Index
A
- Akaike information criterion (AIC) / Laplace approximation
- allele frequencies
- about / Beta distribution
- arm package
- about / The arm package
- association rule mining
B
- Bayesian averaging
- about / Bayesian averaging
- Bayesian classification models
- exercises / Exercises
- Bayesian inference
- Bayesian view of uncertainty / Bayesian view of uncertainty
- exercises / Exercises
- for machine learning / Why Bayesian inference for machine learning?
- Bayesian information criterion (BIC) / Laplace approximation
- Bayesian logistic regression model
- about / The Bayesian logistic regression model
- BayesLogit R package / The BayesLogit R package
- dataset / The dataset
- training, preparing for / Preparation of the training and testing datasets
- datasets testing, preparing for / Preparation of the training and testing datasets
- using / Using the Bayesian logistic model
- Bayesian mixture models
- about / Bayesian mixture models
- bgmm package / The bgmm package for Bayesian mixture models
- Bayesian modeling, at Big Data scale
- exercises / Exercises
- Bayesian models, for unsupervised learning
- exercises / Exercises
- Bayesian neural networks
- exercises / Exercises
- Bayesian Output Analysis Program (BOA) / R packages for Gibbs sampling
- Bayesian regression models
- exercises / Exercises
- Bayesian theorem
- about / Bayesian theorem
- Bayesian treatment, of neural networks
- Bayesian view of uncertainty
- about / Bayesian view of uncertainty
- prior distribution, selecting / Choosing the right prior distribution
- posterior distribution, estimation / Estimation of posterior distribution
- future observations, predicting / Prediction of future observations
- BayesLogit R package
- about / The BayesLogit R package
- Beta distribution
- about / Beta distribution
- bgmm package
- about / Bayesian mixture models
- fully supervised GMM / The bgmm package for Bayesian mixture models
- semi-supervised GMM / The bgmm package for Bayesian mixture models
- partially supervised GMM / The bgmm package for Bayesian mixture models
- unsupervised GMM / The bgmm package for Bayesian mixture models
- bias-variance tradeoff
- binomial distribution
- about / Binomial distribution
- binomlogit package / R packages for Gibbs sampling
- Bmk / R packages for Gibbs sampling
- BoomSpikeSlab package / R packages for Gibbs sampling
- brnn R package
- about / The brnn R package
C
- CD-1 algorithm / Restricted Boltzmann machines
- CD-k algorithm / Restricted Boltzmann machines
- central limit theorem / Probability distributions
- classification
- clustering
- clusters, computing on cloud
- about / Computing clusters on the cloud
- Amazon Web Services / Amazon Web Services
- computing instances, running on AWS / Creating and running computing instances on AWS
- computing instances, creating / Creating and running computing instances on AWS
- R, installing / Installing R and RStudio
- RStudio, installing / Installing R and RStudio
- Spark, running on EC2 / Running Spark on EC2
- Microsoft Azure / Microsoft Azure
- IBM Bluemix / IBM Bluemix
- common machine learning tasks
- overview / An overview of common machine learning tasks
- classification / An overview of common machine learning tasks
- regression / An overview of common machine learning tasks
- clustering / An overview of common machine learning tasks
- association rules / An overview of common machine learning tasks
- forecasting / An overview of common machine learning tasks
- dimensional reduction / An overview of common machine learning tasks
- density estimation / An overview of common machine learning tasks
- Comprehensive R Archive Network (CRAN) / Installing R and RStudio
- conditional probability
- about / Conditional probability
- conjugate distributions / Conjugate priors
- conjugate prior for the likelihood function / Conjugate priors
- Contrastive Divergence (CD) / Restricted Boltzmann machines
- Correlated Topic Models (CTM)
- about / The topicmodels package
- covariance
- about / Expectations and covariance
- Cuda (C++) / Other deep learning packages in R
- curse of dimensionality
D
- darch R package / The darch R package
- data, managing in R
- about / Managing data in R
- data types / Data Types in R
- data structures / Data structures in R
- data, importing into R / Importing data into R
- datasets, slicing / Slicing and dicing datasets
- datasets, dicing / Slicing and dicing datasets
- vectorized operations / Vectorized operations
- data structures, R
- homogeneous / Data structures in R
- heterogeneous / Data structures in R
- data types, R
- integer / Data Types in R
- complex / Data Types in R
- numeric / Data Types in R
- character / Data Types in R
- logical / Data Types in R
- data visualization
- about / Data visualization
- high-level plotting functions / High-level plotting functions
- low-level plotting commands / Low-level plotting commands
- interactive graphics functions / Interactive graphics functions
- DBN-DNN architecture / Deep belief networks
- deep belief nets (DBN) / Deep belief networks and deep learning
- deep belief networks
- about / Deep belief networks and deep learning, Deep belief networks
- restricted Boltzmann machine (RBM) / Restricted Boltzmann machines
- darch R package / The darch R package
- deep learning packages / Other deep learning packages in R
- deep learning
- deepnet / Other deep learning packages in R
- density estimation
- dimensional reduction
- Dirichlet distribution
- about / Dirichlet distribution
- distributed computing
- with Hadoop / Distributed computing using Hadoop
- divergence
- about / Variational approximation
E
- econometrics
- about / Gamma distribution
- Elastic Computing Cloud (EC2) / Amazon Web Services
- Energy efficiency dataset
- about / The Energy efficiency dataset
- energy function / Restricted Boltzmann machines
- Evolutionary Monte Carlo (EMC) algorithm package / R packages for the Metropolis-Hasting algorithm
- exercises
- about / Exercises
- expectation-maximization (EM) algorithm / Bayesian mixture models
- expectations
- about / Expectations and covariance
F
- false negative or type II error
- false positive or type I error
- foreach / Other R packages for large scale machine learning
- foreach R package / The foreach R package
- forecasting
G
- Gamma distribution
- about / Gamma distribution
- Gaussian mixture model (GMM) / Bayesian mixture models
- generalized linear regression
- about / Generalized linear regression
- general purpose graphical processing units (GPGPUs) / Deep belief networks and deep learning
- ggmcmc package / R packages for Gibbs sampling
- ggplot2 / Data visualization
- ggplot2 package / Bayesian regression
- gibbs.met package
- R packages / R packages for Gibbs sampling
- GibbsACOV package / R packages for Gibbs sampling
- Gibbs sampling
- about / Gibbs sampling
- R packages / R packages for Gibbs sampling
- gradient vanishing problem / Deep belief networks
- grid / Data visualization
H
- Hadoop
- Hadoop Distributed File System (HDFS) / RHadoop for using Hadoop from R
- high-level plotting functions
- about / High-level plotting functions
I
- IBM Bluemix
- about / IBM Bluemix
- integrated Development environment (IDE) / Installing R and RStudio
- interactive graphics functions
- about / Interactive graphics functions
K
- kernel density estimation (KDE)
L
- Laplace approximation / Laplace approximation
- Latent Dirichlet allocation (LDA) / An overview of common machine learning tasks
- about / Latent Dirichlet allocation, The lda package
- R packages / R packages for LDA
- lattice / Data visualization
- lda package / R packages for Gibbs sampling
- about / The lda package
- linear regression
- using SparkR / Linear regression using SparkR
- logit function
- loop functions, R programs
- low-level plotting commands
- about / Low-level plotting commands
M
- MapReduce
- marginal distribution
- about / Marginal distribution
- marginalization
- about / Marginal distribution
- Markov Chain Monte Carlo (MCMC) simulations
- about / Monte Carlo simulations
- maximum a posteriori (MAP) estimation / Maximum a posteriori estimation
- maximum likelihood estimate / Bayesian view of uncertainty
- maximum likelihood method / Bayesian mixture models
- MCMCglm package / R packages for Gibbs sampling
- mcmc package / R packages for the Metropolis-Hasting algorithm
- Metropolis-Hasting algorithm
- about / The Metropolis-Hasting algorithm
- R packages / R packages for the Metropolis-Hasting algorithm
- MHadaptive / R packages for the Metropolis-Hasting algorithm
- Microsoft Azure
- about / Microsoft Azure
- miles per gallon (mpg) / Exercises
- mixed membership stochastic block model (MMSB)
- about / The lda package
- model overfitting
- model regularization
- about / Model regularization
- Ridge regression / Model regularization
- Lasso / Model regularization
- models selection
- about / Selecting models of optimum complexity
- subset selection / Subset selection
- model regularization / Model regularization
- Monte Carlo simulations
- about / Monte Carlo simulations
- Metropolis-Hasting algorithm / The Metropolis-Hasting algorithm
- Gibbs sampling / Gibbs sampling
- multicore / Other R packages for large scale machine learning
N
- Naïve Bayes classifier
- about / The Naïve Bayes classifier
- text processing, with tm package / Text processing using the tm package
- model training and prediction / Model training and prediction
O
- OpenBUGS MCMC package / R packages for Gibbs sampling
- Open Database Connectivity (ODBC) / Importing data into R
P
- parallel / Other R packages for large scale machine learning
- parallel R package / The parallel R package
- partially supervised GMM
- belief( ) function / The bgmm package for Bayesian mixture models
- soft( ) function / The bgmm package for Bayesian mixture models
- partition function / Restricted Boltzmann machines
- PCorpus (permanent corpus) / Text processing using the tm package
- performance metrics, for classification
- Pig
- posterior probability distribution
- about / Bayesian view of uncertainty, Estimation of posterior distribution
- estimation / Estimation of posterior distribution
- maximum a posteriori (MAP) estimation / Maximum a posteriori estimation
- Laplace approximation / Laplace approximation
- Monte Carlo simulations / Monte Carlo simulations
- variational approximation / Variational approximation
- simulating / Simulation of the posterior distribution
- prior probability distribution
- about / Bayesian view of uncertainty
- selecting / Choosing the right prior distribution
- non-informative priors / Non-informative priors
- subjective priors / Subjective priors
- conjugate priors / Conjugate priors
- hierarchical priors / Hierarchical priors
- probability distributions
- about / Probability distributions
- probability mass function (pmf) / Probability distributions
- categorical distribution / Probability distributions
- probability density function (pdf) / Probability distributions
- binomial distribution / Binomial distribution
- Beta distribution / Beta distribution
- Gamma distribution / Gamma distribution
- Dirichlet distribution / Dirichlet distribution
- Wishart distribution / Wishart distribution
R
- R
- installing / Installing R and RStudio, Installing R and RStudio
- program, writing / Your first R program
- data, managing / Managing data in R
- RBugs / R packages for Gibbs sampling
- RcppDL / Other deep learning packages in R
- regression
- regression of energy efficiency, with building parameters
- about / Regression of energy efficiency with building parameters
- ordinary regression / Ordinary regression
- Bayesian regression / Bayesian regression
- R environment
- setting up / Setting up the R environment and packages
- exercises / Exercises
- Resilient Distributed Datasets (RDD)
- restricted Boltzmann machine (RBM) / Restricted Boltzmann machines
- Reuter_50_50 dataset
- about / The topicmodels package
- RHadoop
- about / RHadoop for using Hadoop from R
- for using Hadoop from R / RHadoop for using Hadoop from R
- rhdfs package / RHadoop for using Hadoop from R
- rhbase package / RHadoop for using Hadoop from R
- plyrmr package / RHadoop for using Hadoop from R
- rmr2 package / RHadoop for using Hadoop from R
- risk modeling / Subjective priors
- Rmpi / Other R packages for large scale machine learning
- ROC curve
- RODBC package
- about / Importing data into R
- functions / Importing data into R
- Root Mean Square Error (RMSE) / Exercises
- R package e1071
- about / The Naïve Bayes classifier
- R packages
- R packages, for large scale machine learning
- about / Other R packages for large scale machine learning
- parallel R package / The parallel R package
- foreach R package / The foreach R package
- R packages, for LDA
- about / R packages for LDA
- topicmodels package / The topicmodels package
- lda package / The lda package
- R programs
- writing / Writing R programs
- control structures / Control structures
- functions / Functions
- scoping rules / Scoping rules
- loop functions / Loop functions
- RStudio
- about / Setting up the R environment and packages
- URL / Installing R and RStudio
- installing / Installing R and RStudio, Installing R and RStudio
S
- SamplerCompare package / R packages for Gibbs sampling
- sampling
- about / Sampling
- random uniform sampling, from interval / Random uniform sampling from an interval
- from normal distribution / Sampling from normal distribution
- sigmoid function
- about / Two-layer neural networks
- Simple Storage Service (S3) / Amazon Web Services
- snow / Other R packages for large scale machine learning
- SnowballC package
- softmax
- about / Two-layer neural networks
- Spark
- about / Spark – in-memory distributed computing
- URL / Spark – in-memory distributed computing
- running, on EC2 / Running Spark on EC2
- SparkR
- about / SparkR
- stocc package / R packages for Gibbs sampling
- subsets, of R objects
- Single bracket [ ] / Slicing and dicing datasets
- Double bracket [[ ]] / Slicing and dicing datasets
- Dollar sign $ / Slicing and dicing datasets
- use of negative index values / Slicing and dicing datasets
- subset selection approach
- about / Subset selection
- forward selection / Subset selection
- backward selection / Subset selection
- supervised LDA (sLDA)
- about / The lda package
- support vector machines (SVM) / An overview of common machine learning tasks
T
- Theano / Other deep learning packages in R
- tm package
- topic modeling, with Bayesian inference
- about / Topic modeling using Bayesian inference
- Latent Dirichlet allocation / Latent Dirichlet allocation
- topicmodels package
- about / The topicmodels package
- two-layer neural networks
- about / Two-layer neural networks
U
- Unsupervised( ) function
V
- variational approximation
- about / Variational approximation
- variational calculus problem
- about / Variational approximation
- vbdm package
- about / Variational approximation
- VBmix package
- about / Variational approximation
- vbsr package
- about / Variational approximation
- VCorpus (volatile corpus) / Text processing using the tm package
W
- Wishart distribution
- about / Wishart distribution
- word error rate / Deep belief networks and deep learning