最新章節

• Leave a review - let other readers know what you think
• Other Books You May Enjoy
• Summary
• Model evaluation
• The training loop
• Building the discriminator

• Leave a review - let other readers know what you think 更新時間：2021-06-24 18:40:56
• Other Books You May Enjoy
• Summary
• Model evaluation
• The training loop
• Building the discriminator
• Building the generator
• Loading CIFAR-10
• Generating CIFAR-10 images using a Keras GAN
• Model evaluation
• The training loop
• Building the stacked model
• Building the discriminator
• Building the generator
• Loading the dataset
• Generating MNIST images using a Keras GAN
• Safe choices for GAN
• Mode collapse
• Stability
• How GANs can fail
• Step 2 – train the stack
• Step 1 – train the discriminator
• Stacked training
• Discriminator architecture
• Generator architecture
• Adversarial training architecture
• Deep Convolutional GAN architecture
• An overview of the GAN
• Generative Adversarial Networks
• Summary
• Results
• Training
• Agent
• Memory and policy
• Lunar Lander network architecture
• Lunar Lander
• Results
• Training
• Agent
• Policy
• Memory
• CartPole neural network architecture
• CartPole
• Building a reinforcement learning agent in Keras
• Using OpenAI gym
• Installing OpenAI gym
• Installing Keras-RL
• The Keras reinforcement learning framework
• DeepMind
• Exploitation versus exploration
• Memory and experience replay
• Online learning
• Deep Q networks
• Infinite state space
• Q Learning
• Markov Decision Processes
• Reinforcement learning overview
• Using Deep Reinforcement Learning
• Summary
• Example translations
• Decoding a sequence
• Translating a sequence
• Loading models
• Creating reverse indices
• Loading data
• Inference
• Training
• Putting it all together
• Network architecture (for inference)
• Training network architecture
• One hot encoding
• Loading data
• Understanding the data
• Machine translation
• Translation metrics
• Attention
• Teacher forcing
• Characters versus words
• Encoders and decoders
• Sequence-to-sequence model architecture
• Sequence-to-sequence model applications
• Sequence-to-sequence models
• Training Seq2Seq Models
• Summary
• Performance
• Training
• Putting it all together
• Output layer
• Convolution layers
• With GloVe vectors
• Without GloVe vectors
• Input and embedding layer architecture
• Loading pretrained word vectors
• Preparing the data
• Document classification with and without GloVe
• Performance
• Training the network
• Putting it all together
• Output layer
• LSTM layer
• Input and embedding layer architecture
• Preparing the data
• Sentiment analysis with Keras embedding layers and LSTMs
• Case studies for document classifications
• 1D CNNs for natural language processing
• Keras embedding layer
• Getting from words to documents
• Learning word embeddings with counting
• Learning word embeddings with prediction
• A quick example
• Word embedding
• Count and TF-IDF vectorization
• Stemming lemmatization and stopwords
• Bag of Word models
• NLP terminology
• Vectorizing text
• Document classification
• Semantic analysis
• An introduction to natural language processing
• Training LSTMs with Word Embeddings from Scratch
• Summary
• Measuring performance
• Training
• Stateful versus stateless LSTMs
• Network architecture
• Network output
• Data preparation glue
• Input shape
• Creating a lagged training set
• Scaling a time series
• Differencing a time series
• Slicing train and test by date
• Loading the dataset
• Data preparation
• Using an LSTM for time series prediction
• ARIMA and ARIMAX forecasting
• Stock and flow
• A refresher on time series problems
• Backpropagation through time
• Long Short Term Memory Networks
• What makes a neuron recurrent?
• Introducing recurrent neural networks
• Training an RNN from scratch
• Summary
• Training (fine-tuning)
• Training (feature extraction)
• Data input
• Data preparation
• Transfer network architecture
• Source network architecture
• Source domain overview
• Target domain overview
• Transfer learning in Keras
• Source/target domain similarity
• More data is always beneficial
• The impact of source/target volume and similarity
• Common problem domains
• Limited data
• When transfer learning should be used
• Overview of transfer learning
• Transfer Learning with Pretrained CNNs
• Summary
• Training with a generator
• The Keras ImageDataGenerator
• Using data augmentation
• Training
• Multi-GPU models in Keras
• Fully connected layers
• Convolutional layers
• Cost function and metrics
• Output
• Input
• Training a convolutional neural network in Keras
• Batch normalization
• Pooling layers
• Local connectivity
• Parameter sharing
• Benefits of convolutional layers
• A layer of convolutions
• Convolutions in three dimensions
• How do convolutional layers work?
• Introducing convolutions
• Training a CNN from Scratch
• Summary
• Hyperband
• Using random search with scikit-learn
• Common strategies
• Hyperparameter optimization strategies
• Which hyperparameters should we optimize?
• Practical advice
• Adding until you overfit then regularizing
• Finding a giant and then standing on his shoulders
• Should network architecture be considered a hyperparameter?
• Hyperparameter Optimization
• Summary
• Controlling variance with regularization
• Controlling variance with dropout
• Using scikit-learn metrics with multiclass models
• Training
• Putting it all together
• Softmax activation
• Output layer
• Hidden layers
• Input layer
• Loading MNIST
• Building a multiclass classifier in Keras
• Metrics
• Cost function
• Categorical outputs
• Flattening inputs
• Model inputs and outputs
• Problem definition
• Case study - handwritten digit classification
• Drawbacks
• Benefits
• Multiclass classification and deep neural networks
• Using Keras to Solve Multiclass Classification Problems
• Summary
• Measuring precision recall and f1-score
• Measuring ROC AUC in a custom callback
• Using the checkpoint callback in Keras
• Training our model
• Putting it all together
• The output layer
• Coding the hidden layers for our example
• Choosing a hidden layer architecture
• What happens if we use too few neurons?
• What happens if we use too many neurons?
• The hidden layers
• The input layer
• Building a binary classifier in Keras
• Using metrics to assess the performance
• The cost function
• Model inputs and outputs
• Loading data
• Defining our dataset
• Case study – epileptic seizure recognition
• Drawbacks of deep neural networks
• Benefits of deep neural networks
• Binary classification and deep neural networks
• Using Deep Learning to Solve Binary Classification Problems
• Summary
• Visualizing a broken network
• Visualizing network graphs
• Visualizing training
• Using TensorBoard
• Creating a TensorBoard callback
• Introducing Keras callbacks
• Connecting Keras to TensorBoard
• Running TensorBoard
• How TensorBoard talks to Keras/TensorFlow
• Installing TensorBoard
• Setting up TensorBoard
• A brief overview of TensorBoard
• Monitoring Network Training Using TensorBoard
• Summary
• Saving and loading a trained Keras model
• Tuning the model hyperparameters
• Measuring the deep neural network performance
• Building a deep neural network in Keras
• Measuring the performance of our model
• Training the Keras model
• Neural network architecture
• Output layer shape
• Hidden layer shape
• Input layer shape
• Building an MLP in Keras
• Defining our cost function
• Loading the dataset
• Defining our example problem
• How to plan a machine learning problem
• Using deep neural networks for regression
• Drawbacks to consider when using a neural network for regression
• Benefits of using a neural network for regression
• Regression analysis and deep neural networks
• Using Deep Learning to Solve Regression Problems
• Summary
• K-Fold cross-validation
• Managing bias and variance in deep neural networks
• The train val and test datasets
• Bias and variance errors in deep learning
• Building datasets for deep learning
• Installing TensorFlow and Keras
• Installing Python
• Installing Nvidia CUDA Toolkit and cuDNN
• GPU requirements for TensorFlow and Keras
• Popular alternatives to TensorFlow
• What is Keras?
• What is TensorFlow?
• Deep learning frameworks
• The Adam optimizer
• The RMSProp algorithm
• Using momentum with gradient descent
• Optimization algorithms for deep learning
• Stochastic and minibatch gradient descents
• The back propagation function
• The forward propagation process
• The loss and cost functions in deep learning
• Neuron activation functions
• The neuron linear function
• Neurons
• The deep neural network architectures
• The Building Blocks of Deep Learning
• Reviews
• Get in touch
• Conventions used
• Download the example code files
• To get the most out of this book
• What this book covers
• Who this book is for
• Preface
• Packt is searching for authors like you
• About the reviewer
• About the author
• Contributors
• Foreword
• PacktPub.com
• Why subscribe?
• Packt Upsell
• Dedication
• Title Page
• coverpage

• coverpage
• Title Page
• Dedication
• Packt Upsell
• Why subscribe?
• PacktPub.com
• Foreword
• Contributors
• About the author
• About the reviewer
• Packt is searching for authors like you
• Preface
• Who this book is for
• What this book covers
• To get the most out of this book
• Download the example code files
• Conventions used
• Get in touch
• Reviews
• The Building Blocks of Deep Learning
• The deep neural network architectures
• Neurons
• The neuron linear function
• Neuron activation functions
• The loss and cost functions in deep learning
• The forward propagation process
• The back propagation function
• Stochastic and minibatch gradient descents
• Optimization algorithms for deep learning
• Using momentum with gradient descent
• The RMSProp algorithm
• The Adam optimizer
• Deep learning frameworks
• What is TensorFlow?
• What is Keras?
• Popular alternatives to TensorFlow
• GPU requirements for TensorFlow and Keras
• Installing Nvidia CUDA Toolkit and cuDNN
• Installing Python
• Installing TensorFlow and Keras
• Building datasets for deep learning
• Bias and variance errors in deep learning
• The train val and test datasets
• Managing bias and variance in deep neural networks
• K-Fold cross-validation
• Summary
• Using Deep Learning to Solve Regression Problems
• Regression analysis and deep neural networks
• Benefits of using a neural network for regression
• Drawbacks to consider when using a neural network for regression
• Using deep neural networks for regression
• How to plan a machine learning problem
• Defining our example problem
• Loading the dataset
• Defining our cost function
• Building an MLP in Keras
• Input layer shape
• Hidden layer shape
• Output layer shape
• Neural network architecture
• Training the Keras model
• Measuring the performance of our model
• Building a deep neural network in Keras
• Measuring the deep neural network performance
• Tuning the model hyperparameters
• Saving and loading a trained Keras model
• Summary
• Monitoring Network Training Using TensorBoard
• A brief overview of TensorBoard
• Setting up TensorBoard
• Installing TensorBoard
• How TensorBoard talks to Keras/TensorFlow
• Running TensorBoard
• Connecting Keras to TensorBoard
• Introducing Keras callbacks
• Creating a TensorBoard callback
• Using TensorBoard
• Visualizing training
• Visualizing network graphs
• Visualizing a broken network
• Summary
• Using Deep Learning to Solve Binary Classification Problems
• Binary classification and deep neural networks
• Benefits of deep neural networks
• Drawbacks of deep neural networks
• Case study – epileptic seizure recognition
• Defining our dataset
• Loading data
• Model inputs and outputs
• The cost function
• Using metrics to assess the performance
• Building a binary classifier in Keras
• The input layer
• The hidden layers
• What happens if we use too many neurons?
• What happens if we use too few neurons?
• Choosing a hidden layer architecture
• Coding the hidden layers for our example
• The output layer
• Putting it all together
• Training our model
• Using the checkpoint callback in Keras
• Measuring ROC AUC in a custom callback
• Measuring precision recall and f1-score
• Summary
• Using Keras to Solve Multiclass Classification Problems
• Multiclass classification and deep neural networks
• Benefits
• Drawbacks
• Case study - handwritten digit classification
• Problem definition
• Model inputs and outputs
• Flattening inputs
• Categorical outputs
• Cost function
• Metrics
• Building a multiclass classifier in Keras
• Loading MNIST
• Input layer
• Hidden layers
• Output layer
• Softmax activation
• Putting it all together
• Training
• Using scikit-learn metrics with multiclass models
• Controlling variance with dropout
• Controlling variance with regularization
• Summary
• Hyperparameter Optimization
• Should network architecture be considered a hyperparameter?
• Finding a giant and then standing on his shoulders
• Adding until you overfit then regularizing
• Practical advice
• Which hyperparameters should we optimize?
• Hyperparameter optimization strategies
• Common strategies
• Using random search with scikit-learn
• Hyperband
• Summary
• Training a CNN from Scratch
• Introducing convolutions
• How do convolutional layers work?
• Convolutions in three dimensions
• A layer of convolutions
• Benefits of convolutional layers
• Parameter sharing
• Local connectivity
• Pooling layers
• Batch normalization
• Training a convolutional neural network in Keras
• Input
• Output
• Cost function and metrics
• Convolutional layers
• Fully connected layers
• Multi-GPU models in Keras
• Training
• Using data augmentation
• The Keras ImageDataGenerator
• Training with a generator
• Summary
• Transfer Learning with Pretrained CNNs
• Overview of transfer learning
• When transfer learning should be used
• Limited data
• Common problem domains
• The impact of source/target volume and similarity
• More data is always beneficial
• Source/target domain similarity
• Transfer learning in Keras
• Target domain overview
• Source domain overview
• Source network architecture
• Transfer network architecture
• Data preparation
• Data input
• Training (feature extraction)
• Training (fine-tuning)
• Summary
• Training an RNN from scratch
• Introducing recurrent neural networks
• What makes a neuron recurrent?
• Long Short Term Memory Networks
• Backpropagation through time
• A refresher on time series problems
• Stock and flow
• ARIMA and ARIMAX forecasting
• Using an LSTM for time series prediction
• Data preparation
• Loading the dataset
• Slicing train and test by date
• Differencing a time series
• Scaling a time series
• Creating a lagged training set
• Input shape
• Data preparation glue
• Network output
• Network architecture
• Stateful versus stateless LSTMs
• Training
• Measuring performance
• Summary
• Training LSTMs with Word Embeddings from Scratch
• An introduction to natural language processing
• Semantic analysis
• Document classification
• Vectorizing text
• NLP terminology
• Bag of Word models
• Stemming lemmatization and stopwords
• Count and TF-IDF vectorization
• Word embedding
• A quick example
• Learning word embeddings with prediction
• Learning word embeddings with counting
• Getting from words to documents
• Keras embedding layer
• 1D CNNs for natural language processing
• Case studies for document classifications
• Sentiment analysis with Keras embedding layers and LSTMs
• Preparing the data
• Input and embedding layer architecture
• LSTM layer
• Output layer
• Putting it all together
• Training the network
• Performance
• Document classification with and without GloVe
• Preparing the data
• Loading pretrained word vectors
• Input and embedding layer architecture
• Without GloVe vectors
• With GloVe vectors
• Convolution layers
• Output layer
• Putting it all together
• Training
• Performance
• Summary
• Training Seq2Seq Models
• Sequence-to-sequence models
• Sequence-to-sequence model applications
• Sequence-to-sequence model architecture
• Encoders and decoders
• Characters versus words
• Teacher forcing
• Attention
• Translation metrics
• Machine translation
• Understanding the data
• Loading data
• One hot encoding
• Training network architecture
• Network architecture (for inference)
• Putting it all together
• Training
• Inference
• Loading data
• Creating reverse indices
• Loading models
• Translating a sequence
• Decoding a sequence
• Example translations
• Summary
• Using Deep Reinforcement Learning
• Reinforcement learning overview
• Markov Decision Processes
• Q Learning
• Infinite state space
• Deep Q networks
• Online learning
• Memory and experience replay
• Exploitation versus exploration
• DeepMind
• The Keras reinforcement learning framework
• Installing Keras-RL
• Installing OpenAI gym
• Using OpenAI gym
• Building a reinforcement learning agent in Keras
• CartPole
• CartPole neural network architecture
• Memory
• Policy
• Agent
• Training
• Results
• Lunar Lander
• Lunar Lander network architecture
• Memory and policy
• Agent
• Training
• Results
• Summary
• Generative Adversarial Networks
• An overview of the GAN
• Deep Convolutional GAN architecture
• Adversarial training architecture
• Generator architecture
• Discriminator architecture
• Stacked training
• Step 1 – train the discriminator
• Step 2 – train the stack
• How GANs can fail
• Stability
• Mode collapse
• Safe choices for GAN
• Generating MNIST images using a Keras GAN
• Loading the dataset
• Building the generator
• Building the discriminator
• Building the stacked model
• The training loop
• Model evaluation
• Generating CIFAR-10 images using a Keras GAN
• Loading CIFAR-10
• Building the generator
• Building the discriminator
• The training loop
• Model evaluation
• Summary
• Other Books You May Enjoy
• Leave a review - let other readers know what you think 更新時間：2021-06-24 18:40:56