Advances in Domain Adaptation Theory

Advances in Domain Adaptation Theory gives current, state-of-the-art results on transfer learning, with a particular focus placed on domain adaptation from a theoretical point-of-view. The book begins with a brief overview of the most popular concepts used to provide generalization guarantees, including sections on Vapnik-Chervonenkis (VC), Rademacher, PAC-Bayesian, Robustness and Stability based bounds. In addition, the book explains domain adaptation problem and describes the four major families of theoretical results that exist in the literature, including the Divergence based bounds. Next, PAC-Bayesian bounds are discussed, including the original PAC-Bayesian bounds for domain adaptation and their updated version. Additional sections present generalization guarantees based on the robustness and stability properties of the learning algorithm. Gives an overview of current results on transfer learning Focuses on the adaptation of the field from a theoretical point-of-view Describes four major families of theoretical results in the literature Summarizes existing results on adaptation in the field Provides tips for future research

The annual conference on NIPS is the flagship conference on neural computation. It draws top academic researchers from around the world & is considered to be a showcase conference for new developments in network algorithms & architectures. This volume contains all of the papers presented at NIPS 2006.

An overview of recent efforts in the machine learning community to deal with dataset and covariate shift, which occurs when test and training inputs and outputs have different distributions. Dataset shift is a common problem in predictive modeling that occurs when the joint distribution of inputs and outputs differs between training and test stages. Covariate shift, a particular case of dataset shift, occurs when only the input distribution changes. Dataset shift is present in most practical applications, for reasons ranging from the bias introduced by experimental design to the irreproducibility of the testing conditions at training time. (An example is -email spam filtering, which may fail to recognize spam that differs in form from the spam the automatic filter has been built on.) Despite this, and despite the attention given to the apparently similar problems of semi-supervised learning and active learning, dataset shift has received relatively little attention in the machine learning community until recently. This volume offers an overview of current efforts to deal with dataset and covariate shift. The chapters offer a mathematical and philosophical introduction to the problem, place dataset shift in relationship to transfer learning, transduction, local learning, active learning, and semi-supervised learning, provide theoretical views of dataset and covariate shift (including decision theoretic and Bayesian perspectives), and present algorithms for covariate shift. Contributors Shai Ben-David, Steffen Bickel, Karsten Borgwardt, Michael Brückner, David Corfield, Amir Globerson, Arthur Gretton, Lars Kai Hansen, Matthias Hein, Jiayuan Huang, Choon Hui Teo, Takafumi Kanamori, Klaus-Robert Müller, Sam Roweis, Neil Rubens, Tobias Scheffer, Marcel Schmittfull, Bernhard Schölkopf Hidetoshi Shimodaira, Alex Smola, Amos Storkey, Masashi Sugiyama

This book presents the proceedings of the 24th European Conference on Artificial Intelligence (ECAI 2020), held in Santiago de Compostela, Spain, from 29 August to 8 September 2020. The conference was postponed from June, and much of it conducted online due to the COVID-19 restrictions. The conference is one of the principal occasions for researchers and practitioners of AI to meet and discuss the latest trends and challenges in all fields of AI and to demonstrate innovative applications and uses of advanced AI technology. The book also includes the proceedings of the 10th Conference on Prestigious Applications of Artificial Intelligence (PAIS 2020) held at the same time. A record number of more than 1,700 submissions was received for ECAI 2020, of which 1,443 were reviewed. Of these, 361 full-papers and 36 highlight papers were accepted (an acceptance rate of 25% for full-papers and 45% for highlight papers). The book is divided into three sections: ECAI full papers; ECAI highlight papers; and PAIS papers. The topics of these papers cover all aspects of AI, including Agent-based and Multi-agent Systems; Computational Intelligence; Constraints and Satisfiability; Games and Virtual Environments; Heuristic Search; Human Aspects in AI; Information Retrieval and Filtering; Knowledge Representation and Reasoning; Machine Learning; Multidisciplinary Topics and Applications; Natural Language Processing; Planning and Scheduling; Robotics; Safe, Explainable, and Trustworthy AI; Semantic Technologies; Uncertainty in AI; and Vision. The book will be of interest to all those whose work involves the use of AI technology.

The First Asian Conference on Machine Learning (ACML 2009) was held at Nanjing, China during November 2–4, 2009.This was the ?rst edition of a series of annual conferences which aim to provide a leading international forum for researchers in machine learning and related ?elds to share their new ideas and research ?ndings. This year we received 113 submissions from 18 countries and regions in Asia, Australasia, Europe and North America. The submissions went through a r- orous double-blind reviewing process. Most submissions received four reviews, a few submissions received ?ve reviews, while only several submissions received three reviews. Each submission was handled by an Area Chair who coordinated discussions among reviewers and made recommendation on the submission. The Program Committee Chairs examined the reviews and meta-reviews to further guarantee the reliability and integrity of the reviewing process. Twenty-nine - pers were selected after this process. To ensure that important revisions required by reviewers were incorporated into the ?nal accepted papers, and to allow submissions which would have - tential after a careful revision, this year we launched a “revision double-check” process. In short, the above-mentioned 29 papers were conditionally accepted, and the authors were requested to incorporate the “important-and-must”re- sionssummarizedbyareachairsbasedonreviewers’comments.Therevised?nal version and the revision list of each conditionally accepted paper was examined by the Area Chair and Program Committee Chairs. Papers that failed to pass the examination were ?nally rejected.

Similarity between objects plays an important role in both human cognitive processes and artificial systems for recognition and categorization. How to appropriately measure such similarities for a given task is crucial to the performance of many machine learning, pattern recognition and data mining methods. This book is devoted to metric learning, a set of techniques to automatically learn similarity and distance functions from data that has attracted a lot of interest in machine learning and related fields in the past ten years. In this book, we provide a thorough review of the metric learning literature that covers algorithms, theory and applications for both numerical and structured data. We first introduce relevant definitions and classic metric functions, as well as examples of their use in machine learning and data mining. We then review a wide range of metric learning algorithms, starting with the simple setting of linear distance and similarity learning. We show how one may scale-up these methods to very large amounts of training data. To go beyond the linear case, we discuss methods that learn nonlinear metrics or multiple linear metrics throughout the feature space, and review methods for more complex settings such as multi-task and semi-supervised learning. Although most of the existing work has focused on numerical data, we cover the literature on metric learning for structured data like strings, trees, graphs and time series. In the more technical part of the book, we present some recent statistical frameworks for analyzing the generalization performance in metric learning and derive results for some of the algorithms presented earlier. Finally, we illustrate the relevance of metric learning in real-world problems through a series of successful applications to computer vision, bioinformatics and information retrieval.

The aim of this book is to discuss the fundamental ideas which lie behind the statistical theory of learning and generalization. It considers learning from the general point of view of function estimation based on empirical data. Omitting proofs and technical details, the author concentrates on discussing the main results of learning theory and their connections to fundamental problems in statistics. These include: - the general setting of learning problems and the general model of minimizing the risk functional from empirical data - a comprehensive analysis of the empirical risk minimization principle and shows how this allows for the construction of necessary and sufficient conditions for consistency - non-asymptotic bounds for the risk achieved using the empirical risk minimization principle - principles for controlling the generalization ability of learning machines using small sample sizes - introducing a new type of universal learning machine that controls the generalization ability.

This comprehensive text/reference presents a broad review of diverse domain adaptation (DA) methods for machine learning, with a focus on solutions for visual applications. The book collects together solutions and perspectives proposed by an international selection of pre-eminent experts in the field, addressing not only classical image categorization, but also other computer vision tasks such as detection, segmentation and visual attributes. Topics and features: Surveys the complete field of visual DA, including shallow methods designed for homogeneous and heterogeneous data as well as deep architectures Presents a positioning of the dataset bias in the CNN-based feature arena Proposes detailed analyses of popular shallow methods that addresses landmark data selection, kernel embedding, feature alignment, joint feature transformation and classifier adaptation, or the case of limited access to the source data Discusses more recent deep DA methods, including discrepancy-based adaptation networks and adversarial discriminative DA models Addresses domain adaptation problems beyond image categorization, such as a Fisher encoding adaptation for vehicle re-identification, semantic segmentation and detection trained on synthetic images, and domain generalization for semantic part detection Describes a multi-source domain generalization technique for visual attributes and a unifying framework for multi-domain and multi-task learning This authoritative volume will be of great interest to a broad audience ranging from researchers and practitioners, to students involved in computer vision, pattern recognition and machine learning. Dr. Gabriela Csurka is a Senior Scientist in the Computer Vision Team at Xerox Research Centre Europe, Meylan, France.

Artificial intelligence (AI) is taking an increasingly important role in our society. From cars, smartphones, airplanes, consumer applications, and even medical equipment, the impact of AI is changing the world around us. The ability of machines to demonstrate advanced cognitive skills in taking decisions, learn and perceive the environment, predict certain behavior, and process written or spoken languages, among other skills, makes this discipline of paramount importance in today's world. Although AI is changing the world for the better in many applications, it also comes with its challenges. This book encompasses many applications as well as new techniques, challenges, and opportunities in this fascinating area.

This in-depth tutorial for students, researchers, and developers covers foundations, plus applications ranging from search to multimedia.

Since the initial work on constrained clustering, there have been numerous advances in methods, applications, and our understanding of the theoretical properties of constraints and constrained clustering algorithms. Bringing these developments together, Constrained Clustering: Advances in Algorithms, Theory, and Applications presents an extensive collection of the latest innovations in clustering data analysis methods that use background knowledge encoded as constraints. Algorithms The first five chapters of this volume investigate advances in the use of instance-level, pairwise constraints for partitional and hierarchical clustering. The book then explores other types of constraints for clustering, including cluster size balancing, minimum cluster size,and cluster-level relational constraints. Theory It also describes variations of the traditional clustering under constraints problem as well as approximation algorithms with helpful performance guarantees. Applications The book ends by applying clustering with constraints to relational data, privacy-preserving data publishing, and video surveillance data. It discusses an interactive visual clustering approach, a distance metric learning approach, existential constraints, and automatically generated constraints. With contributions from industrial researchers and leading academic experts who pioneered the field, this volume delivers thorough coverage of the capabilities and limitations of constrained clustering methods as well as introduces new types of constraints and clustering algorithms.

Adaptive Learning Methods for Nonlinear System Modeling presents some of the recent advances on adaptive algorithms and machine learning methods designed for nonlinear system modeling and identification. Real-life problems always entail a certain degree of nonlinearity, which makes linear models a non-optimal choice. This book mainly focuses on those methodologies for nonlinear modeling that involve any adaptive learning approaches to process data coming from an unknown nonlinear system. By learning from available data, such methods aim at estimating the nonlinearity introduced by the unknown system. In particular, the methods presented in this book are based on online learning approaches, which process the data example-by-example and allow to model even complex nonlinearities, e.g., showing time-varying and dynamic behaviors. Possible fields of applications of such algorithms includes distributed sensor networks, wireless communications, channel identification, predictive maintenance, wind prediction, network security, vehicular networks, active noise control, information forensics and security, tracking control in mobile robots, power systems, and nonlinear modeling in big data, among many others. This book serves as a crucial resource for researchers, PhD and post-graduate students working in the areas of machine learning, signal processing, adaptive filtering, nonlinear control, system identification, cooperative systems, computational intelligence. This book may be also of interest to the industry market and practitioners working with a wide variety of nonlinear systems. Presents the key trends and future perspectives in the field of nonlinear signal processing and adaptive learning. Introduces novel solutions and improvements over the state-of-the-art methods in the very exciting area of online and adaptive nonlinear identification. Helps readers understand important methods that are effective in nonlinear system modelling, suggesting the right methodology to address particular issues.

The three volume proceedings LNAI 10534 – 10536 constitutes the refereed proceedings of the European Conference on Machine Learning and Knowledge Discovery in Databases, ECML PKDD 2017, held in Skopje, Macedonia, in September 2017. The total of 101 regular papers presented in part I and part II was carefully reviewed and selected from 364 submissions; there are 47 papers in the applied data science, nectar and demo track. The contributions were organized in topical sections named as follows: Part I: anomaly detection; computer vision; ensembles and meta learning; feature selection and extraction; kernel methods; learning and optimization, matrix and tensor factorization; networks and graphs; neural networks and deep learning. Part II: pattern and sequence mining; privacy and security; probabilistic models and methods; recommendation; regression; reinforcement learning; subgroup discovery; time series and streams; transfer and multi-task learning; unsupervised and semisupervised learning. Part III: applied data science track; nectar track; and demo track.

This book presents a collection of high-quality research by leading experts in computer vision and its applications. Each of the 16 chapters can be read independently and discusses the principles of a specific topic, reviews up-to-date techniques, presents outcomes, and highlights the challenges and future directions. As such the book explores the latest trends in fashion creative processes, facial features detection, visual odometry, transfer learning, face recognition, feature description, plankton and scene classification, video face alignment, video searching, and object segmentation. It is intended for postgraduate students, researchers, scholars and developers who are interested in computer vision and connected research disciplines, and is also suitable for senior undergraduate students who are taking advanced courses in related topics. However, it is also provides a valuable reference resource for practitioners from industry who want to keep abreast of recent developments in this dynamic, exciting and profitable research field.

List of figures. Preface to the 1992 edition. Preface. The general setting. A formal framework. lustrations. Schemata. The optimal allocation of trials. Reproductive plans and genetic operators. The robustness of genetic plans. Adaptation of codings and representations. An overview. Interim and prospectus. Glossary of important symbols.

Cities are home to the most consequential current attempts at human adaptation and they provide one possible focus for the flourishing of life on this planet. However, for this to be realized in more than an ad hoc way, a substantial rethinking of current approaches and practices needs to occur. Urban Sustainability in Theory and Practice responds to the crises of sustainability in the world today by going back to basics. It makes four major contributions to thinking about and acting upon cities. It provides a means of reflexivity learning about urban sustainability in the process of working practically for positive social development and projected change. It challenges the usually taken-for-granted nature of sustainability practices while providing tools for modifying those practices. It emphasizes the necessity of a holistic and integrated understanding of urban life. Finally it rewrites existing dominant understandings of the social whole such as the triple-bottom line approach that reduce environmental questions to externalities and social questions to background issues. The book is a much-needed practical and conceptual guide for rethinking urban engagement. Covering the full range of sustainability domains and bridging discourses aimed at academics and practitioners, this is an essential read for all those studying, researching and working in urban geography, sustainability assessment, urban planning, urban sociology and politics, sustainable development and environmental studies.

At the close of the 1980s, the independent contributions of Yann Brenier, Mike Cullen and John Mather launched a revolution in the venerable field of optimal transport founded by G. Monge in the 18th century, which has made breathtaking forays into various other domains of mathematics ever since. The author presents a broad overview of this area, supplying complete and self-contained proofs of all the fundamental results of the theory of optimal transport at the appropriate level of generality. Thus, the book encompasses the broad spectrum ranging from basic theory to the most recent research results. PhD students or researchers can read the entire book without any prior knowledge of the field. A comprehensive bibliography with notes that extensively discuss the existing literature underlines the book’s value as a most welcome reference text on this subject.