Institute Homepage
Institute Homepage EN Sign In

Publications

DEPARTMENTS

Emperical Interference

Haptic Intelligence

Modern Magnetic Systems

Perceiving Systems

Physical Intelligence

Robotic Materials

Social Foundations of Computation

Research Groups

Autonomous Vision

Autonomous Learning

Bioinspired Autonomous Miniature Robots

Dynamic Locomotion

Embodied Vision

Human Aspects of Machine Learning

Intelligent Control Systems

Learning and Dynamical Systems

Locomotion in Biorobotic and Somatic Systems

Micro, Nano, and Molecular Systems

Movement Generation and Control

Neural Capture and Synthesis

Physics for Inference and Optimization

Organizational Leadership and Diversity

Probabilistic Learning Group

Topics

Robot Learning

Conference Paper

2022

Autonomous Learning

Robotics

AI

Career

Award

Dynamic Locomotion Book Special issue on embodied intelligence-understanding animal locomotion and its robotic implementations Manoonponga, P., Badri-Spröwitz, A., Owaki, D. Advanced Robotics, 39:1-2, Taylor & Francis and RSJ, Milton, January 2025 (Published)
Embodied Intelligence (EI)’ refers to the innate ability of animals to utilize their body structures and interact with their environment (morphological computation) in conjunction with their brain and nervous systems (neural computation). This synergy enables them to achieve flexible, versatile, and robust locomotion, and allows them to learn and perform complex tasks throughout their lives. In modern robotics, where artificial intelligence (AI) is the driver for transformative advancements, the harmonious and continuous dynamic interaction between neural computation (including control, memory, and plasticity), the physical (flexible) body, and the environment – collectively referred to as ‘embodiment’ – remains a fundamental principle. Given that animals exhibit adaptive movement strategies across diverse real-world scenarios, understanding these strategies can pave the way for innovative robotic systems that reflect ‘nature intelligence’.
DOI URL BibTeX
Social Foundations of Computation Book The Emerging Science of Machine Learning Benchmarks Hardt, M. 2025 (Published)
Machine learning turns on one simple trick: Split the data into training and test sets. Anything goes on the training set. Rank models on the test set and let model builders compete. Call it a benchmark. Machine learning researchers cherish a good tradition of lamenting the apparent shortcomings of benchmarks. Critics argue that static test sets and metrics promote narrow research objectives, stifling more creative scientific pursuits. Benchmarks also incentivize gaming; in fact, Goodhart's Law cautions against applying competitive pressure to statistical measurement. Over time, researchers may overfit to benchmarks, building models that exploit data artifacts. As a result, test set performance draws a skewed picture of model capabilities that deceives us—especially when comparing humans and machines. To top off the list of issues, there are a slew of reasons why things don't transfer well from benchmarks to the real world.
Website URL BibTeX
Social Foundations of Computation Book Fairness and Machine Learning: Limitations and Opportunities Barocas, S., Hardt, M., Narayanan, A. MIT Press, December 2023 (Published)
An introduction to the intellectual foundations and practical utility of the recent work on fairness and machine learning. Fairness and Machine Learning introduces advanced undergraduate and graduate students to the intellectual foundations of this recently emergent field, drawing on a diverse range of disciplinary perspectives to identify the opportunities and hazards of automated decision-making. It surveys the risks in many applications of machine learning and provides a review of an emerging set of proposed solutions, showing how even well-intentioned applications may give rise to objectionable results. It covers the statistical and causal measures used to evaluate the fairness of machine learning models as well as the procedural and substantive aspects of decision-making that are core to debates about fairness, including a review of legal and philosophical perspectives on discrimination. This incisive textbook prepares students of machine learning to do quantitative work on fairness while reflecting critically on its foundations and its practical utility.• Introduces the technical and normative foundations of fairness in automated decision-making• Covers the formal and computational methods for characterizing and addressing problems• Provides a critical assessment of their intellectual foundations and practical utility• Features rich pedagogy and extensive instructor resources
URL BibTeX
Social Foundations of Computation Book Patterns, Predictions, and Actions: Foundations of Machine Learning Hardt, M., Recht, B. Princeton University Press, August 2022 (Published)
An authoritative, up-to-date graduate textbook on machine learning that highlights its historical context and societal impacts Patterns, Predictions, and Actions introduces graduate students to the essentials of machine learning while offering invaluable perspective on its history and social implications. Beginning with the foundations of decision making, Moritz Hardt and Benjamin Recht explain how representation, optimization, and generalization are the constituents of supervised learning. They go on to provide self-contained discussions of causality, the practice of causal inference, sequential decision making, and reinforcement learning, equipping readers with the concepts and tools they need to assess the consequences that may arise from acting on statistical decisions. Provides a modern introduction to machine learning, showing how data patterns support predictions and consequential actions Pays special attention to societal impacts and fairness in decision making Traces the development of machine learning from its origins to today Features a novel chapter on machine learning benchmarks and datasets Invites readers from all backgrounds, requiring some experience with probability, calculus, and linear algebra An essential textbook for students and a guide for researchers
URL BibTeX
Empirical Inference Book Reinforcement Learning Algorithms: Analysis and Applications Belousov, B., H., A., Klink, P., Parisi, S., Peters, J. 883, Studies in Computational Intelligence, Springer International Publishing, 2021 (Published) DOI BibTeX
Autonomous Vision Book Computer Vision for Autonomous Vehicles: Problems, Datasets and State-of-the-Art Janai, J., Güney, F., Behl, A., Geiger, A. 12(1-3), Foundations and Trends® in Computer Graphics and Vision, now Publishers Inc., Hanover, MA, 2020 (Published)
Recent years have witnessed enormous progress in AI-related fields such as computer vision, machine learning, and autonomous vehicles. As with any rapidly growing field, it becomes increasingly difficult to stay up-to-date or enter the field as a beginner. While several survey papers on particular sub-problems have appeared, no comprehensive survey on problems, datasets, and methods in computer vision for autonomous vehicles has been published. This monograph attempts to narrow this gap by providing a survey on the state-of-the-art datasets and techniques. Our survey includes both the historically most relevant literature as well as the current state of the art on several specific topics, including recognition, reconstruction, motion estimation, tracking, scene understanding, and end-to-end learning for autonomous driving. Towards this goal, we analyze the performance of the state of the art on several challenging benchmarking datasets, including KITTI, MOT, and Cityscapes. Besides, we discuss open problems and current research challenges. To ease accessibility and accommodate missing references, we also provide a website that allows navigating topics as well as methods and provides additional information.
pdf Project Page link DOI BibTeX
Book Measuring, modelling and minimizing perceived motion incongruence for vehicle motion simulation Cleij, D. 57:294, MPI Series in Biological Cybernetics, Logos Verlag, Berlin, Germany, 2020
{Humans always wanted to go faster and higher than their own legs could carry them. This led them to invent numerous types of vehicles to move fast over land, water and air. As training how to handle such vehicles and testing new developments can be dangerous and costly, vehicle motion simulators were invented. Motion-based simulators in particular, combine visual and physical motion cues to provide occupants with a feeling of being in the real vehicle. While visual cues are generally not limited in amplitude, physical cues certainly are, due to the limited simulator motion space. A motion cueing algorithm (MCA) is used to map the vehicle motions onto the simulator motion space. This mapping inherently creates mismatches between the visual and physical motion cues. Due to imperfections in the human perceptual system, not all visual/physical cueing mismatches are perceived. However, if a mismatch is perceived, it can impair the simulation realism and even cause simulator sickness. For MCA design, a good understanding of when mismatches are perceived, and ways to prevent these from occurring, are therefore essential. In this thesis a data-driven approach, using continuous subjective measures of the time-varying Perceived Motion Incongruence (PMI), is adopted. PMI in this case refers to the effect that perceived mismatches between visual and physical motion cues have on the resulting simulator realism. The main goal of this thesis was to develop an MCA-independent off-line prediction method for time-varying PMI during vehicle motion simulation, with the aim of improving motion cueing quality. To this end, a complete roadmap, describing how to measure and model PMI and how to apply such models to predict and minimize PMI in motion simulations is presented. Results from several human-in-the-loop experiments are used to demonstrate the potential of this novel approach.}
BibTeX
Modern Magnetic Systems Book Prototyping Micro- and Nano-Optics with Focused Ion Beam Lithography Keskinbora, K. SL48:46, SPIE.Spotlight, SPIE Press, Bellingham, WA, 2019 (Published) DOI BibTeX
Book The Role of Visual Cues in Body Size Estimation Thaler, A. 56:204, MPI Series in Biological Cybernetics, Logos Verlag, Berlin, Germany, 2019
{Our body is central to what we define as our self. The mental representation of our physical appearance, often called body image, can have a great influence on our psychological health. Given the increase in body mass index worldwide and the societal pressure to conform to body ideals, it is important to gain a better understanding of the nature of body representations and factors that play a role in body size estimation tasks. This doctoral thesis takes a multifaceted approach for investigating the role of different visual cues in the estimation of own body size and shape by using a variety of experimental methods and novel state-of-the-art computer graphics methods. Two visual cues were considered: visual perspective and identity cues in the visual appearance of a body (shape, and color-information), as well as their interactions with own body size and gender. High ecological validity was achieved by testing body size estimation in natural settings, when looking into a mirror, and by generating biometrically plausible virtual bodies based on 3D body scans and statistical body models, and simulating real-world scenarios in immersive virtual reality.}
BibTeX
Book The impossible puzzle: No global embedding in environmental space memory Strickrodt, M. 55:276, MPI Series in Biological Cybernetics, Logos Verlag, Berlin, Germany, 2019
{We live in a fragmented environment where spatial information is scattered across rooms, streets, neighborhoods, and cities. To point out the direction to a currently non-visible location or to find novel shortcuts across previously untraveled terrain we need to rely on our spatial memory by piecing the experienced fragments together in our head. This thesis is concerned with the question of how our spatial memory for navigable space (also called survey knowledge) is structured. Two major theoretical approaches are contrasted. Euclidean map approaches assume that spatial locations are represented in a map-like, globally embedded, Euclidean format. Enriched graph approaches propose a partitioned, unit-wise representation of places connected in a network. In four consecutive studies participants learned spatial relations between objects spread across virtual environments and solved survey tasks afterward (e.g., pointing to object locations from memory). The observed effects imply that our memory of navigable space is stored in the format of an Enriched graph, a network of local places connected by directed links, without the necessity of a global calibration. Survey estimates seem to be constructed incrementally along the memorized connectivity and are generally transient. Additionally, a general reference direction can be acquired, a main direction that is propagated across a sub-group of multiple local places (i.e., a region) or that can cover the entire environment. Taken together, our representation of navigable space seems to be best described as an impossible puzzle where the memorized pieces and connections do not necessarily match up on a global scale.}
BibTeX
Book Where are you? Self- and body part localization using virtual reality setups van der Veer, A. 54:184, MPI Series in Biological Cybernetics, Logos Verlag, Berlin, Germany, 2019
{This volume presents a line of original experimental studies on the bodily self, investigating where people locate themselves in their bodies and how accurate they are at localizing their body parts. So far, it was not well known whether people locate themselves in one or more specific regions of their bodies. On the other hand, some systematic distortions in indicating bodily locations were already documented. In the present studies, participants were therefore asked to indicate their self-locations, as well as the locations of several of their body parts, using a self-directed, first-person perspective pointing paradigm in various virtual reality (VR) setups (different head-mounted displays and a large-screen immersive display). Overall, participants were found to locate themselves mainly in the (upper) face and the (upper) torso. However, striking differences in self-localization were found when testing in different VR setups. Upon further investigation, these differences were found to be foremost due to inaccuracies in body part localization. When taking these inaccuracies into account, differences between setups\textemdashand also with self-localization outside of VR\textemdashlargely disappear. Another striking finding was that providing participants\textemdashin between pointing phases\textemdashwith information about their bodies in the form of a real-time animated self-avatar, did not make them more accurate at locating their own body parts. While manipulating their viewpoint to chest-height of their self-avatar did shift the afterwards indicated locations of their own body parts upwards, towards where they were seen on the avatar. Potential explanations for the various new findings, also from tasks outside of VR, are discussed. Taken together, this volume suggests a differential involvement of multi-sensory information processing in experienced self-location within the body and the ability to locate body parts. Self-localization seems to be less flexible, possibly because it is strongly grounded in the \textquotesinglebodily senses\textquotesingle, while body part localization appears more adaptable to the manipulation of sensory stimuli, at least in the visual modality.}
BibTeX
Book Auditory cues for attention management Glatz, C. 51:158, MPI Series in Biological Cybernetics, Logos Verlag, Berlin, Germany, 2018
{An exhaustible supply of mental resources necessitate that we are selective for what we attend to. Attention prioritizes what ought to be processed and what ignored, allocating valuable resources to selected information at the cost of unattended information elsewhere. For this purpose it is necessary to know the conditions that help the brain decide when attention should be paid, where to and to what information. This dissertation shows how auditory cues can support the management of limited attentional resources based on auditory characteristics. Auditory cues can increase the overall alertness, orient attention to unattended information, or manage attentional resources by informing of an upcoming task-switch and, therefore, indicate when to pay attention to which task.}
BibTeX
Book Motion Feedback in the Teleoperation of Unmanned Aerial Vehicles Lächele, J. 53:122, MPI Series in Biological Cybernetics, Logos Verlag, Berlin, Germany, 2018
{Teleoperation of Unmanned Aerial Vehicles (UAVs) is a valuable tool in scenarios where the operator needs to be protected from hazardous environments or where on-board operation is impossible. Technical limitations, e.g., sensor performance, noise and latencies introduced in the transmission, and ineffective display of the information to the operator can lead to reduced performance and in the worst case a loss of the remote vehicle. The spatial decoupling between the operator and the vehicle is one of the main challenges in teleoperation. This dissertation provides an analysis of providing two types of additional feedback, i.e., vehicle-state and task-related motion feedback, by physically moving the operator using the CyberMotion Simulator. The additional information included in the motion feedback can be used by the operator to improve performance and control behavior of remote UAVs.}
BibTeX
Book Towards Human-UAV Physical Interaction and Fully Actuated Aerial Vehicles Rajappa, S. 52:187, MPI Series in Biological Cybernetics, Logos Verlag, Berlin, Germany, 2018
{Unmanned Aerial Vehicles\textquoteright (UAVs) ability to reach places not accessible to humans or other robots and execute tasks makes them unique and is gaining a lot of research interest recently. Initially UAVs were used as surveying and data collection systems, but lately UAVs are also efficiently employed in aerial manipulation and interaction tasks. In recent times, UAV interaction with the environment has become a common scenario, where manipulators are mounted on top of such systems. Current applications has driven towards the direction of UAVs and humans coexisting and sharing the same workspace, leading to the emerging futuristic domain of Human-UAV physical interaction. The research in this thesis initially addresses the delicate problem of external wrench (force/torque) estimation in aerial vehicles which is executable during flight without any additional sensors. Thereafter a novel architecture is proposed, allowing humans to physically interact with a UAV through the employment of sensor-ring structure and the developed external wrench estimator. The methodologies and algorithms to distinguish forces and torques derived by physical interaction with a human from the disturbance wrenches (due to e.g., wind) are defined through an optimization problem. Furthermore, an admittance-impedance control strategy is employed to act on them differently. This new hardware/software architecture allows for the safe human-UAV physical interaction through exchange of forces. But at the same time, other limitations such as the inability to exchange torques due to the underactuation of quadrotors and the need for a robust controller become evident. In order to improve the robust performance of the UAV, an adaptive super twisting sliding mode controller that works efficiently against parameter uncertainties, unknown dynamics and external perturbations is implemented. In addition, a novel fully actuated tilted propeller hexarotor UAV is designed along with the exact feedback linearization controller and the tilt angles are optimized in order to minimize power consumption, thereby improving the flight time. This fully actuated hexarotor could reorient while hovering and perform 6DoF (Degrees of Freedom) trajectory tracking. Eventually, the external wrench observer, interaction techniques, hardware design, software framework, the robust controller and the different methodologies are put together into the development of Human-UAV physical interaction with fully actuated Hexarotor UAV. This framework allows humans and UAVs to exchange forces as well as torques, becoming the next generation platform for the aerial manipulation and human physical interaction with UAVs.}
BibTeX
Empirical Inference Book Elements of Causal Inference - Foundations and Learning Algorithms Peters, J., Janzing, D., Schölkopf, B. Adaptive Computation and Machine Learning Series, The MIT Press, Cambridge, MA, USA, 2017 (Published) PDF URL BibTeX
Physical Intelligence Book Mobile Microrobotics Sitti, M. Mobile Microrobotics, The MIT Press, Cambridge, MA, 2017 (Published)
Progress in micro- and nano-scale science and technology has created a demand for new microsystems for high-impact applications in healthcare, biotechnology, manufacturing, and mobile sensor networks. The new robotics field of microrobotics has emerged to extend our interactions and explorations to sub-millimeter scales. This is the first textbook on micron-scale mobile robotics, introducing the fundamentals of design, analysis, fabrication, and control, and drawing on case studies of existing approaches. The book covers the scaling laws that can be used to determine the dominant forces and effects at the micron scale; models forces acting on microrobots, including surface forces, friction, and viscous drag; and describes such possible microfabrication techniques as photo-lithography, bulk micromachining, and deep reactive ion etching. It presents on-board and remote sensing methods, noting that remote sensors are currently more feasible; studies possible on-board microactuators; discusses self-propulsion methods that use self-generated local gradients and fields or biological cells in liquid environments; and describes remote microrobot actuation methods for use in limited spaces such as inside the human body. It covers possible on-board powering methods, indispensable in future medical and other applications; locomotion methods for robots on surfaces, in liquids, in air, and on fluid-air interfaces; and the challenges of microrobot localization and control, in particular multi-robot control methods for magnetic microrobots. Finally, the book addresses current and future applications, including noninvasive medical diagnosis and treatment, environmental remediation, and scientific tools.
Mobile Microrobotics By Metin Sitti - Chapter 1 (PDF) URL BibTeX
Perceiving Systems Book Advanced Structured Prediction Nowozin, S., Gehler, P. V., Jancsary, J., Lampert, C. H. Advanced Structured Prediction, 432, Neural Information Processing Series, MIT Press, November 2014 (Published)
The goal of structured prediction is to build machine learning models that predict relational information that itself has structure, such as being composed of multiple interrelated parts. These models, which reflect prior knowledge, task-specific relations, and constraints, are used in fields including computer vision, speech recognition, natural language processing, and computational biology. They can carry out such tasks as predicting a natural language sentence, or segmenting an image into meaningful components. These models are expressive and powerful, but exact computation is often intractable. A broad research effort in recent years has aimed at designing structured prediction models and approximate inference and learning procedures that are computationally efficient. This volume offers an overview of this recent research in order to make the work accessible to a broader research community. The chapters, by leading researchers in the field, cover a range of topics, including research trends, the linear programming relaxation approach, innovations in probabilistic modeling, recent theoretical progress, and resource-aware learning.
publisher URL BibTeX
Empirical Inference Book Learning Motor Skills: From Algorithms to Robot Experiments Kober, J., Peters, J. 97:191, Springer Tracts in Advanced Robotics, Springer, 2014 DOI BibTeX
Empirical Inference Book Empirical Inference - Festschrift in Honor of Vladimir N. Vapnik Schölkopf, B., Luo, Z., Vovk, V. Springer, 2013 (Published) BibTeX
Perceiving Systems Book Consumer Depth Cameras for Computer Vision - Research Topics and Applications Fossati, A., Gall, J., Grabner, H., Ren, X., Konolige, K. Advances in Computer Vision and Pattern Recognition, Springer, 2012 publisher's site BibTeX
Autonomous Learning Book The Playful Machine - Theoretical Foundation and Practical Realization of Self-Organizing Robots Der, R., Martius, G. Springer, Berlin Heidelberg, 2012
Autonomous robots may become our closest companions in the near future. While the technology for physically building such machines is already available today, a problem lies in the generation of the behavior for such complex machines. Nature proposes a solution: young children and higher animals learn to master their complex brain-body systems by playing. Can this be an option for robots? How can a machine be playful? The book provides answers by developing a general principle---homeokinesis, the dynamical symbiosis between brain, body, and environment---that is shown to drive robots to self-determined, individual development in a playful and obviously embodiment-related way: a dog-like robot starts playing with a barrier, eventually jumping or climbing over it; a snakebot develops coiling and jumping modes; humanoids develop climbing behaviors when fallen into a pit, or engage in wrestling-like scenarios when encountering an opponent. The book also develops guided self-organization, a new method that helps to make the playful machines fit for fulfilling tasks in the real world.
URL BibTeX
Empirical Inference Book Optimization for Machine Learning Sra, S., Nowozin, S., Wright, S. 494, Neural information processing series, MIT Press, Cambridge, MA, USA, December 2011
The interplay between optimization and machine learning is one of the most important developments in modern computational science. Optimization formulations and methods are proving to be vital in designing algorithms to extract essential knowledge from huge volumes of data. Machine learning, however, is not simply a consumer of optimization technology but a rapidly evolving field that is itself generating new optimization ideas. This book captures the state of the art of the interaction between optimization and machine learning in a way that is accessible to researchers in both fields. Optimization approaches have enjoyed prominence in machine learning because of their wide applicability and attractive theoretical properties. The increasing complexity, size, and variety of today's machine learning models call for the reassessment of existing assumptions. This book starts the process of reassessment. It describes the resurgence in novel contexts of established frameworks such as first-order methods, stochastic approximations, convex relaxations, interior-point methods, and proximal methods. It also devotes attention to newer themes such as regularized optimization, robust optimization, gradient and subgradient methods, splitting techniques, and second-order methods. Many of these techniques draw inspiration from other fields, including operations research, theoretical computer science, and subfields of optimization. The book will enrich the ongoing cross-fertilization between the machine learning community and these other fields, and within the broader optimization community.
Web BibTeX
Empirical Inference Book Bayesian Time Series Models Barber, D., Cemgil, A., Chiappa, S. 432, Cambridge University Press, Cambridge, UK, August 2011 BibTeX
Empirical Inference Book Handbook of Statistical Bioinformatics Lu, H., Schölkopf, B., Zhao, H. 627, Springer Handbooks of Computational Statistics, Springer, Berlin, Germany, 2011 Web DOI BibTeX
Empirical Inference Book From Motor Learning to Interaction Learning in Robots Sigaud, O., Peters, J. 538, Studies in Computational Intelligence ; 264, (Editors: O Sigaud, J Peters), Springer, Berlin, Germany, January 2010
From an engineering standpoint, the increasing complexity of robotic systems and the increasing demand for more autonomously learning robots, has become essential. This book is largely based on the successful workshop "From motor to interaction learning in robots" held at the IEEE/RSJ International Conference on Intelligent Robot Systems. The major aim of the book is to give students interested the topics described above a chance to get started faster and researchers a helpful compandium.
Web DOI BibTeX
Modern Magnetic Systems Book Handbook of Hydrogen Storage Hirscher, M. 353 p., Wiley-VCH, Weinheim, 2010 BibTeX
Empirical Inference Book Predicting Structured Data Bakir, G., Hofmann, T., Schölkopf, B., Smola, A., Taskar, B., Vishwanathan, S. 360, Advances in neural information processing systems, MIT Press, Cambridge, MA, USA, September 2007
Machine learning develops intelligent computer systems that are able to generalize from previously seen examples. A new domain of machine learning, in which the prediction must satisfy the additional constraints found in structured data, poses one of machine learning’s greatest challenges: learning functional dependencies between arbitrary input and output domains. This volume presents and analyzes the state of the art in machine learning algorithms and theory in this novel field. The contributors discuss applications as diverse as machine translation, document markup, computational biology, and information extraction, among others, providing a timely overview of an exciting field.
Web BibTeX
Empirical Inference Book Semi-Supervised Learning Chapelle, O., Schölkopf, B., Zien, A. 508, Adaptive computation and machine learning, MIT Press, Cambridge, MA, USA, September 2006
In the field of machine learning, semi-supervised learning (SSL) occupies the middle ground, between supervised learning (in which all training examples are labeled) and unsupervised learning (in which no label data are given). Interest in SSL has increased in recent years, particularly because of application domains in which unlabeled data are plentiful, such as images, text, and bioinformatics. This first comprehensive overview of SSL presents state-of-the-art algorithms, a taxonomy of the field, selected applications, benchmark experiments, and perspectives on ongoing and future research. Semi-Supervised Learning first presents the key assumptions and ideas underlying the field: smoothness, cluster or low-density separation, manifold structure, and transduction. The core of the book is the presentation of SSL methods, organized according to algorithmic strategies. After an examination of generative models, the book describes algorithms that implement the low-density separation assumption, graph-based methods, and algorithms that perform two-step learning. The book then discusses SSL applications and offers guidelines for SSL practitioners by analyzing the results of extensive benchmark experiments. Finally, the book looks at interesting directions for SSL research. The book closes with a discussion of the relationship between semi-supervised learning and transduction.
Web BibTeX
Empirical Inference Book Gaussian Processes for Machine Learning Rasmussen, C., Williams, C. 248, Adaptive Computation and Machine Learning, MIT Press, Cambridge, MA, USA, January 2006
Gaussian processes (GPs) provide a principled, practical, probabilistic approach to learning in kernel machines. GPs have received increased attention in the machine-learning community over the past decade, and this book provides a long-needed systematic and unified treatment of theoretical and practical aspects of GPs in machine learning. The treatment is comprehensive and self-contained, targeted at researchers and students in machine learning and applied statistics. The book deals with the supervised-learning problem for both regression and classification, and includes detailed algorithms. A wide variety of covariance (kernel) functions are presented and their properties discussed. Model selection is discussed both from a Bayesian and a classical perspective. Many connections to other well-known techniques from machine learning and statistics are discussed, including support-vector machines, neural networks, splines, regularization networks, relevance vector machines and others. Theoretical issues including learning curves and the PAC-Bayesian framework are treated, and several approximation methods for learning with large datasets are discussed. The book contains illustrative examples and exercises, and code and datasets are available on the Web. Appendixes provide mathematical background and a discussion of Gaussian Markov processes.
Web BibTeX
Empirical Inference Book Kernel Methods in Computational Biology Schölkopf, B., Tsuda, K., Vert, J. 410, Computational Molecular Biology, MIT Press, Cambridge, MA, USA, August 2004
Modern machine learning techniques are proving to be extremely valuable for the analysis of data in computational biology problems. One branch of machine learning, kernel methods, lends itself particularly well to the difficult aspects of biological data, which include high dimensionality (as in microarray measurements), representation as discrete and structured data (as in DNA or amino acid sequences), and the need to combine heterogeneous sources of information. This book provides a detailed overview of current research in kernel methods and their applications to computational biology. Following three introductory chapters—an introduction to molecular and computational biology, a short review of kernel methods that focuses on intuitive concepts rather than technical details, and a detailed survey of recent applications of kernel methods in computational biology—the book is divided into three sections that reflect three general trends in current research. The first part presents different ideas for the design of kernel functions specifically adapted to various biological data; the second part covers different approaches to learning from heterogeneous data; and the third part offers examples of successful applications of support vector machine methods.
Web BibTeX
Modern Magnetic Systems Book Magnetism and the Microstructure of Ferromagnetic Solids Kronmüller, H., Fähnle, M. 432 p., 1st ed., Cambridge University Press, Cambridge, 2003 BibTeX
Empirical Inference Book Learning with Kernels: Support Vector Machines, Regularization, Optimization, and Beyond Schölkopf, B., Smola, A. 644, Adaptive Computation and Machine Learning, MIT Press, Cambridge, MA, USA, December 2002, Parts of this book, including an introduction to kernel methods, can be downloaded here.
In the 1990s, a new type of learning algorithm was developed, based on results from statistical learning theory: the Support Vector Machine (SVM). This gave rise to a new class of theoretically elegant learning machines that use a central concept of SVMs-kernels—for a number of learning tasks. Kernel machines provide a modular framework that can be adapted to different tasks and domains by the choice of the kernel function and the base algorithm. They are replacing neural networks in a variety of fields, including engineering, information retrieval, and bioinformatics. Learning with Kernels provides an introduction to SVMs and related kernel methods. Although the book begins with the basics, it also includes the latest research. It provides all of the concepts necessary to enable a reader equipped with some basic mathematical knowledge to enter the world of machine learning using theoretically well-founded yet easy-to-use kernel algorithms and to understand and apply the powerful algorithms that have been developed over the last few years.
Web DOI BibTeX
Theory of Inhomogeneous Condensed Matter Book Morphology of Condensed Matter - Physics and Geometry of Spatially Complex Systems 600:439 p., Lecture Notes in Physics, Springer, Berlin [et al.], 2002 BibTeX
Empirical Inference Book Advances in Large Margin Classifiers Smola, A., Bartlett, P., Schölkopf, B., Schuurmans, D. 422, Neural Information Processing, MIT Press, Cambridge, MA, USA, October 2000
The concept of large margins is a unifying principle for the analysis of many different approaches to the classification of data from examples, including boosting, mathematical programming, neural networks, and support vector machines. The fact that it is the margin, or confidence level, of a classification--that is, a scale parameter--rather than a raw training error that matters has become a key tool for dealing with classifiers. This book shows how this idea applies to both the theoretical analysis and the design of algorithms. The book provides an overview of recent developments in large margin classifiers, examines connections with other methods (e.g., Bayesian inference), and identifies strengths and weaknesses of the method, as well as directions for future research. Among the contributors are Manfred Opper, Vladimir Vapnik, and Grace Wahba.
Web BibTeX
Autonomous Motion Book Integrierte Wissensverarbeitung mit CAD am Beispiel der konstruktionsbegleitenden Kalkulation (Ways to smarter CAD Systems) Schaal, S. Hanser 1992. (Konstruktionstechnik München Band 8). Zugl. München: TU Diss., München, 1992, clmc BibTeX
Book Testtitel Testauthor, 0 BibTeX
Book testnasim 0 BibTeX