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.

The book we have at hand is the fourth monograph I wrote for Springer Verlag. The previous one named "Self-Organization and Associative Mem ory" (Springer Series in Information Sciences, Volume 8) came out in 1984. Since then the self-organizing neural-network algorithms called SOM and LVQ have become very popular, as can be seen from the many works re viewed in Chap. 9. The new results obtained in the past ten years or so have warranted a new monograph. Over these years I have also answered lots of questions; they have influenced the contents of the present book. I hope it would be of some interest and help to the readers if I now first very briefly describe the various phases that led to my present SOM research, and the reasons underlying each new step. I became interested in neural networks around 1960, but could not in terrupt my graduate studies in physics. After I was appointed Professor of Electronics in 1965, it still took some years to organize teaching at the uni versity. In 1968 - 69 I was on leave at the University of Washington, and D. Gabor had just published his convolution-correlation model of autoasso ciative memory. I noticed immediately that there was something not quite right about it: the capacity was very poor and the inherent noise and crosstalk were intolerable. In 1970 I therefore sugge~ted the auto associative correlation matrix memory model, at the same time as J.A. Anderson and K. Nakano.

The human brain, wi th its hundred billion or more neurons, is both one of the most complex systems known to man and one of the most important. The last decade has seen an explosion of experimental research on the brain, but little theory of neural networks beyond the study of electrical properties of membranes and small neural circuits. Nonetheless, a number of workers in Japan, the United States and elsewhere have begun to contribute to a theory which provides techniques of mathematical analysis and computer simulation to explore properties of neural systems containing immense numbers of neurons. Recently, it has been gradually recognized that rather independent studies of the dynamics of pattern recognition, pattern format::ion, motor control, self-organization, etc. , in neural systems do in fact make use of common methods. We find that a "competition and cooperation" type of interaction plays a fundamental role in parallel information processing in the brain. The present volume brings together 23 papers presented at a U. S. -Japan Joint Seminar on "Competition and Cooperation in Neural Nets" which was designed to catalyze better integration of theory and experiment in these areas. It was held in Kyoto, Japan, February 15-19, 1982, under the joint sponsorship of the U. S. National Science Foundation and the Japan Society for the Promotion of Science. Participants included brain theorists, neurophysiologists, mathematicians, computer scientists, and physicists. There are seven papers from the U. S.

Pattern recognizers evolve across the sections into perceptrons, a layer of perceptrons, multiple-layered perceptrons, functional link nets, and radial basis function networks. Other networks covered in the process are learning vector quantization networks, self-organizing maps, and recursive neural networks. Backpropagation is derived in complete detail for one and two hidden layers for both unipolar and bipolar sigmoid activation functions.

In response to the exponentially increasing need to analyze vast amounts of data, Neural Networks for Applied Sciences and Engineering: From Fundamentals to Complex Pattern Recognition provides scientists with a simple but systematic introduction to neural networks. Beginning with an introductory discussion on the role of neural networks in

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

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.