R Deep learning essentials : build automatic classification and prediction models using unsupervised learning / Joshua F. Wiley.

Online resource; title from PDF title page (EBSCO, viewed April 19, 2016).

Includes bibliographical references and index.

Annotation Build automatic classification and prediction models using unsupervised learningAbout This Book Harness the ability to build algorithms for unsupervised data using deep learning concepts with R Master the common problems faced such as overfitting of data, anomalous datasets, image recognition, and performance tuning while building the models Build models relating to neural networks, prediction and deep predictionWho This Book Is ForThis book caters to aspiring data scientists who are well versed with machine learning concepts with R and are looking to explore the deep learning paradigm using the packages available in R. You should have a fundamental understanding of the R language and be comfortable with statistical algorithms and machine learning techniques, but you do not need to be well versed with deep learning concepts.What You Will Learn Set up the R package H2O to train deep learning models Understand the core concepts behind deep learning models Use Autoencoders to identify anomalous data or outliers Predict or classify data automatically using deep neural networks Build generalizable models using regularization to avoid overfitting the training dataIn DetailDeep learning is a branch of machine learning based on a set of algorithms that attempt to model high-level abstractions in data by using model architectures. With the superb memory management and the full integration with multi-node big data platforms, the H2O engine has become more and more popular among data scientists in the field of deep learning.This book will introduce you to the deep learning package H2O with R and help you understand the concepts of deep learning. We will start by setting up important deep learning packages available in R and then move towards building models related to neural networks, prediction, and deep prediction, all of this with the help of real-life examples.After installing the H2O package, you will learn about prediction algorithms. Moving ahead, concepts such as overfitting data, anomalous data, and deep prediction models are explained. Finally, the book will cover concepts relating to tuning and optimizing models.Style and approachThis book takes a practical approach to showing you the concepts of deep learning with the R programming language. We will start with setting up important deep learning packages available in R and then move towards building models related to neural network, prediction, and deep prediction - and all of this with the help of real-life examples.

Cover; Copyright; Credits; About the Author; About the Reviewer; www.PacktPub.com; Table of Contents; Preface; Chapter 1: Getting Started with Deep Learning; Chapter 2: Training a Prediction Model; Chapter 3: Preventing Overfitting; Chapter 4: Identifying Anomalous Data; Chapter 5: Training Deep Prediction Models; Chapter 6: Tuning and Optimizing Models; Appendix: Bibliography; Index; What is deep learning?; R packages for deep learning; Connecting R and H2O; Summary; Neural networks in R; The problem of overfitting data -- the consequences explained

Use case -- build and apply a neural networkSummary; L1 penalty; L2 penalty; Ensembles and model averaging; Use case -- improving out-of-sample model performance using dropout; Summary; Getting started with unsupervised learning; How do auto-encoders work?; Training an auto-encoder in R; Use case: building and applying an auto-encoder model; Fine-tuning auto-encoder models; Summary; Getting started with deep feedforward neural networks; Common activation functions -- rectifiers, hyperbolic tangent, and maxout; Picking hyperparameters; Training and predicting new data from a deep neural network

Use case -- training a deep neural network for automatic classificationSummary; Dealing with missing data; Solutions for models with low accuracy; Summary; Conceptual overview of neural networks; Deep neural networks; Setting up reproducible results; Neural networks; The deepnet package; The darch package; The H2O package; Initializing H2O; Linking datasets to an H2O cluster; Building a neural network; Generating predictions from a neural network; L1 penalty in action; L2 penalty in action; Weight decay (L2 penalty in neural networks); Regularized auto-encoders; Working with model results

Grid searchRandom search; Penalized auto-encoders; Denoising auto-encoders

eBooks on EBSCOhost EBSCO eBook Subscription Academic Collection - Worldwide