Exploring Neural Networks with C#

This book presents the important properties of neural networks-while keeping mathematics to a minimum. Explaining how to build neural networks and use them, the book presents complicated information about neural networks structure, functioning, and learning in a manner that is easy to understand. Taking a "learn-by-doing" approach, the book is filled with illustrations to guide readers through the mystery of neural networks. Examples of experiments are provided in the text to encourage individual research. C# programs are also included to help readers independently discover the properties of neural networks.

The utility of artificial neural network models lies in the fact that they can be used to infer functions from observations—making them especially useful in applications where the complexity of data or tasks makes the design of such functions by hand impractical.Exploring Neural Networks with C# presents the important properties of neural networks—while keeping the complex mathematics to a minimum. Explaining how to build and use neural networks, it presents complicated information about neural networks structure, functioning, and learning in a manner that is easy to understand.Taking a "learn by doing" approach, the book is filled with illustrations to guide you through the mystery of neural networks. Examples of experiments are provided in the text to encourage individual research. Online access to C# programs is also provided to help you discover the properties of neural networks.Following the procedures and using the programs included with the book will allow you to learn how to work with neural networks and evaluate your progress. You can download the programs as both executable applications and C# source code from http://home.agh.edu.pl/~tad//index.php?page=programy&lang=en

Introduction to Natural and Artificial Neural NetworksWhy Learn about Neural Networks? From Brain Research to Artificial Neural NetworksConstruction of First Neural NetworksLayered Construction of Neural NetworkFrom Biological Brain to First Artificial Neural NetworkCurrent Brain Research MethodsUsing Neural Networks to Study the Human MindSimplification of Neural Networks: Comparison with Biological NetworksMain Advantages of Neural NetworksNeural Networks as Replacements for Traditional ComputersWorking with Neural NetworksReferencesNeural Net StructureBuilding Neural NetsConstructing Artificial NeuronsAttempts to Model Biological NeuronsHow Artificial Neural Networks WorkImpact of Neural Network Structure on CapabilitiesChoosing Neural Network Structures Wisely"Feeding" Neural Networks: Input LayersNature of Data: The Home of the CowInterpreting Answers Generated by Networks: Output LayersPreferred Result: Number or Decision?Network Choices: One Network with Multiple Outputs versus Multiple Networks with Single OutputsHidden LayersDetermining Numbers of NeuronsReferencesQuestions and Self-Study TasksTeaching NetworksNetwork TutoringSelf-LearningMethods of Gathering InformationOrganizing Network LearningLearning FailuresUse of MomentumDuration of Learning ProcessTeaching Hidden LayersLearning without TeachersCautions Surrounding Self-LearningQuestions and Self-Study TasksFunctioning of Simplest NetworksFrom Theory to Practice: Using Neural NetworksCapacity of Single NeuronExperimental ObservationsManaging More InputsNetwork FunctioningConstruction of Simple Linear Neural NetworkUse of NetworkRivalry in Neural NetworksAdditional ApplicationsQuestions and Self-Study TasksTeaching Simple Linear One-Layer Neural NetworksBuilding Teaching FileTeaching One Neuron"Inborn" Abilities of NeuronsCautionsTeaching Simple NetworksPotential Uses for Simple Neural NetworksTeaching Networks to Filter SignalsQuestions and Self-Study TasksNonlinear NetworksAdvantages of NonlinearityFunctioning of Nonlinear NeuronsTeaching Nonlinear NetworksDemonstrating Actions of Nonlinear NeuronsCapabilities of Multilayer Networks of Nonlinear NeuronsNonlinear Neuron Learning SequenceExperimentation during Learning PhaseQuestions and Self-Study TasksBackpropagationDefinitionChanging Thresholds of Nonlinear CharacteristicsShapes of Nonlinear CharacteristicsFunctioning of Multilayer Network Constructed of Nonlinear ElementsTeaching Multilayer NetworksObservations during TeachingReviewing Teaching ResultsQuestions and Self-Study TasksForms of Neural Network LearningUsing Multilayer Neural Networks for RecognitionImplementing a Simple Neural Network for RecognitionSelecting Network Structure for ExperimentsPreparing Recognition TasksObservation of LearningAdditional ObservationsQuestions and Self-Study TasksSelf-Learning Neural NetworksBasic ConceptsObservation of Learning ProcessesEvaluating Progress of Self-TeachingNeuron Responses to Self-TeachingImagination and ImprovisationRemembering and ForgettingSelf-Learning TriggersBenefits from CompetitionResults of Self-Learning with CompetitionQuestions and Self-Study TasksSelf-Organizing Neural NetworksStructure of Neural Network to Create Mappings Resulting from Self-OrganizingUses of Self-OrganizationImplementing Neighborhood in NetworksNeighbor NeuronsUses of Kohonen NetworksKohonen Network Handling of Difficult DataNetworks with Excessively Wide Ranges of Initial WeightsChanging Self-Organization via Self-LearningPractical Uses of Kohonen NetworksTool for Transformation of Input Space DimensionsQuestions and Self-Study TasksRecurrent NetworksDescription of Recurrent Neural NetworkFeatures of Networks with FeedbackBenefits of Associative MemoryConstruction of Hopfield NetworkFunctioning of Neural Network as Associative MemoryProgram for Examining Hopfield Network OperationsInteresting ExamplesAutomatic Pattern Generation for Hopfield NetworkStudies of Associative MemoryOther Observations of Associative MemoryQuestions and Self-Study TasksIndex