The book constitutes the proceedings of the 24th International Conference on Artificial Neural Networks, ICANN 2014, held in Hamburg, Germany, in September 2014. The 107 papers included in the proceedings were carefully reviewed and selected from 173 submissions. The focus of the papers is on following topics: recurrent networks; competitive learning and self-organisation; clustering and classification; trees and graphs; human-machine interaction; deep networks; theory; reinforcement learning and action; vision; supervised learning; dynamical models and time series; neuroscience; and applications.

The book constitutes the proceedings of the 23rd International Conference on Artificial Neural Networks, ICANN 2013, held in Sofia, Bulgaria, in September 2013. The 78 papers included in the proceedings were carefully reviewed and selected from 128 submissions. The focus of the papers is on following topics: neurofinance graphical network models, brain machine interfaces, evolutionary neural networks, neurodynamics, complex systems, neuroinformatics, neuroengineering, hybrid systems, computational biology, neural hardware, bioinspired embedded systems, and collective intelligence.

The present collection of papers forms the Proceedings of the First Meeting on Brain Theory, held October 1-4, 1984 at the International Centre for Theoretical Physics in Trieste, Italy. The Meeting was organized with the aim of bringing together brain theorists who are willing to put their own research in the perspective of the general development of neuroscience. Such a meeting was considered necessary since the explosion of experi mental work in neuroscience during the last decades has not been accompanied by an adequate development on the theoretical side. The intensity of the discussions during the Meeting is prob ably reflected best in the report of the organizers, reprinted here following the Preface. During the Meeting it was decided that a workshop of this kind should be repeated at regular intervals of approximately 2 years. The International Centre for Theoretical Physics in Trieste has kindly agreed to act as host for future meetings. The present Meeting was supported by grants from the In ternational Centre for Theoretical Physics and the International School for Advanced Studies in Trieste, IBM-Germany through the "Stifterverband fur die Deutsche Wissenschaft" and the Max Planck-Institute for Biological Cybernetics.

The book offers a new approach to information theory that is more general then the classical approach by Shannon. The classical definition of information is given for an alphabet of symbols or for a set of mutually exclusive propositions (a partition of the probability space ) with corresponding probabilities adding up to 1. The new definition is given for an arbitrary cover of , i.e. for a set of possibly overlapping propositions. The generalized information concept is called novelty and it is accompanied by two new concepts derived from it, designated as information and surprise, which describe "opposite" versions of novelty, information being related more to classical information theory and surprise being related more to the classical concept of statistical significance. In the discussion of these three concepts and their interrelations several properties or classes of covers are defined, which turn out to be lattices. The book also presents applications of these new concepts, mostly in statistics and in neuroscience.

The two-volume set LNCS 7552 + 7553 constitutes the proceedings of the 22nd International Conference on Artificial Neural Networks, ICANN 2012, held in Lausanne, Switzerland, in September 2012. The 162 papers included in the proceedings were carefully reviewed and selected from 247 submissions. They are organized in topical sections named: theoretical neural computation; information and optimization; from neurons to neuromorphism; spiking dynamics; from single neurons to networks; complex firing patterns; movement and motion; from sensation to perception; object and face recognition; reinforcement learning; bayesian and echo state networks; recurrent neural networks and reservoir computing; coding architectures; interacting with the brain; swarm intelligence and decision-making; mulitlayer perceptrons and kernel networks; training and learning; inference and recognition; support vector machines; self-organizing maps and clustering; clustering, mining and exploratory analysis; bioinformatics; and time weries and forecasting.

The two-volume set LNCS 7552 + 7553 constitutes the proceedings of the 22nd International Conference on Artificial Neural Networks, ICANN 2012, held in Lausanne, Switzerland, in September 2012. The 162 papers included in the proceedings were carefully reviewed and selected from 247 submissions. They are organized in topical sections named: theoretical neural computation; information and optimization; from neurons to neuromorphism; spiking dynamics; from single neurons to networks; complex firing patterns; movement and motion; from sensation to perception; object and face recognition; reinforcement learning; bayesian and echo state networks; recurrent neural networks and reservoir computing; coding architectures; interacting with the brain; swarm intelligence and decision-making; mulitlayer perceptrons and kernel networks; training and learning; inference and recognition; support vector machines; self-organizing maps and clustering; clustering, mining and exploratory analysis; bioinformatics; and time weries and forecasting.

This book presents research performed as part of the EU project on biomimetic multimodal learning in a mirror neuron-based robot (MirrorBot) and contri- tions presented at the International AI-Workshop on NeuroBotics. The ov- all aim of the book is to present a broad spectrum of current research into biomimetic neural learning for intelligent autonomous robots. There is a need for a new type of robot which is inspired by nature and so performs in a more ?exible learned manner than current robots. This new type of robot is driven by recent new theories and experiments in neuroscience indicating that a biological and neuroscience-oriented approach could lead to new life-like robotic systems. The book focuses on some of the research progress made in the MirrorBot project which uses concepts from mirror neurons as a basis for the integration of vision, language and action. In this book we show the development of new techniques using cell assemblies, associative neural networks, and Hebbian-type learning in order to associate vision, language and motor concepts. We have developed biomimetic multimodal learning and language instruction in a robot to investigate the task ofsearching for objects. As well as the researchperformed in this area for the MirrorBot project, the second part of this book incorporates signi?cant contributions from other research in the ?eld of biomimetic robotics. This second part of the book concentrates on the progress made in neuroscience inspired robotic learning approaches (in short: NeuroBotics).

KI2004wasthe27theditionoftheannualGermanConferenceonArti?cialInt- ligence, which traditionally brings together academic and industrial researchers from all areas of AI and which enjoys increasing international attendance. KI 2004 received 103 submissions from 26 countries. This volume contains the 30 papers that were ?nally selected for presentation at the conference. The papers cover quite a broad spectrum of "classical" subareas of AI, like na- ral language processing, neural networks, knowledge representation, reasoning, planning, and search. When looking at this year's contributions, it was exciting to observe that there was a strong trend towards actual real-world applications of AI technology. A majority of contributions resulted from or were motivated by applications in a variety of areas. Examples include applications of pl- ning, where the technology is being exploited for taxiway tra?c control and game playing; natural language processing and knowledge representation are enabling advanced Web-based information processing; and the integration of - sults from automated reasoning, neural networks and machine perception into robotics leads to signi?cantly improved capabilities of autonomous systems. The technical programme of KI 2004 was highlighted by invited talks from outstanding researchers in the areas of automated reasoning, robot planning, constraintreasoning, machinelearning, andsemanticWeb: Jorg ] Siekmann(DFKI andUniversityofSaarland, Saarbruc ] ken), MalikGhallab(LAAS-CNRS, Toulouse), Franco, is Fages (INRIA Rocquencourt), Martin Riedmiller (University of - nabru ]ck), andWolfgangWahlster(DFKIandUniversityofSaarland, Saarbruc ] ken). Their invited papers are also presented in this volume."

The focus of the papers presented in these proceedings is on employing various methodologies and approaches for solving real-life problems. Although the mechanisms that the human brain employs to solve problems are not yet completely known, we do have good insight into the functional processing performed by the human mind. On the basis of the understanding of these natural processes, scientists in the field of applied intelligence have developed multiple types of artificial processes, and have employed them successfully in solving real-life problems. The types of approaches used to solve problems are dependant on both the nature of the problem and the expected outcome. While knowledge-based systems are useful for solving problems in well-understood domains with relatively stable environments, the approach may fail when the domain knowledge is either not very well understood or changing rapidly. The techniques of data discovery through data mining will help to alleviate some problems faced by knowledge-based approaches to solving problems in such domains. Research and development in the area of artificial intelligence are influenced by opportunity, needs, and the availability of resources. The rapid advancement of Internet technology and the trend of increasing bandwidths provide an opportunity and a need for intelligent information processing, thus creating an excellent opportunity for agent-based computations and learning. Over 40% of the papers appearing in the conference proceedings focus on the area of machine learning and intelligent agents - clear evidence of growing interest in this area.

This revised edition offers an approach to information theory that is more general than the classical approach of Shannon. Classically, information is defined for an alphabet of symbols or for a set of mutually exclusive propositions (a partition of the probability space ) with corresponding probabilities adding up to 1. The new definition is given for an arbitrary cover of , i.e. for a set of possibly overlapping propositions. The generalized information concept is called novelty and it is accompanied by two concepts derived from it, designated as information and surprise, which describe "opposite" versions of novelty, information being related more to classical information theory and surprise being related more to the classical concept of statistical significance. In the discussion of these three concepts and their interrelations several properties or classes of covers are defined, which turn out to be lattices. The book also presents applications of these concepts, mostly in statistics and in neuroscience.

This book brings together a selection of papers by George Gerstein, representing his long-term endeavor of making neuroscience into a more rigorous science inspired by physics, where he had his roots. Professor Gerstein was many years ahead of the field, consistently striving for quantitative analyses, mechanistic models, and conceptual clarity. In doing so, he pioneered Computational Neuroscience, many years before the term itself was born. The overarching goal of George Gerstein's research was to understand the functional organization of neuronal networks in the brain. The editors of this book have compiled a selection of George Gerstein's many seminal contributions to neuroscience--be they experimental, theoretical or computational--into a single, comprehensive volume .The aim is to provide readers with a fresh introduction of these various concepts in the original literature. The volume is organized in a series of chapters by subject, ordered in time, each one containing one or more of George Gerstein's papers.

In the new edition of Neural Assemblies, the author places his original ideas and motivations within the framework of modern and cognitive neuroscience and gives a short and focused overview of the development of computational neuroscience and artificial neural networks over the last 40 years. In this book the author develops a theory of how the human brain might function. Starting with a motivational introduction to the brain as an organ of information processing, he presents a computational perspective on the basic concepts and ideas of neuroscience research on the underlying principles of brain function. In addition, the reader is introduced to the most important methods from computer science and mathematical modeling that are required for a computational understanding of information processing in the brain. Written by an expert in the field of neural information processing, this book offers a personal historical view of the development of artificial intelligence, artificial neural networks, and computational cognitive neuroscience over the last 40 years, with a focus on the realization of higher cognitive functions rather than more peripheral sensory or motor organization. The book is therefore aimed at students and researchers who want to understand how the basic neuroscientific and computational concepts in the study of brain function have changed over the last decades.