Pattern Recognition by Self-Organizing Neural Networks presentsthe most recent advances in an area of research that is becoming vitally important in the fields ofcognitive science, neuroscience, artificial intelligence, and neural networks in general. The 19articles take up developments in competitive learning and computational maps, adaptive resonancetheory, and specialized architectures and biological connections. Introductorysurvey articles provide a framework for understanding the many models involved in various approachesto studying neural networks. These are followed in Part 2 by articles that form the foundation formodels of competitive learning and computational mapping, and recent articles by Kohonen, applyingthem to problems in speech recognition, and by Hecht-Nielsen, applying them to problems in designingadaptive lookup tables. Articles in Part 3 focus on adaptive resonance theory (ART) networks,selforganizing pattern recognition systems whose top-down template feedback signals guarantee theirstable learning in response to arbitrary sequences of input patterns. In Part 4, articles describeembedding ART modules into larger architectures and provide experimental evidence fromneurophysiology, event-related potentials, and psychology that support the prediction that ARTmechanisms exist in the brain. Contributors: J.-P. Banquet, G.A. Carpenter, S.Grossberg, R. Hecht-Nielsen, T. Kohonen, B. Kosko, T.W. Ryan, N.A. Schmajuk, W. Singer, D. Stork, C.von der Malsburg, C.L. Winter.

This book is the third in a series based on conferences sponsored by the Metroplex Institute for Neural Dynamics, an interdisciplinary organization of neural network professionals in academia and industry. The topics selected are of broad interest to both those interested in designing machines to perform intelligent functions and those interested in studying how these functions are actually performed by living organisms and generate discussion of basic and controversial issues in the study of mind. The topic of optimality was chosen because it has provoked considerable discussion and controversy in many different academic fields. There are several aspects to the issue of optimality. First, is it true that actual behavior and cognitive functions of living animals, including humans, can be considered as optimal in some sense? Second, what is the utility function for biological organisms, if any, and can it be described mathematically? Rather than organize the chapters on a "biological versus artificial" basis or by what stance they took on optimality, it seemed more natural to organize them either by what level of questions they posed or by what intelligent functions they dealt with. The book begins with some general frameworks for discussing optimality, or the lack of it, in biological or artificial systems. The next set of chapters deals with some general mathematical and computational theories that help to clarify what the notion of optimality might entail in specific classes of networks. The final section deals with optimality in the context of many different high-level issues, including exploring one's environment, understanding mental illness, linguistic communication, and social organization. The diversity of topics covered in this book is designed to stimulate interdisciplinary thinking and speculation about deep problems in intelligent system organization.

The Self-Organizing Map (SOM) is one of the most frequently used architectures for unsupervised artificial neural networks. Introduced by Teuvo Kohonen in the 1980s, SOMs have been developed as a very powerful method for visualization and unsupervised classification tasks by an active and innovative community of interna tional researchers. A number of extensions and modifications have been developed during the last two decades. The reason is surely not that the original algorithm was imperfect or inad equate. It is rather the universal applicability and easy handling of the SOM. Com pared to many other network paradigms, only a few parameters need to be arranged and thus also for a beginner the network leads to useful and reliable results. Never theless there is scope for improvements and sophisticated new developments as this book impressively demonstrates. The number of published applications utilizing the SOM appears to be unending. As the title of this book indicates, the reader will benefit from some of the latest the oretical developments and will become acquainted with a number of challenging real-world applications. Our aim in producing this book has been to provide an up to-date treatment of the field of self-organizing neural networks, which will be ac cessible to researchers, practitioners and graduated students from diverse disciplines in academics and industry. We are very grateful to the father of the SOMs, Professor Teuvo Kohonen for sup porting this book and contributing the first chapter.

TheInternationalConferenceonMachineLearningandDataMining(MLDM)is the third meeting in a series of biennial events, which started in 1999, organized by the Institute of Computer Vision and Applied Computer Sciences (IBaI) in Leipzig. MLDM began as a workshop and is now a conference, and has brought the topic of machine learning and data mining to the attention of the research community. Seventy-?ve papers were submitted to the conference this year. The program committeeworkedhardtoselectthemostprogressiveresearchinafairandc- petent review process which led to the acceptance of 33 papers for presentation at the conference. The 33 papers in these proceedings cover a wide variety of topics related to machine learning and data mining. The two invited talks deal with learning in case-based reasoning and with mining for structural data. The contributed papers can be grouped into nine areas: support vector machines; pattern dis- very; decision trees; clustering; classi?cation and retrieval; case-based reasoning; Bayesian models and methods; association rules; and applications. We would like to express our appreciation to the reviewers for their precise andhighlyprofessionalwork.WearegratefultotheGermanScienceFoundation for its support of the Eastern European researchers. We appreciate the help and understanding of the editorial sta? at Springer Verlag, and in particular Alfred Hofmann,whosupportedthepublicationoftheseproceedingsintheLNAIseries. Last, but not least, we wish to thank all the speakers and participants who contributed to the success of the conference.

Biologically inspiredcomputing isdi?erentfromconventionalcomputing.Ithas adi?erentfeel; often the terminology does notsound like it’stalkingabout machines.The activities ofthiscomputingsoundmorehumanthanmechanistic as peoplespeak ofmachines that behave, react, self-organize,learn, generalize, remember andeven to forget.Much ofthistechnology tries to mimic nature’s approach in orderto mimicsome of nature’s capabilities.They havearigorous, mathematical basisand neuralnetworks forexamplehaveastatistically valid set on which the network istrained. Twooutlinesaresuggestedasthepossibletracksforpatternrecognition.They are neuralnetworks andfunctionalnetworks.NeuralNetworks (many interc- nected elements operating in parallel) carryout tasks that are not only beyond the scope ofconventionalprocessing but also cannotbeunderstood in the same terms.Imagingapplicationsfor neuralnetworksseemtobea natural?t.Neural networks loveto do pattern recognition. A new approachto pattern recognition usingmicroARTMAP together with wavelet transforms in the context ofhand written characters,gestures andsignatures havebeen dealt.The KohonenN- work,Back Propagation Networks andCompetitive Hop?eld NeuralNetwork havebeen considered for various applications. Functionalnetworks,beingageneralizedformofNeuralNetworkswherefu- tionsarelearnedratherthanweightsiscomparedwithMultipleRegressionAn- ysisforsome applicationsandtheresults are seen to be coincident. New kinds of intelligence can be added to machines, and we will havethe possibilityof learningmore about learning.Thus our imaginationsand options are beingstretched.These new machines will be fault-tolerant,intelligentand self-programmingthustryingtomakethemachinessmarter.Soastomakethose who use the techniques even smarter. Chapter1 isabrief introduction toNeural and Functionalnetworks in the context of Patternrecognitionusing these disciplinesChapter2 givesa review ofthearchitectures relevantto the investigation andthedevelopment ofthese technologies in the past few decades. Retracted VIII Preface Chapter3begins with the lookattherecognition ofhandwritten alphabets usingthealgorithm for ordered list ofboundary pixelsas well as the Ko- nenSelf-Organizing Map (SOM).Chapter 4 describes the architecture ofthe MicroARTMAP and its capability.

This 1996 book explains the statistical framework for pattern recognition and machine learning, now in paperback.

Neural computation arises from the capacity of nervous tissue to process information and accumulate knowledge in an intelligent manner. Conventional computational machines have encountered enormous difficulties in duplicatingsuch functionalities. This has given rise to the development of Artificial Neural Networks where computation is distributed over a great number of local processing elements with a high degree of connectivityand in which external programming is replaced with supervised and unsupervised learning. The papers presented in this volume are carefully reviewed versions of the talks delivered at the International Workshop on Artificial Neural Networks (IWANN '93) organized by the Universities of Catalonia and the Spanish Open University at Madrid and held at Barcelona, Spain, in June 1993. The 111 papers are organized in seven sections: biological perspectives, mathematical models, learning, self-organizing networks, neural software, hardware implementation, and applications (in five subsections: signal processing and pattern recognition, communications, artificial vision, control and robotics, and other applications).

The Handbook of Neural Computation is a practical, hands-on guide to the design and implementation of neural networks used by scientists and engineers to tackle difficult and/or time-consuming problems. The handbook bridges an information pathway between scientists and engineers in different disciplines who apply neural networks to similar probl

The book collects the scientific contributions presented at the 10th Workshop on Self-Organizing Maps (WSOM 2014) held at the University of Applied Sciences Mittweida, Mittweida (Germany, Saxony), on July 2–4, 2014. Starting with the first WSOM-workshop 1997 in Helsinki this workshop focuses on newest results in the field of supervised and unsupervised vector quantization like self-organizing maps for data mining and data classification. This 10th WSOM brought together more than 50 researchers, experts and practitioners in the beautiful small town Mittweida in Saxony (Germany) nearby the mountains Erzgebirge to discuss new developments in the field of unsupervised self-organizing vector quantization systems and learning vector quantization approaches for classification. The book contains the accepted papers of the workshop after a careful review process as well as summaries of the invited talks. Among these book chapters there are excellent examples of the use of self-organizing maps in agriculture, computer science, data visualization, health systems, economics, engineering, social sciences, text and image analysis and time series analysis. Other chapters present the latest theoretical work on self-organizing maps as well as learning vector quantization methods, such as relating those methods to classical statistical decision methods. All the contribution demonstrate that vector quantization methods cover a large range of application areas including data visualization of high-dimensional complex data, advanced decision making and classification or data clustering and data compression.

In a simple and accessible way it extends embedding field theory into areas of machine intelligence that have not been clearly dealt with before. Neural Networks for Pattern Recognition takes the pioneering work in artificial neural networks by Stephen Grossberg and his colleagues to a new level. In a simple and accessible way it extends embedding field theory into areas of machine intelligence that have not been clearly dealt with before. Following a tutorial of existing neural networks for pattern classification, Nigrin expands on these networks to present fundamentally new architectures that perform realtime pattern classification of embedded and synonymous patterns and that will aid in tasks such as vision, speech recognition, sensor fusion, and constraint satisfaction. Nigrin presents the new architectures in two stages. First he presents a network called Sonnet 1 that already achieves important properties such as the ability to learn and segment continuously varied input patterns in real time, to process patterns in a context sensitive fashion, and to learn new patterns without degrading existing categories. He then removes simplifications inherent in Sonnet 1 and introduces radically new architectures. These architectures have the power to classify patterns that may have similar meanings but that have different external appearances (synonyms). They also have been designed to represent patterns in a distributed fashion, both in short-term and long-term memory.