ANNOUNCING
THE FAST & EASY WAY TO MASTER NEURAL NETWORKS
For people interested in statistics, machine learning, data analysis, data mining, and future handson practitioners seeking a career in the field, it sets a strong foundation, delivers the prerequisite knowledge, and whets your appetite for more.
This rich, fascinating, accessible hands on guide, puts neural networks firmly into the hands of the practitioner. It reveals how they work, and takes you under the hood with an easy to follow process showing you how to build them faster than you imagined possible using the powerful, free R predictive analytics package.
Everything you need to get started is contained within this book. It is your detailed, practical, tactical hands on guide. To accelerate your success, it contains exercises with fully worked solutions also provided. Once you have mastered the process, it will be easy for you to translate your knowledge into other powerful applications. A book for everyone interested in machine learning, predictive analytics, neural networks and decision science. Here is what it can do for you:

Table of Contents
Acknowledgements Preface Introduction Who Uses Neural Networks? What Problems Can Neural Networks Solve How to Get the Most from this Book Notes PART I: MultiLayer Perceptron Chapter 1: MLP in a Nutshell The Role of the Neuron Neural Network Learning Practical Applications Sheet Sediment Transport Stock Market Volatility Trauma Survival Brown Trout Reds Chlorophyll Dynamics Notes Chapter 2: Building a Single Layer MLP Which Packages Should I Use? Understanding Your Data Role of Standardization How to Choose the Optimal Number of Nodes Creating a Neural Network Formula Ensuring Reproducible Results Estimating the Model Predicting New Cases Exercises Notes Chapter 3: Building MLPs With More Than One Layer How Many Hidden Layers should I choose? Dealing With Local Minima Building the Model Understanding the Weight Vectors Predicting Class Outcomes Exercises Notes Chapter 4: Using Multiple Models Estimating Alternative Models Combining Predictions A Practical Alternative to Backpropagation Bootstraping the Error Exercises Notes PART II: Probabilistic Neural Network Chapter 5: Understanding PNNs How PNNs Work Why Use PNNs? Practical Applications Leaf Recognition Emotional Speech in Children Grading Pearl Quality Classification of Enzymes Notes Chapter 6: Classification Using a PNN Loading the Appropriate Packages Getting the Data Dealing with Missing Values Building the Model How to Choose the Optimal Smoothing Parameter Assessing Training Sample Performance Assessing Prediction Accuracy Exercises Notes PART III: Generalized Regression Network Chapter 7: The GRNN Model What is GRNN Used For? The Role of each Layer Practical Applications Surface Radiation Swine Gas Design Optimization of Brushless DC Motors Notes Chapter 8: Regression Using GRNNs Getting the Required Packages and Data Prepare Data How to Estimate the Model Building Predictions Exercises Notes PART IV: Recurrent Neural Networks Chapter 9: Elman Neural Networks Role of Context Layer Neurons Understanding the Information Flow Advantages of Elman Neural Networks Practical Applications Weather Forecasting Urban Rail Auxiliary Inverter Fault Prediction Forecasting the Quality of Water Forecasting the Stock Market Notes Chapter 10: Building Elman Networks Loading the Required Packages Getting and Cleaning the Data Transforming the Data How to Estimate the Model Prediction with an Elman Network Exercises Notes Chapter 11: Jordan Neural Networks Practical Applications Wind Forecasting Classification of ProteinProtein interaction Recognizing Spanish Digits Notes Chapter 12: Modeling with Jordan Networks Loading the Required Packages How to Transform Your Data Selecting the Training Sample How to Estimate the Model Exercises Notes Solutions to Exercises Appendix Index 