最新章節

• Leave a review – let other readers know what you think
• Other Books You May Enjoy
• Summary
• Code synthesis
• Visual reasoning
• Lip reading

• Leave a review – let other readers know what you think 更新時間：2021-06-30 19:18:45
• Other Books You May Enjoy
• Summary
• Code synthesis
• Visual reasoning
• Lip reading
• Clinical imaging
• Predictive medicine
• Genomics
• Novel applications
• Capsule networks
• Generative Adversarial Networks
• Recent models for deep learning
• Deep Learning Trends
• Summary
• Model compression
• List of pre-trained models
• Tricks and techniques
• When not to use fine-tuning
• When to use fine-tuning
• Fine-tuning
• Fine-tuning
• Early stopping
• Dropout
• Batch normalization
• Preventing overfitting
• Others
• Regression
• Multi-class multi-label classification
• Multi-class classification
• Choosing the loss function
• Clip gradients
• Mini-batch
• Learning rate
• Optimization
• Xavier initialization
• ReLU initialization
• Random initialization
• All-zero
• Weight initialization
• Tricks in training
• Data normalization
• Data augmentation
• Data cleaning
• Massaging your data
• Deep Learning Hacks
• Summary
• Reinforcement learning with Q-learning example
• Simple reinforcement learning example
• Implementing reinforcement learning
• Dueling DQN
• Prioritized experience delay
• Double-DQN
• Reward clipping
• Target network
• Experience replay
• Deep Q-network (DQN)
• Deep reinforcement learning
• Actor-critic-based algorithms
• Policy search-based algorithms
• Value learning-based algorithms
• Problem setup
• What is reinforcement learning (RL)?
• Deep Reinforcement Learning
• Summary
• Multi-source based self-driving
• Visual question answering
• The difference between hard attention and soft attention
• Attention in computer vision
• Attention in NLP
• Attention models
• Rank position
• SPICE
• CIDEr
• METEOR
• ROUGE
• BLEU
• Evaluation
• Datasets
• Other types of approaches
• Beam Search
• Testing/inference
• Training
• Decoder
• Encoder
• Show and tell
• Image captioning
• Co-learning
• Fusion
• Alignment
• Translation
• Representation
• Challenges of multimodality learning
• What is multimodality learning?
• Multimodality
• Summary
• Chatbots
• Seq2Seq inference
• Machine translation
• Sequence tagging
• Language modeling
• Applications
• LSTM implementation with tensorflow
• Long short-term memory network
• Training RNN is tough
• Basic RNN model
• RNN architectures
• Recurrent neural networks
• Limitations of neural networks
• Deep learning for text
• Advanced Natural Language Processing
• Summary
• Fine-tuning
• Example use cases
• Applications
• FastText
• Understanding GloVe
• Using the pre-trained Word2Vec embeddings
• Word2Vec from Google News
• Using existing pre-trained Word2Vec embeddings
• Training a Word2Vec using TensorFlow
• Continuous Bag-of-Words model
• The loss function
• The output layer
• The hidden layer
• The input layer
• Skip-Gram model
• Other hyperparameters
• Hierarchical softmax
• Negative sampling
• Generating training data
• The word windows
• Basic idea of Word2Vec
• Word2Vec
• Commonly used pre-trained word embeddings
• Problems of distributed representation
• Advantages of distributed representation
• Idea of word embeddings
• Word embeddings
• Motivation and distributed representation
• Deep learning NLP
• Weighting the terms tf-idf
• Bag of words
• Traditional NLP
• NLP - Vector Representation
• Summary
• ResNet
• GoogLeNet
• Visual Geometry Group
• AlexNet
• Popular CNN architectures
• Fine-tuning CNNs
• Handwritten digit classification example
• Model visualization
• Loss functions
• Regularization
• Network initialization
• Fully connected or dense layer
• Pooling or subsampling layer
• Convolution layer
• Network layers
• Data augmentation
• Input preprocessing
• Data transformations
• Convolutional Neural Networks
• Origins of CNNs
• Deep Learning in Computer Vision
• Summary
• Handwritten digits recognition
• TensorFlow setup and key concepts
• Practical examples
• Step 3 – The output gate
• Step 2 – Updating memory/cell state
• Step 1 – The forget gate
• Cells and gates in LTSM
• Vanishing gradient and LTSM
• Backpropagation through time
• Cells in RNN and unrolling
• Recurrent neural networks (RNN/LSTM)
• RBM versus Boltzmann Machines
• Stacked/continuous RBM
• Contrastive divergence (CD-k)
• Encoding and decoding
• Energy function
• Restricted Boltzmann Machines
• Overall
• Fully connected layer
• Pooling/subsampling
• Convolution
• Convolutional Neural Networks
• Deep learning models
• Regularization
• Optimization algorithms
• Vanishing and exploding gradients
• Automatic differentiation
• Updating the network
• Backpropagation
• Calculating errors
• Backpropagation
• Forward propagation
• Weight initialization
• How a network learns
• Choosing the right activation function
• Softmax
• Leaky ReLU and maxout
• ReLU
• Tanh or hyperbolic tangent function
• Sigmoid or logistic function
• Activation functions
• Hidden layers
• The output layer
• The input layer
• Multilayer perceptrons
• Getting Started with Neural Networks
• Summary
• Setup using Docker
• Setup from scratch
• Setting up deep learning on AWS
• Framework comparison
• Keras
• Microsoft Cognitive Toolkit
• Theano
• Torch
• MXNet
• Caffe
• TensorFlow – a deep learning library
• Deep learning software frameworks
• Cooling systems
• Hard drive
• RAM size
• CPU cache size
• CPU cores
• Deep learning hardware guide
• Deep learning with GPU
• Matrix properties
• Data operations
• Data representation
• Basics of linear algebra
• Getting Yourself Ready for Deep Learning
• Summary
• Future potential and challenges
• Deep learning for business
• Success stories
• Lucrative applications
• Applications
• Hierarchical feature representation
• Distributed feature representation
• The representation viewpoint
• The neural viewpoint
• The motivation of deep architecture
• Impact of deep learning
• Advantages over traditional shallow methods
• Why deep learning?
• The history and rise of deep learning
• What is AI and deep learning?
• Why Deep Learning?
• Reviews
• Get in touch
• Conventions used
• Download the color images
• 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 authors
• Contributors
• PacktPub.com
• Why subscribe?
• Packt Upsell
• Title Page
• coverpage

• coverpage
• Title Page
• Packt Upsell
• Why subscribe?
• PacktPub.com
• Contributors
• About the authors
• 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
• Download the color images
• Conventions used
• Get in touch
• Reviews
• Why Deep Learning?
• What is AI and deep learning?
• The history and rise of deep learning
• Why deep learning?
• Advantages over traditional shallow methods
• Impact of deep learning
• The motivation of deep architecture
• The neural viewpoint
• The representation viewpoint
• Distributed feature representation
• Hierarchical feature representation
• Applications
• Lucrative applications
• Success stories
• Deep learning for business
• Future potential and challenges
• Summary
• Getting Yourself Ready for Deep Learning
• Basics of linear algebra
• Data representation
• Data operations
• Matrix properties
• Deep learning with GPU
• Deep learning hardware guide
• CPU cores
• CPU cache size
• RAM size
• Hard drive
• Cooling systems
• Deep learning software frameworks
• TensorFlow – a deep learning library
• Caffe
• MXNet
• Torch
• Theano
• Microsoft Cognitive Toolkit
• Keras
• Framework comparison
• Setting up deep learning on AWS
• Setup from scratch
• Setup using Docker
• Summary
• Getting Started with Neural Networks
• Multilayer perceptrons
• The input layer
• The output layer
• Hidden layers
• Activation functions
• Sigmoid or logistic function
• Tanh or hyperbolic tangent function
• ReLU
• Leaky ReLU and maxout
• Softmax
• Choosing the right activation function
• How a network learns
• Weight initialization
• Forward propagation
• Backpropagation
• Calculating errors
• Backpropagation
• Updating the network
• Automatic differentiation
• Vanishing and exploding gradients
• Optimization algorithms
• Regularization
• Deep learning models
• Convolutional Neural Networks
• Convolution
• Pooling/subsampling
• Fully connected layer
• Overall
• Restricted Boltzmann Machines
• Energy function
• Encoding and decoding
• Contrastive divergence (CD-k)
• Stacked/continuous RBM
• RBM versus Boltzmann Machines
• Recurrent neural networks (RNN/LSTM)
• Cells in RNN and unrolling
• Backpropagation through time
• Vanishing gradient and LTSM
• Cells and gates in LTSM
• Step 1 – The forget gate
• Step 2 – Updating memory/cell state
• Step 3 – The output gate
• Practical examples
• TensorFlow setup and key concepts
• Handwritten digits recognition
• Summary
• Deep Learning in Computer Vision
• Origins of CNNs
• Convolutional Neural Networks
• Data transformations
• Input preprocessing
• Data augmentation
• Network layers
• Convolution layer
• Pooling or subsampling layer
• Fully connected or dense layer
• Network initialization
• Regularization
• Loss functions
• Model visualization
• Handwritten digit classification example
• Fine-tuning CNNs
• Popular CNN architectures
• AlexNet
• Visual Geometry Group
• GoogLeNet
• ResNet
• Summary
• NLP - Vector Representation
• Traditional NLP
• Bag of words
• Weighting the terms tf-idf
• Deep learning NLP
• Motivation and distributed representation
• Word embeddings
• Idea of word embeddings
• Advantages of distributed representation
• Problems of distributed representation
• Commonly used pre-trained word embeddings
• Word2Vec
• Basic idea of Word2Vec
• The word windows
• Generating training data
• Negative sampling
• Hierarchical softmax
• Other hyperparameters
• Skip-Gram model
• The input layer
• The hidden layer
• The output layer
• The loss function
• Continuous Bag-of-Words model
• Training a Word2Vec using TensorFlow
• Using existing pre-trained Word2Vec embeddings
• Word2Vec from Google News
• Using the pre-trained Word2Vec embeddings
• Understanding GloVe
• FastText
• Applications
• Example use cases
• Fine-tuning
• Summary
• Advanced Natural Language Processing
• Deep learning for text
• Limitations of neural networks
• Recurrent neural networks
• RNN architectures
• Basic RNN model
• Training RNN is tough
• Long short-term memory network
• LSTM implementation with tensorflow
• Applications
• Language modeling
• Sequence tagging
• Machine translation
• Seq2Seq inference
• Chatbots
• Summary
• Multimodality
• What is multimodality learning?
• Challenges of multimodality learning
• Representation
• Translation
• Alignment
• Fusion
• Co-learning
• Image captioning
• Show and tell
• Encoder
• Decoder
• Training
• Testing/inference
• Beam Search
• Other types of approaches
• Datasets
• Evaluation
• BLEU
• ROUGE
• METEOR
• CIDEr
• SPICE
• Rank position
• Attention models
• Attention in NLP
• Attention in computer vision
• The difference between hard attention and soft attention
• Visual question answering
• Multi-source based self-driving
• Summary
• Deep Reinforcement Learning
• What is reinforcement learning (RL)?
• Problem setup
• Value learning-based algorithms
• Policy search-based algorithms
• Actor-critic-based algorithms
• Deep reinforcement learning
• Deep Q-network (DQN)
• Experience replay
• Target network
• Reward clipping
• Double-DQN
• Prioritized experience delay
• Dueling DQN
• Implementing reinforcement learning
• Simple reinforcement learning example
• Reinforcement learning with Q-learning example
• Summary
• Deep Learning Hacks
• Massaging your data
• Data cleaning
• Data augmentation
• Data normalization
• Tricks in training
• Weight initialization
• All-zero
• Random initialization
• ReLU initialization
• Xavier initialization
• Optimization
• Learning rate
• Mini-batch
• Clip gradients
• Choosing the loss function
• Multi-class classification
• Multi-class multi-label classification
• Regression
• Others
• Preventing overfitting
• Batch normalization
• Dropout
• Early stopping
• Fine-tuning
• Fine-tuning
• When to use fine-tuning
• When not to use fine-tuning
• Tricks and techniques
• List of pre-trained models
• Model compression
• Summary
• Deep Learning Trends
• Recent models for deep learning
• Generative Adversarial Networks
• Capsule networks
• Novel applications
• Genomics
• Predictive medicine
• Clinical imaging
• Lip reading
• Visual reasoning
• Code synthesis
• Summary
• Other Books You May Enjoy
• Leave a review – let other readers know what you think 更新時間：2021-06-30 19:18:45