最新章節

• API changes
• Installing Keras 2.0
• Keras 2.0 - what is new
• Conclusion
• Summary
• The road ahead

• API changes 更新時間：2021-07-02 23:58:32
• Installing Keras 2.0
• Keras 2.0 - what is new
• Conclusion
• Summary
• The road ahead
• Example - Keras deep Q-network for catch
• Experience replay or the value of experience
• Balancing exploration with exploitation
• The deep Q-network as a Q-function
• Q-learning
• Maximizing future rewards
• Reinforcement learning
• AI Game Playing
• Summary
• Keras example - style transfer
• Keras example - deep dreaming
• Generative models
• Keras example - building a custom normalization layer
• Keras example - using the lambda layer
• Customizing Keras
• Keras example - memory network for question answering
• Composing deep networks
• Keras autoencoder example - sentence vectors
• Unsupervised learning - autoencoders
• Keras regression example - predicting benzene levels in the air
• Regression networks
• Keras functional API
• Additional Deep Learning Models
• Summary
• Other RNN variants
• Stateful LSTM with Keras - predicting electricity consumption
• Stateful RNNs
• Bidirectional RNNs
• GRU with Keras - POS tagging
• Gated recurrent unit - GRU
• LSTM with Keras - sentiment analysis
• Long short term memory - LSTM
• Vanishing and exploding gradients
• RNN topologies
• SimpleRNN with Keras - generating text
• SimpleRNN cells
• Recurrent Neural Network — RNN
• Summary
• Look up embeddings
• Fine-tune learned embeddings from GloVe
• Fine-tuning learned embeddings from word2vec
• Learn embeddings from scratch
• Using pre-trained embeddings
• Exploring GloVe
• Using third-party implementations of word2vec
• Extracting word2vec embeddings from the model
• The CBOW word2vec model
• The skip-gram word2vec model
• word2vec
• Distributed representations
• Word Embeddings
• Summary
• WaveNet - a generative model for learning how to produce audio
• Keras adversarial GANs for forging CIFAR
• Keras adversarial GANs for forging MNIST
• Deep convolutional generative adversarial networks
• Some GAN applications
• What is a GAN?
• Generative Adversarial Networks and WaveNet
• Summary
• Very deep inception-v3 net used for transfer learning
• Recycling pre-built deep learning models for extracting features
• Utilizing Keras built-in VGG-16 net module
• Recognizing cats with a VGG-16 net
• Very deep convolutional networks for large-scale image recognition
• Predicting with CIFAR-10
• Improving the CIFAR-10 performance with data augmentation
• Improving the CIFAR-10 performance with deeper a network
• Recognizing CIFAR-10 images with deep learning
• Understanding the power of deep learning
• LeNet code in Keras
• An example of DCNN - LeNet
• ConvNets summary
• Average pooling
• Max-pooling
• Pooling layers
• Shared weights and bias
• Local receptive fields
• Deep convolutional neural network - DCNN
• Deep Learning with ConvNets
• Summary
• Using Quiver and Keras
• Using TensorBoard and Keras
• Checkpointing
• Callbacks for customizing the training process
• Saving and loading the weights and the architecture of a model
• Some useful operations
• An overview of optimizers
• An overview of metrics
• An overview of losses functions
• An overview of predefined activation functions
• Batch normalization
• Regularization
• Convolutional and pooling layers
• Recurrent neural networks - simple LSTM and GRU
• Regular dense
• An overview of predefined neural network layers
• Functional composition
• Sequential composition
• Composing models in Keras
• What is a tensor?
• Getting started with Keras architecture
• Keras API
• Installing Keras on Microsoft Azure
• Installing Keras on Amazon AWS
• Installing Keras on Google Cloud ML
• Installing Keras on Docker
• Configuring Keras
• Step 5 - testing Theano TensorFlow and Keras
• Step 4 - install Keras
• Step 3 - install TensorFlow
• Step 2 - install Theano
• Step 1 - install some useful dependencies
• Installing Keras
• Keras Installation and API
• Summary
• Towards a deep learning approach
• A practical overview of backpropagation
• Predicting output
• Hyperparameters tuning
• Adopting regularization for avoiding overfitting
• Summarizing the experiments run for recognizing handwritten charts
• Increasing the size of batch computation
• Increasing the number of internal hidden neurons
• Controlling the optimizer learning rate
• Increasing the number of epochs
• Testing different optimizers in Keras
• Further improving the simple net in Keras with dropout
• Improving the simple net in Keras with hidden layers
• Running a simple Keras net and establishing a baseline
• Defining a simple neural net in Keras
• One-hot encoding - OHE
• A real example - recognizing handwritten digits
• Activation functions
• Activation function - ReLU
• Activation function - sigmoid
• Problems in training the perceptron and a solution
• Multilayer perceptron - the first example of a network
• The first example of Keras code
• Perceptron
• Neural Networks Foundations
• Questions
• Piracy
• Errata
• Downloading the color images of this book
• Downloading the example code
• Customer support
• Reader feedback
• Conventions
• Who this book is for
• What you need for this book
• What this book covers
• How deep learning is different from machine learning and artificial intelligence
• Mission
• Preface
• Customer Feedback
• www.PacktPub.com
• About the Reviewer
• About the Authors
• Credits
• 版權信息
• 封面

• 封面
• 版權信息
• Credits
• About the Authors
• About the Reviewer
• www.PacktPub.com
• Customer Feedback
• Preface
• Mission
• How deep learning is different from machine learning and artificial intelligence
• What this book covers
• What you need for this book
• Who this book is for
• Conventions
• Reader feedback
• Customer support
• Downloading the example code
• Downloading the color images of this book
• Errata
• Piracy
• Questions
• Neural Networks Foundations
• Perceptron
• The first example of Keras code
• Multilayer perceptron - the first example of a network
• Problems in training the perceptron and a solution
• Activation function - sigmoid
• Activation function - ReLU
• Activation functions
• A real example - recognizing handwritten digits
• One-hot encoding - OHE
• Defining a simple neural net in Keras
• Running a simple Keras net and establishing a baseline
• Improving the simple net in Keras with hidden layers
• Further improving the simple net in Keras with dropout
• Testing different optimizers in Keras
• Increasing the number of epochs
• Controlling the optimizer learning rate
• Increasing the number of internal hidden neurons
• Increasing the size of batch computation
• Summarizing the experiments run for recognizing handwritten charts
• Adopting regularization for avoiding overfitting
• Hyperparameters tuning
• Predicting output
• A practical overview of backpropagation
• Towards a deep learning approach
• Summary
• Keras Installation and API
• Installing Keras
• Step 1 - install some useful dependencies
• Step 2 - install Theano
• Step 3 - install TensorFlow
• Step 4 - install Keras
• Step 5 - testing Theano TensorFlow and Keras
• Configuring Keras
• Installing Keras on Docker
• Installing Keras on Google Cloud ML
• Installing Keras on Amazon AWS
• Installing Keras on Microsoft Azure
• Keras API
• Getting started with Keras architecture
• What is a tensor?
• Composing models in Keras
• Sequential composition
• Functional composition
• An overview of predefined neural network layers
• Regular dense
• Recurrent neural networks - simple LSTM and GRU
• Convolutional and pooling layers
• Regularization
• Batch normalization
• An overview of predefined activation functions
• An overview of losses functions
• An overview of metrics
• An overview of optimizers
• Some useful operations
• Saving and loading the weights and the architecture of a model
• Callbacks for customizing the training process
• Checkpointing
• Using TensorBoard and Keras
• Using Quiver and Keras
• Summary
• Deep Learning with ConvNets
• Deep convolutional neural network - DCNN
• Local receptive fields
• Shared weights and bias
• Pooling layers
• Max-pooling
• Average pooling
• ConvNets summary
• An example of DCNN - LeNet
• LeNet code in Keras
• Understanding the power of deep learning
• Recognizing CIFAR-10 images with deep learning
• Improving the CIFAR-10 performance with deeper a network
• Improving the CIFAR-10 performance with data augmentation
• Predicting with CIFAR-10
• Very deep convolutional networks for large-scale image recognition
• Recognizing cats with a VGG-16 net
• Utilizing Keras built-in VGG-16 net module
• Recycling pre-built deep learning models for extracting features
• Very deep inception-v3 net used for transfer learning
• Summary
• Generative Adversarial Networks and WaveNet
• What is a GAN?
• Some GAN applications
• Deep convolutional generative adversarial networks
• Keras adversarial GANs for forging MNIST
• Keras adversarial GANs for forging CIFAR
• WaveNet - a generative model for learning how to produce audio
• Summary
• Word Embeddings
• Distributed representations
• word2vec
• The skip-gram word2vec model
• The CBOW word2vec model
• Extracting word2vec embeddings from the model
• Using third-party implementations of word2vec
• Exploring GloVe
• Using pre-trained embeddings
• Learn embeddings from scratch
• Fine-tuning learned embeddings from word2vec
• Fine-tune learned embeddings from GloVe
• Look up embeddings
• Summary
• Recurrent Neural Network — RNN
• SimpleRNN cells
• SimpleRNN with Keras - generating text
• RNN topologies
• Vanishing and exploding gradients
• Long short term memory - LSTM
• LSTM with Keras - sentiment analysis
• Gated recurrent unit - GRU
• GRU with Keras - POS tagging
• Bidirectional RNNs
• Stateful RNNs
• Stateful LSTM with Keras - predicting electricity consumption
• Other RNN variants
• Summary
• Additional Deep Learning Models
• Keras functional API
• Regression networks
• Keras regression example - predicting benzene levels in the air
• Unsupervised learning - autoencoders
• Keras autoencoder example - sentence vectors
• Composing deep networks
• Keras example - memory network for question answering
• Customizing Keras
• Keras example - using the lambda layer
• Keras example - building a custom normalization layer
• Generative models
• Keras example - deep dreaming
• Keras example - style transfer
• Summary
• AI Game Playing
• Reinforcement learning
• Maximizing future rewards
• Q-learning
• The deep Q-network as a Q-function
• Balancing exploration with exploitation
• Experience replay or the value of experience
• Example - Keras deep Q-network for catch
• The road ahead
• Summary
• Conclusion
• Keras 2.0 - what is new
• Installing Keras 2.0
• API changes 更新時間：2021-07-02 23:58:32