Pattern Recognition with Neural Networks in C++

The addition of artificial network computing to traditional pattern recognition has given rise to a new, different, and more powerful methodology that is presented in this practical guide to the application of artificial neural networks. The material covered in the book is accessible to working engineers with little or no explicit background in neural networks.

The addition of artificial neural network computing to traditional pattern recognition has given rise to a new, different, and more powerful methodology that is presented in this interesting book. This is a practical guide to the application of artificial neural networks.Geared toward the practitioner, Pattern Recognition with Neural Networks in C++ covers pattern classification and neural network approaches within the same framework. Through the book's presentation of underlying theory and numerous practical examples, readers gain an understanding that will allow them to make judicious design choices rendering neural application predictable and effective. The book provides an intuitive explanation of each method for each network paradigm. This discussion is supported by a rigorous mathematical approach where necessary. C++ has emerged as a rich and descriptive means by which concepts, models, or algorithms can be precisely described. For many of the neural network models discussed, C++ programs are presented for the actual implementation. Pictorial diagrams and in-depth discussions explain each topic. Necessary derivative steps for the mathematical models are included so that readers can incorporate new ideas into their programs as the field advances with new developments. For each approach, the authors clearly state the known theoretical results, the known tendencies of the approach, and their recommendations for getting the best results from the method. The material covered in the book is accessible to working engineers with little or no explicit background in neural networks. However, the material is presented in sufficient depth so that those with prior knowledge will find this book beneficial. Pattern Recognition with Neural Networks in C++ is also suitable for courses in neural networks at an advanced undergraduate or graduate level. This book is valuable for academic as well as practical research.

IntroductionPattern Recognition SystemsMotivation for Artificial Neural Network ApproachA Prelude to Pattern RecognitionStatistical Pattern RecognitionSyntactic Pattern RecognitionThe Character Recognition ProblemOrganization of TopicsNeural Networks: An OverviewMotivation for Overviewing Biological Neural NetworksBackgroundBiological Neural NetworksHierarchical Organization of the BrainHistorical BackgroundArtificial Neural NetworksPreprocessingGeneralDealing with Input from a Scanned ImageImage CompressionEdge DetectionSkeletonizingDealing with Input from a TabletSegmentationFeed Forward Networks with Supervised LearningFeed-Forward Multilayer Perceptron (FFMLP) ArchitectureFFMLP in C++Training with Back PropagationA Primitive Example Training Strategies and Avoiding Local MinimaVariations on Gradient DescentTopologyACON vs. OCONOvertraining and GeneralizationTraining Set Size and Network SizeConjugate Gradient MethodALOPEXSome Other Types of Neural NetworksGeneralRadial Basis Function NetworksHigher Order Neural NetworksFeature Extraction I: Geometric Features and TransformationsGeneralGeometric Features (Loops, Intersections and Endpoints) Feature MapsA Network Example Using Geometric Features Feature Extraction Using TransformationsFourier DescriptorsGabor Transformations and WaveletsFeature Extraction II: Principle Component AnalysisDimensionality ReductionPrincipal ComponentsKarhunen-Loeve (K-L) TransformationPrincipal Component Neural NetworksApplicationsKohonen Networks and Learning Vector QuantizationGeneralK-Means AlgorithmAn Introduction to the Kohonen ModelThe Role of Lateral FeedbackKohonen Self-Organizing Feature MapLearning Vector QuantizationVariations on LVQ Neural Associative Memories and Hopfield NetworksGeneralLinear Associative Memory (LAM)Hopfield NetworksA Hopfield ExampleDiscussionBit Map ExampleBAM NetworksA BAM ExampleAdaptive Resonance Theory (ART)GeneralDiscovering the Cluster StructureVector QuantizationART PhilosophyThe Stability-Plasticity DilemmaArt1: Basic OperationArt1: AlgorithmThe Gain Control MechanismART2 ModelDiscussionApplicationsNeocognitionIntroductionArchitectureExample of a System with Sample Training PatternsSystems with Multiple ClassifiersGeneralA Framework for Combining Multiple RecognizersVoting SchemesThe Confusion MatrixReliabilitySome Empirical Approaches

Pandya\, Abhijit S.; Macy\, Robert B.