售 价:¥
温馨提示:数字商品不支持退换货,不提供源文件,不支持导出打印
为你推荐
Preface
About the Book
About the Authors
Learning Objectives
Audience
Approach
Hardware Requirements
Software Requirements
Conventions
Installation and Setup
Installing the Code Bundle
Additional Resources
Chapter 1
Introduction to Machine Learning with Keras
Introduction
Data Representation
Tables of Data
Loading Data
Exercise 1: Loading a Dataset from the UCI Machine Learning Repository
Data Preprocessing
Exercise 2: Cleaning the Data
Appropriate Representation of the Data
Exercise 3: Appropriate Representation of the Data
Life Cycle of Model Creation
Machine Learning Libraries
scikit-learn
Keras
Advantages of Keras
Disadvantages of Keras
More than Building Models
Model Training
Classifiers and Regression Models
Classification Tasks
Regression Tasks
Training and Test Datasets
Model Evaluation Metrics
Exercise 4: Creating a Simple Model
Model Tuning
Baseline Models
Exercise 5: Determining a Baseline Model
Regularization
Cross-Validation
Activity 1: Adding Regularization to the Model
Summary
Chapter 2
Machine Learning versus Deep Learning
Introduction
Advantages of ANNs over Traditional Machine Learning Algorithms
Advantages of Traditional Machine Learning Algorithms over ANNs
Hierarchical Data Representation
Linear Transformations
Scalars, Vectors, Matrices, and Tensors
Tensor Addition
Exercise 6: Perform Various Operations with Vectors, Matrices, and Tensors
Reshaping
Matrix Transposition
Exercise 7: Matrix Reshaping and Transposition
Matrix Multiplication
Exercise 8: Matrix Multiplication
Exercise 9: Tensor Multiplication
Introduction to Keras
Layer Types
Activation Functions
Model Fitting
Activity 2: Creating a Logistic Regression Model Using Keras
Summary
Chapter 3
Deep Learning with Keras
Introduction
Building Your First Neural Network
Logistic Regression to a Deep Neural Network
Activation Functions
Forward Propagation for Making Predictions
Loss Function
Backpropagation for Computing Derivatives of Loss Function
Gradient Descent for Learning Parameters
Exercise 10: Neural Network Implementation with Keras
Activity 3: Building a Single-Layer Neural Network for Performing Binary Classification
Model Evaluation
Evaluating a Trained Model with Keras
Splitting Data into Training and Test Sets
Underfitting and Overfitting
Early Stopping
Activity 4: Diabetes Diagnosis with Neural Networks
Summary
Chapter 4
Evaluate Your Model with Cross-Validation using Keras Wrappers
Introduction
Cross-Validation
Drawbacks of Splitting a Dataset Only Once
K-Fold Cross-Validation
Leave-One-Out Cross-Validation
Comparing the K-Fold and LOO Methods
Cross-Validation for Deep Learning Models
Keras Wrapper with scikit-learn
Exercise 11: Building the Keras Wrapper with scikit-learn for a Regression Problem
Cross-Validation with scikit-learn
Cross-Validation Iterators in scikit-learn
Exercise 12: Evaluate Deep Neural Networks with Cross-Validation
Activity 5: Model Evaluation Using Cross-Validation for a Diabetes Diagnosis Classifier
Model Selection with Cross-validation
Cross-Validation for Model Evaluation versus Model Selection
Exercise 13: Write User-Defined Functions to Implement Deep Learning Models with Cross-Validation
Activity 6: Model Selection Using Cross-Validation for the Diabetes Diagnosis Classifier
Activity 7: Model Selection Using Cross-validation on the Boston House Prices Dataset
Summary
Chapter 5
Improving Model Accuracy
Introduction
Regularization
The Need for Regularization
Reducing Overfitting with Regularization
L1 and L2 Regularization
L1 and L2 Regularization Formulation
L1 and L2 Regularization Implementation in Keras
Activity 8: Weight Regularization on a Diabetes Diagnosis Classifier
Dropout Regularization
Principles of Dropout Regularization
Reducing Overfitting with Dropout
Exercise 14: Dropout Implementation in Keras
Activity 9: Dropout Regularization on Boston Housing Dataset
Other Regularization Methods
Early Stopping
Exercise 15: Implementing Early Stopping in Keras
Data Augmentation
Adding Noise
Hyperparameter Tuning with scikit-learn
Grid Search with scikit-learn
Randomized Search with scikit-learn
Activity 10: Hyperparameter Tuning on the Diabetes Diagnosis Classifier
Summary
Chapter 6
Model Evaluation
Introduction
Accuracy
Exercise 16: Calculating Null Accuracy on a Dummy Healthcare Dataset
Advantages and Limitations of Accuracy
Imbalanced Datasets
Working with Imbalanced Datasets
Confusion Matrix
Metrics Computed from a Confusion Matrix
Exercise 17: Computing Accuracy and Null Accuracy with Healthcare Data
Activity 11: Computing the Accuracy and Null Accuracy of a Neural Network When We Change the Train/Test Split
Activity 12: Derive and Compute Metrics Based on a Confusion Matrix
Exercise 18: Calculate the ROC and AUC Curves
Summary
Chapter 7
Computer Vision with Convolutional Neural Networks
Introduction
Computer Vision
Convolutional Neural Networks
Architecture of a CNN
Input Image
Convolution Layer
Pooling Layer
Flattening
Image Augmentation
Advantages of Image Augmentation
Exercise 19: Build a CNN and Identify Images of Cats and Dogs
Activity 13: Amending our Model with Multiple Layers and the Use of SoftMax
Exercise 20: Amending our model by reverting to the Sigmoid activation function
Exercise 21: Changing the Optimizer from Adam to SGD
Exercise 22: Classifying a New Image
Activity 14: Classify a New Image
Summary
Chapter 8
Transfer Learning and Pre-Trained Models
Introduction
Pre-Trained Sets and Transfer Learning
Feature Extraction
Fine-Tuning a Pre-Trained Network
The ImageNet Dataset
Some Pre-Trained Networks in Keras
Exercise 23: Identify an Image Using the VGG16 Network
Activity 15: Use the VGG16 Network to Train a Deep Learning Network to Identify Images
Exercise 24: Classification of Images That Are Not Present in the ImageNet Database.
Exercise 25: Fine-Tune the VGG16 Model
Exercise 26: Image Classification with ResNet
Activity 16: Image Classification with ResNet
Summary
Chapter 9
Sequential Modeling with Recurrent Neural Networks
Introduction
Sequential Memory and Sequential Modeling
Recurrent Neural Networks (RNNs)
The Vanishing Gradient Problem
Long Short-Term Memory (LSTM)
Exercise 27: Predict the Trend of Apple's Stock Price Using an LSTM with 50 Units (Neurons)
Activity 17: Predict the Trend of Microsoft's Stock Price Using an LSTM with 50 Units (Neurons)
Exercise 28: Predicting the Trend of Apple's Stock Price Using an LSTM with 100 units
Activity 18: Predicting Microsoft's Stock Price with Added Regularization
Activity 19: Predicting the Trend of Microsoft's Stock Price Using an LSTM with an Increasing Number of LSTM Neurons (100 Units)
Summary
Appendix
Chapter 1: Introduction to Machine Learning with Keras
Activity 1: Adding Regularization to the Model
Chapter 2: Machine Learning versus Deep Learning
Activity 2: Creating a Logistic Regression Model Using Keras
Chapter 3: Deep Learning with Keras
Activity 3: Building a Single-Layer Neural Network for Performing Binary Classification
Activity 4: Diabetes Diagnosis with Neural Networks
Chapter 4: Evaluate Your Model with Cross-Validation with Keras Wrappers
Activity 5: Model Evaluation Using Cross-Validation for a Diabetes Diagnosis Classifier
Activity 6: Model Selection Using Cross-Validation for the Diabetes Diagnosis Classifier
Activity 7: Model Selection Using Cross-validation on the Boston House Prices Dataset
Chapter 5: Improving Model Accuracy
Activity 8: Weight Regularization on a Diabetes Diagnosis Classifier
Activity 9: Dropout Regularization on Boston House Prices Dataset
Activity 10: Hyperparameter Tuning on the Diabetes Diagnosis Classifier
Chapter 6: Model Evaluation
Activity 11: Computing Accuracy and Null Accuracy of Neural Network When We Change the Train/Test Split
Activity 12: Derive and Compute Metrics Based on the Confusion Matrix
Chapter 7: Computer Vision with Convolutional Neural Networks
Activity 13: Amending our Model with Multiple Layers and Use of SoftMax
Activity 14: Classify a New Image
Chapter 8: Transfer Learning and Pre-trained Models
Activity 15: Use the VGG16 Network to Train a Deep Learning Network to Identify Images
Activity 16: Image Classification with ResNet
Chapter 9: Sequential Modeling with Recurrent Neural Networks
Activity 17: Predict the Trend of Microsoft’s Stock Price Using an LSTM with 50 Units (Neurons)
Activity 18: Predicting Microsoft’s stock price with added regularization
Activity 19: Predicting the Trend of Microsoft’s Stock Price Using LSTM with 100 Units
买过这本书的人还买过
读了这本书的人还在读
同类图书排行榜