the development of a flexibly applicable system for nonlinear feature selection. The important point here is to guarantee the practicable computability of the developed method even for high dimensional data spaces, which are rather realistic in technical environments. The employed measure for the feature selection process is based on the sophisticated concept of mutual information. The property of the mutual information, regarding its high sensitivity and specificity to linear- and nonlinear statistical dependencies, makes it the method of choice for the development of a highly flexible, nonlinear feature selection framework. In addition to the mere selection of relevant features, the developed framework is also applicable for the nonlinear analysis of the temporal influences of the selected features. Hence, a subsequent dynamic modelling can be performed more efficiently, since the proposed feature selection algorithm additionally provides information about the temporal dependencies between input- and output variables. In contrast to feature extraction techniques, the developed feature selection algorithm in this work has another considerable advantage. In the case of cost intensive measurements, the variables with the highest information content can be selected in a prior feasibility study. Hence, the developed method can also be employed to avoid redundance in the acquired data and thus prevent for additional costs.