最新章節

• Summary
• Anaconda Windows installation
• Windows installation
• Installing remaining libraries via pip
• Installing pip
• Anaconda installation

• Summary 更新時間：2021-07-02 15:47:29
• Anaconda Windows installation
• Windows installation
• Installing remaining libraries via pip
• Installing pip
• Anaconda installation
• macOS X environment installation
• Installing necessary libraries
• Installing pip
• Installing the Python 3 interpreter
• pip Linux installation method
• Installing Anaconda on Linux
• Initial distribution requirements
• Linux installation
• Software Installation and Configuration
• Summary
• References
• Basic RL techniques: Q-learning
• Optimizing the Markov process
• Decision elements
• Markov decision process
• Reinforcement learning
• Discriminative and generative models
• Types of GAN applications
• GANs
• Recent Models and Developments
• References
• Summary
• Dataset preprocessing
• Dataset description and loading
• Univariate time series prediction with energy consumption data
• Part 4 — output filtered cell state
• Part 3 — apply changes to cell
• Part 2 — set values to keep
• Part 1 — set values to forget (input gate)
• The gate and multiplier operation
• LSTM
• Main problems of the traditional RNNs — exploding and vanishing gradients
• Training method — backpropagation through time
• Development of RNN
• Types of sequence to be modeled
• RNN definition
• Solving problems with order — RNNs
• Recurrent Neural Networks
• Summary
• References
• Implementing transfer learning
• Exploring a convolutional network with Quiver
• Exploring a convolutional model with Quiver
• Deploying a deep neural network with Keras
• Segmentation
• Detection
• Classification
• Types of problem solved by deep layers of CNNs
• Residual Networks (ResNet)
• Batch-normalized inception V2 and V3
• GoogLenet and the Inception model
• The VGG model
• Alexnet
• Lenet 5
• Deep convolutional network architectures through time
• Deep neural networks
• Advantages of the dropout layers
• Improving efficiency with the dropout operation
• Subsampling operation (pooling)
• Implementing the 2D discrete convolution operation in an example
• Stride and padding
• Kernels and convolutions
• Discrete convolution
• Continuous convolution
• Getting started with convolution
• Origin of convolutional neural networks
• Convolutional Neural Networks
• References
• Summary
• L1 versus L2 properties
• Defining loss functions for neural networks
• Linear transfer function
• Rectified linear unit or ReLU
• Playing with the sigmoid
• Sigmoid or logistic function
• Representing and understanding the transfer functions
• Defining and graphing transfer function types
• Implementing a simple function with a single-layer perceptron
• Types of problem to be tackled
• The chosen optimization algorithm – backpropagation
• The feedforward mechanism
• MLP origins
• Single and multilayer perceptrons
• Limitations of early models
• Similarities and differences between a perceptron and ADALINE
• Improving our predictions – the ADALINE algorithm
• The perceptron model
• History of neural models
• Neural Networks
• References
• Summary
• Dataset format
• The CHDAGE dataset
• Practical example – cardiac disease modeling with logistic regression
• Multiclass application – softmax regression
• Properties of the logistic function
• The sigmoid or logistic function
• The importance of the logit inverse
• Logit function properties
• Logit function
• Link function
• Logistic function predecessor – the logit functions
• Problem domain of linear regression and logistic regression
• Logistic regression
• Linear regression with gradient descent in practice
• Polynomial regression and an introduction to underfitting and overfitting
• Correlation fit
• Defining the error function
• Creating the prediction function
• Getting an intuitive idea with Seaborn pairplot
• The Iris dataset
• Data exploration and linear regression in practice
• Correlation plot
• Useful diagrams for variable explorations – pairplot
• Going practical – new tools for new methods
• Expressing recursion as a process
• Formalizing our concepts
• The gradient descent loop
• Some intuitive background
• Gradient descent
• Searching for the slope and intercept with covariance and correlation
• Correlation
• Covariance
• Covariance/correlation method
• Pros and cons of the analytical approach
• Analytical approach
• The many ways of minimizing errors
• Determination of the cost function
• Linear regression
• Quantitative versus qualitative variables
• Applications of regression
• Regression analysis
• Linear and Logistic Regression
• References
• Summary
• The Elbow method
• Going beyond the basics
• K-NN sample implementation
• Pros and cons of K-NN
• Mechanics of K-NN
• Nearest neighbors
• K-means implementations
• K-means algorithm breakdown
• Pros and cons of K-means
• Finding a common center - K-means
• Automating the clustering process
• Grouping as a human activity
• Clustering
• References
• Summary
• Homogeneity completeness and V-measure
• Silhouette coefficient
• Clustering quality measurements
• Confusion matrix
• Precision score recall and F-measure
• Accuracy
• Classification metrics
• Mean squared error
• Median absolute error
• Mean absolute error
• Regression metrics
• Model implementation and results interpretation
• Parameter initialization
• Types of training – online and batch processing
• Common training terms – iteration batch and epoch
• Dataset partitioning
• Model fitting and evaluation
• Loss function definition
• Asking ourselves the right questions
• Model definition
• Normalization or standardization
• Normalization and feature scaling
• Dataset preprocessing
• One hot encoding
• Imputation of missing data
• Feature engineering
• Working on 2D data
• Working interactively with IPython
• Loading datasets and doing exploratory analysis with SciPy and pandas
• The ETL process
• Dataset definition and retrieval
• Understanding the problem
• The Learning Process
• Summary
• Partial derivatives
• Chain rule
• Sliding on the slope
• In search of changes–derivatives
• Preliminary knowledge
• Differential calculus elements
• Kurtosis
• Skewness
• Statistical measures for probability functions
• Logistic distribution
• Normal distribution
• Uniform distribution
• Bernoulli distributions
• Useful probability distributions
• Random variables and distributions
• Probability
• Events
• Probability and random variables
• Standard deviation
• Variance
• Mean
• Descriptive statistics - main operations
• Statistics - the basic pillar of modeling uncertainty
• Basic mathematical concepts
• Jupyter notebook
• SciPy
• Pandas
• What's matplotlib?
• The matplotlib library
• The NumPy library
• The Python language
• Tools of the trade–programming language and libraries
• Unsupervised problem solving–clustering
• Supervised learning strategies - regression versus classification
• Grades of supervision
• Types of machine learning
• Machine learning in the bigger picture
• Introduction - Machine Learning and Statistical Science
• Questions
• Piracy
• Errata
• Downloading the example code
• Customer support
• Reader feedback
• Conventions
• Who this book is for
• What you need for this book
• What this book covers
• Preface
• Customer Feedback
• Why subscribe?
• www.PacktPub.com
• About the Reviewers
• About the Author
• Foreword
• Credits
• Machine Learning for Developers
• Copyright
• Title Page
• coverpage

• coverpage
• Title Page
• Copyright
• Machine Learning for Developers
• Credits
• Foreword
• About the Author
• About the Reviewers
• www.PacktPub.com
• Why subscribe?
• Customer Feedback
• Preface
• What this book covers
• What you need for this book
• Who this book is for
• Conventions
• Reader feedback
• Customer support
• Downloading the example code
• Errata
• Piracy
• Questions
• Introduction - Machine Learning and Statistical Science
• Machine learning in the bigger picture
• Types of machine learning
• Grades of supervision
• Supervised learning strategies - regression versus classification
• Unsupervised problem solving–clustering
• Tools of the trade–programming language and libraries
• The Python language
• The NumPy library
• The matplotlib library
• What's matplotlib?
• Pandas
• SciPy
• Jupyter notebook
• Basic mathematical concepts
• Statistics - the basic pillar of modeling uncertainty
• Descriptive statistics - main operations
• Mean
• Variance
• Standard deviation
• Probability and random variables
• Events
• Probability
• Random variables and distributions
• Useful probability distributions
• Bernoulli distributions
• Uniform distribution
• Normal distribution
• Logistic distribution
• Statistical measures for probability functions
• Skewness
• Kurtosis
• Differential calculus elements
• Preliminary knowledge
• In search of changes–derivatives
• Sliding on the slope
• Chain rule
• Partial derivatives
• Summary
• The Learning Process
• Understanding the problem
• Dataset definition and retrieval
• The ETL process
• Loading datasets and doing exploratory analysis with SciPy and pandas
• Working interactively with IPython
• Working on 2D data
• Feature engineering
• Imputation of missing data
• One hot encoding
• Dataset preprocessing
• Normalization and feature scaling
• Normalization or standardization
• Model definition
• Asking ourselves the right questions
• Loss function definition
• Model fitting and evaluation
• Dataset partitioning
• Common training terms – iteration batch and epoch
• Types of training – online and batch processing
• Parameter initialization
• Model implementation and results interpretation
• Regression metrics
• Mean absolute error
• Median absolute error
• Mean squared error
• Classification metrics
• Accuracy
• Precision score recall and F-measure
• Confusion matrix
• Clustering quality measurements
• Silhouette coefficient
• Homogeneity completeness and V-measure
• Summary
• References
• Clustering
• Grouping as a human activity
• Automating the clustering process
• Finding a common center - K-means
• Pros and cons of K-means
• K-means algorithm breakdown
• K-means implementations
• Nearest neighbors
• Mechanics of K-NN
• Pros and cons of K-NN
• K-NN sample implementation
• Going beyond the basics
• The Elbow method
• Summary
• References
• Linear and Logistic Regression
• Regression analysis
• Applications of regression
• Quantitative versus qualitative variables
• Linear regression
• Determination of the cost function
• The many ways of minimizing errors
• Analytical approach
• Pros and cons of the analytical approach
• Covariance/correlation method
• Covariance
• Correlation
• Searching for the slope and intercept with covariance and correlation
• Gradient descent
• Some intuitive background
• The gradient descent loop
• Formalizing our concepts
• Expressing recursion as a process
• Going practical – new tools for new methods
• Useful diagrams for variable explorations – pairplot
• Correlation plot
• Data exploration and linear regression in practice
• The Iris dataset
• Getting an intuitive idea with Seaborn pairplot
• Creating the prediction function
• Defining the error function
• Correlation fit
• Polynomial regression and an introduction to underfitting and overfitting
• Linear regression with gradient descent in practice
• Logistic regression
• Problem domain of linear regression and logistic regression
• Logistic function predecessor – the logit functions
• Link function
• Logit function
• Logit function properties
• The importance of the logit inverse
• The sigmoid or logistic function
• Properties of the logistic function
• Multiclass application – softmax regression
• Practical example – cardiac disease modeling with logistic regression
• The CHDAGE dataset
• Dataset format
• Summary
• References
• Neural Networks
• History of neural models
• The perceptron model
• Improving our predictions – the ADALINE algorithm
• Similarities and differences between a perceptron and ADALINE
• Limitations of early models
• Single and multilayer perceptrons
• MLP origins
• The feedforward mechanism
• The chosen optimization algorithm – backpropagation
• Types of problem to be tackled
• Implementing a simple function with a single-layer perceptron
• Defining and graphing transfer function types
• Representing and understanding the transfer functions
• Sigmoid or logistic function
• Playing with the sigmoid
• Rectified linear unit or ReLU
• Linear transfer function
• Defining loss functions for neural networks
• L1 versus L2 properties
• Summary
• References
• Convolutional Neural Networks
• Origin of convolutional neural networks
• Getting started with convolution
• Continuous convolution
• Discrete convolution
• Kernels and convolutions
• Stride and padding
• Implementing the 2D discrete convolution operation in an example
• Subsampling operation (pooling)
• Improving efficiency with the dropout operation
• Advantages of the dropout layers
• Deep neural networks
• Deep convolutional network architectures through time
• Lenet 5
• Alexnet
• The VGG model
• GoogLenet and the Inception model
• Batch-normalized inception V2 and V3
• Residual Networks (ResNet)
• Types of problem solved by deep layers of CNNs
• Classification
• Detection
• Segmentation
• Deploying a deep neural network with Keras
• Exploring a convolutional model with Quiver
• Exploring a convolutional network with Quiver
• Implementing transfer learning
• References
• Summary
• Recurrent Neural Networks
• Solving problems with order — RNNs
• RNN definition
• Types of sequence to be modeled
• Development of RNN
• Training method — backpropagation through time
• Main problems of the traditional RNNs — exploding and vanishing gradients
• LSTM
• The gate and multiplier operation
• Part 1 — set values to forget (input gate)
• Part 2 — set values to keep
• Part 3 — apply changes to cell
• Part 4 — output filtered cell state
• Univariate time series prediction with energy consumption data
• Dataset description and loading
• Dataset preprocessing
• Summary
• References
• Recent Models and Developments
• GANs
• Types of GAN applications
• Discriminative and generative models
• Reinforcement learning
• Markov decision process
• Decision elements
• Optimizing the Markov process
• Basic RL techniques: Q-learning
• References
• Summary
• Software Installation and Configuration
• Linux installation
• Initial distribution requirements
• Installing Anaconda on Linux
• pip Linux installation method
• Installing the Python 3 interpreter
• Installing pip
• Installing necessary libraries
• macOS X environment installation
• Anaconda installation
• Installing pip
• Installing remaining libraries via pip
• Windows installation
• Anaconda Windows installation
• Summary 更新時間：2021-07-02 15:47:29