عنوان
پدید آورنده
موضوع
رده
QA276.45.R3 .L589 2018
QA276
.
45
.
R3
.
L589
2018
کتابخانه
محل استقرار
INTERNATIONAL STANDARD BOOK NUMBER
(Number (ISBN
1788474554
(Number (ISBN
1788478401
(Number (ISBN
9781788474559
(Number (ISBN
9781788478403
Erroneous ISBN
1788478401
Erroneous ISBN
9781788478403
TITLE AND STATEMENT OF RESPONSIBILITY
Title Proper
R Deep Learning Projects :
General Material Designation
[Book]
Other Title Information
Master the techniques to design and develop neural network models in R.
.PUBLICATION, DISTRIBUTION, ETC
Place of Publication, Distribution, etc.
Birmingham :
Name of Publisher, Distributor, etc.
Packt Publishing,
Date of Publication, Distribution, etc.
2018.
PHYSICAL DESCRIPTION
Specific Material Designation and Extent of Item
1 online resource (253 pages)
GENERAL NOTES
Text of Note
Exploratory data analysis.
INTERNAL BIBLIOGRAPHIES/INDEXES NOTE
Text of Note
Includes bibliographical references and index.
CONTENTS NOTE
Text of Note
Cover; Copyright and Credits; Packt Upsell; Contributors; Table of Contents; Preface; Chapter 1: Handwritten Digit Recognition Using Convolutional Neural Networks; What is deep learning and why do we need it?; What makes deep learning special?; What are the applications of deep learning?; Handwritten digit recognition using CNNs; Get started with exploring MNIST; First attempt â#x80;#x93; logistic regression; Going from logistic regression to single-layer neural networks; Adding more hidden layers to the networks; Extracting richer representation with CNNs; Summary.
Text of Note
Chapter 2: Traffic Sign Recognition for Intelligent VehiclesHow is deep learning applied in self-driving cars?; How does deep learning become a state-of-the-art solution?; Traffic sign recognition using CNN; Getting started with exploring GTSRB; First solution â#x80;#x93; convolutional neural networks using MXNet; Trying something new â#x80;#x93; CNNs using Keras with TensorFlow; Reducing overfitting with dropout; Dealing with a small training set â#x80;#x93; data augmentation; Reviewing methods to prevent overfitting in CNNs; Summary; Chapter 3: Fraud Detection with Autoencoders; Getting ready.
Text of Note
Chapter 4: Text Generation Using Recurrent Neural NetworksWhat is so exciting about recurrent neural networks?; But what is a recurrent neural network, really?; LSTM and GRU networks; LSTM; GRU; RNNs from scratch in R; Classes in R with R6; Perceptron as an R6 class; Logistic regression; Multi-layer perceptron; Implementing a RNN; Implementation as an R6 class; Implementation without R6; RNN without derivatives â#x80;#x94; the cross-entropy method; RNN using Keras; A simple benchmark implementation; Generating new text from old; Exercises; Summary; Chapter 5: Sentiment Analysis with Word Embeddings.
Text of Note
Installing Keras and TensorFlow for RInstalling H2O; Our first examples; A simple 2D example; Autoencoders and MNIST; Outlier detection in MNIST; Credit card fraud detection with autoencoders; Exploratory data analysis; The autoencoder approach â#x80;#x93; Keras; Fraud detection with H2O; Exercises; Variational Autoencoders; Image reconstruction using VAEs; Outlier detection in MNIST; Text fraud detection; From unstructured text data to a matrix; From text to matrix representation â#x80;#x94; the Enron dataset; Autoencoder on the matrix representation; Exercises; Summary.
Text of Note
Warm-up â#x80;#x93; data explorationWorking with tidy text; The more, the merrier â#x80;#x93; calculating n-grams instead of single words; Bag of words benchmark; Preparing the data; Implementing a benchmark â#x80;#x93; logistic regression ; Exercises; Word embeddings; word2vec; GloVe; Sentiment analysis from movie reviews; Data preprocessing; From words to vectors; Sentiment extraction; The importance of data cleansing; Vector embeddings and neural networks; Bi-directional LSTM networks; Other LSTM architectures; Exercises; Mining sentiment from Twitter; Connecting to the Twitter API; Building our model.
0
8
8
8
8
SUMMARY OR ABSTRACT
Text of Note
R is a popular programming language used by statisticians and mathematicians for statistical analysis, and is popularly used for deep learning. This book demonstrates end-to-end implementations of five real-world projects on popular topics in deep learning such as handwritten digit recognition, traffic light detection, fraud detection, text ...
ACQUISITION INFORMATION NOTE
Source for Acquisition/Subscription Address
OverDrive, Inc.
Source for Acquisition/Subscription Address
01201872
Stock Number
361CBCC8-C94D-472D-AC6F-4B0C12C84CBC
Stock Number
B08604
OTHER EDITION IN ANOTHER MEDIUM
Title
R Deep Learning Projects : Master the techniques to design and develop neural network models in R.
TOPICAL NAME USED AS SUBJECT
Artificial intelligence.
Neural networks.
R.
Artificial intelligence.
MATHEMATICS-- Applied.
MATHEMATICS-- Probability & Statistics-- General.
(SUBJECT CATEGORY (Provisional
MAT-- 003000
MAT-- 029000
DEWEY DECIMAL CLASSIFICATION
Number
519
.
502855133
Edition
23
LIBRARY OF CONGRESS CLASSIFICATION
Class number
QA276
.
45
.
R3
Book number
.
L589
2018
PERSONAL NAME - PRIMARY RESPONSIBILITY
Liu, Yuxi (Hayden)
PERSONAL NAME - ALTERNATIVE RESPONSIBILITY
Maldonado, Pablo.
ORIGINATING SOURCE
Date of Transaction
20200823060405.0
Cataloguing Rules (Descriptive Conventions))
pn
ELECTRONIC LOCATION AND ACCESS
Electronic name
مطالعه متن کتاب [Book]
Y
