R Deep Learning Cookbook

Author: Dr. PKS Prakash;Achyutuni Sri Krishna Rao  

Publisher: Packt Publishing‎

Publication year: 2017

E-ISBN: 9781787127111

P-ISBN(Paperback): 9781787121089

Subject: TP Automation Technology , Computer Technology;TP3 Computers

Keyword: 计算技术、计算机技术,自动化技术、计算机技术

Language: ENG

Access to resources Favorite

Disclaimer: Any content in publications that violate the sovereignty, the constitution or regulations of the PRC is not accepted or approved by CNPIEC.

R Deep Learning Cookbook

Description

Powerful, independent recipes to build deep learning models in different application areas using R libraries About This Book • Master intricacies of R deep learning packages such as mxnet & tensorflow • Learn application on deep learning in different domains using practical examples from text, image and speech • Guide to set-up deep learning models using CPU and GPU Who This Book Is For Data science professionals or analysts who have performed machine learning tasks and now want to explore deep learning and want a quick reference that could address the pain points while implementing deep learning. Those who wish to have an edge over other deep learning professionals will find this book quite useful. What You Will Learn • Build deep learning models in different application areas using TensorFlow, H2O, and MXnet. • Analyzing a Deep boltzmann machine • Setting up and Analysing Deep belief networks • Building supervised model using various machine learning algorithms • Set up variants of basic convolution function • Represent data using Autoencoders. • Explore generative models available in Deep Learning. • Discover sequence modeling using Recurrent nets • Learn fundamentals of Reinforcement Leaning • Learn the steps involved in applying Deep Learning in text mining • Explore application of deep learning in signal processing • Utilize Transfer learning for utilizing pre-trained model • Train a deep learning model on a GPU In Detail Deep Learning is the next big thing. It

Chapter

Chapter 1: Getting Started

Introduction

Installing R with an IDE

Getting ready

How to do it...

Installing a Jupyter Notebook application

How to do it...

There's more...

Starting with the basics of machine learning in R

How to do it...

How it works...

Setting up deep learning tools/packages in R

How to do it...

Installing MXNet in R

Getting ready

How to do it...

Installing TensorFlow in R

Getting ready

How to do it...

How it works...

See also

Installing H2O in R

Getting ready

How to do it...

How it works...

There's more...

Installing all three packages at once using Docker

Getting ready

How to do it...

There's more...

Chapter 2: Deep Learning with R

Starting with logistic regression

Getting ready

How to do it...

Introducing the dataset

Getting ready

How to do it...

Performing logistic regression using H2O

Getting ready

How to do it...

How it works...

See also

Performing logistic regression using TensorFlow

Getting ready

How to do it...

How it works...

Visualizing TensorFlow graphs

Getting ready

How to do it...

How it works...

Starting with multilayer perceptrons

Getting ready

How to do it...

There's more...

See also

Setting up a neural network using H2O

Getting ready

How to do it...

How it works...

Tuning hyper-parameters using grid searches in H2O

Getting ready

How to do it...

How it works...

Setting up a neural network using MXNet

Getting ready

How to do it...

How it works...

Setting up a neural network using TensorFlow

Getting ready

How to do it...

How it works...

There's more...

Chapter 3: Convolution Neural Network

Introduction

Downloading and configuring an image dataset

Getting ready

How to do it...

How it works...

See also

Learning the architecture of a CNN classifier

Getting ready

How to do it...

How it works...

Using functions to initialize weights and biases

Getting ready

How to do it...

How it works...

Using functions to create a new convolution layer

Getting ready

How to do it...

How it works...

Using functions to create a new convolution layer

Getting ready

How to do it...

How it works...

Using functions to flatten the densely connected layer

Getting ready

How to do it...

How it works...

Defining placeholder variables

Getting ready

How to do it...

How it works...

Creating the first convolution layer

Getting ready

How to do it...

How it works...

Creating the second convolution layer

Getting ready

How to do it...

How it works...

Flattening the second convolution layer

Getting ready

How to do it...

How it works...

Creating the first fully connected layer

Getting ready

How to do it...

How it works...

Applying dropout to the first fully connected layer

Getting ready

How to do it...

How it works...

Creating the second fully connected layer with dropout

Getting ready

How to do it...

How it works...

Applying softmax activation to obtain a predicted class

Getting ready

How to do it...

Defining the cost function used for optimization

Getting ready

How to do it...

How it works...

Performing gradient descent cost optimization

Getting ready

How to do it...

Executing the graph in a TensorFlow session

Getting ready

How to do it...

How it works...

Evaluating the performance on test data

Getting ready

How to do it...

How it works...

Chapter 4: Data Representation Using Autoencoders

Introduction

Setting up autoencoders

Getting ready

How to do it...

Data normalization

Getting ready

Visualizing dataset distribution

How to do it...

How to set up an autoencoder model

Running optimization

Setting up a regularized autoencoder

Getting ready

How to do it...

How it works...

Fine-tuning the parameters of the autoencoder

Setting up stacked autoencoders

Getting ready

How to do it...

Setting up denoising autoencoders

Getting ready

How to do it...

Reading the dataset

Corrupting data to train

Setting up a denoising autoencoder

How it works...

Building and comparing stochastic encoders and decoders

Getting ready

How to do it...

Setting up a VAE model

Output from the VAE autoencoder

Learning manifolds from autoencoders

How to do it...

Setting up principal component analysis

Evaluating the sparse decomposition

Getting ready

How to do it...

How it works...

Chapter 5: Generative Models in Deep Learning

Comparing principal component analysis with the Restricted Boltzmann machine

Getting ready

How to do it...

Setting up a Restricted Boltzmann machine for Bernoulli distribution input

Getting ready

How to do it...

Training a Restricted Boltzmann machine

Getting ready

Example of a sampling

How to do it...

Backward or reconstruction phase of RBM

Getting ready

How to do it...

Understanding the contrastive divergence of the reconstruction

Getting ready

How to do it...

How it works...

Initializing and starting a new TensorFlow session

Getting ready

How to do it...

How it works...

Evaluating the output from an RBM

Getting ready

How to do it...

How it works...

Setting up a Restricted Boltzmann machine for Collaborative Filtering

Getting ready

How to do it...

Performing a full run of training an RBM

Getting ready

How to do it...

Setting up a Deep Belief Network

Getting ready

How to do it...

How it works...

Implementing a feed-forward backpropagation Neural Network

Getting ready

How to do it...

How it works...

Setting up a Deep Restricted Boltzmann Machine

Getting ready

How to do it...

How it works...

Chapter 6: Recurrent Neural Networks

Setting up a basic Recurrent Neural Network

Getting ready

How to do it...

How it works...

Setting up a bidirectional RNN model

Getting ready

How to do it...

Setting up a deep RNN model

How to do it...

Setting up a Long short-term memory based sequence model

How to do it...

How it works...

Chapter 7: Reinforcement Learning

Introduction

Setting up a Markov Decision Process

Getting ready

How to do it...

Performing model-based learning

How to do it...

Performing model-free learning

Getting ready

How to do it...

Chapter 8: Application of Deep Learning in Text Mining

Performing preprocessing of textual data and extraction of sentiments

How to do it...

How it works...

Analyzing documents using tf-idf

How to do it...

How it works...

Performing sentiment prediction using LSTM network

How to do it...

How it works...

Application using text2vec examples

How to do it...

How it works...

Chapter 9: Application of Deep Learning to Signal processing

Introducing and preprocessing music MIDI files

Getting ready

How to do it...

Building an RBM model

Getting ready

How to do it...

Generating new music notes

How to do it...

Chapter 10: Transfer Learning

Introduction

Illustrating the use of a pretrained model

Getting ready

How to do it...

Setting up the Transfer Learning model

Getting ready

How to do it...

Building an image classification model

Getting ready

How to do it...

Training a deep learning model on a GPU

Getting ready

How to do it...

Comparing performance using CPU and GPU

Getting ready

How to do it...

There's more...

See also

Index

The users who browse this book also browse


No browse record.