【深度学习书籍】Introduction to Deep Learning Using R pdf _下载

书名：Introduction to Deep Learning Using R: AStep-by-Step Guide to Learning and Implementing Deep Learning Models Using R
作者: Taweh Beysolow II
出版社: Apress
出版年: 2017-8-18

内容简介

Understand deep learning, the nuances of itsdifferent models, and where these models can be applied.

The abundance of data and demand for superiorproducts/services have driven the development of advanced computer sciencetechniques, among them image and speech recognition. Introduction to DeepLearning Using R provides a theoretical and practical understanding of themodels that perform these tasks by building upon the fundamentals of datascience through machine learning and deep learning. This step-by-step guidewill help you understand the disciplines so that you can apply the methodologyin a variety of contexts. All examples are taught in the R statisticallanguage, allowing students and professionals to implement these techniquesusing open source tools.

What You'll Learn

1.Understand the intuition and mathematics thatpower deep learning models

2.Utilize various algorithms using the R programminglanguage and its packages

3.Use best practices for experimental design andvariable selection

4.Practice the methodology to approach andeffectively solve problems as a data scientist

5.Evaluate the effectiveness of algorithmicsolutions and enhance their predictive power

Who This Book Is For

Students, researchers, and data scientists who arefamiliar with programming using R. This book also is also of use for those whowish to learn how to appropriately deploy these algorithms in applicationswhere they would be most useful.

作者简介

TawehBeysolow II is a Machine LearningScientist currently based in the United States with a passion for research andapplying machine learning methods to solve problems. He has a Bachelor ofScience degree in Economics from St. Johns University and a Master of Sciencein Applied Statistics from Fordham University. Currently, he is extremelypassionate about all matters related to machine learning, data science,quantitative finance, and economics.

目录
Chapter 1: What is Deep Learning?

Chapter Goal: Review the historyof Deep Learning, how where the field is today, and discuss the general goalsthat the book has for the reader in their progression.

No of pages10

Chapter 2: A Review of Notation,Vectors and Matrices

Chapter Goal: Establish a senseof understanding in the aforementioned topics within the reader to allow themto understand the models described later. Topics discussed includes thefollowing: Notation, vectors, matrices, inner products, norms, and linearequations.

No of Pages: 50

Apress Proposal Submission Formfor Prospective Authors

Chapter 3: A Review of Optimization

Chapter Goal: Discuss/ReviewOptimization concepts and how it is used in Deep Learning models. Topicsdiscussed include the following: constrained and unconstrained optimization,gradient descent, and newton’s method.

No of pages : 60

Chapter 4: Single LayerArtificial Neural Network (ANNs)

Chapter Goal: Introduce readersto ANNs, it’s uses, the math that powers the model, as well as discussing itslimitations

No of pages: 10

Chapter 5: Deep Neural Networks(Multi-layer ANNs)

Chapter Goal: Establish thedifference between single and multilayer ANNs as well as discuss the nuancesthat are created as a product of having multiple hidden layers

No of pages: 10

Chapter 6: Convolutional NeuralNetworks (CNNs)

Chapter Goal: Build upon theknowledge of neural networks described earlier and begin to branch in the othermodels, such as CNNs. Here, we will establish what a convolutional layer is, inaddition to what the uses of this model are, such as computer vision andprocessing visual data.

No of pages: 10

Apress Proposal Submission Formfor Prospective Authors

Chapter 7: Recurrent NeuralNetworks (RNNs)

Chapter Goal: Describe themathematics and intuition behind RNNs and their use cases, such as handwritingrecognition and speech recognition. Also describe how the unique structurebehind them differentiates themselves from feed forward networks.

No of pages: 10

Chapter 8: Deep Belief Networksand Deep Boltzman Machines

Chapter Goal: Discuss thesimilarities between these two models and how their disadvantages andadvantages in contrast to the prior Deep Learning Models described

No. of pages: 20

Chapter 9: Tuning and TrainingDeep Network Architectures

Chapter Goal: Establish anunderstanding of how to properly train Deep Network models and tune theirparameters as to avoid common pitfalls such as overfitting.

No. of Pages: 20

Chapter 10: Experimental Designand Variable Selection

Chapter Goal: Now that the readerhas an understanding of various Deep Learning Models, and the concepts thatpower them, it is time to establish an understanding of how to properly performexperiments, including the examples given in the later part of the text. Topicsdiscussed include the following: Fisher’s priciples, Plackett-Burman designs,statistical control, and variable selection techniques.
No. of Pages: 60

Chapter 11: Example Problems

Chapter Goal: In this Chapter,the user will be given questions and detailed answer guides in solving thesupervised and unsupervised learning example problems. Problems covered are thefollowing: Regression, Classification, and Image Recognition.

No of Pages: 60

Chapter 12: Conclusion andClosing Commentary

Chapter Goal: Give readersrecommendations on what resources they should seek moving forward givenspecific interests, as well as recommendations for what tools they should userelated to R.

No. of Pages: 5