舉報 
會員
Hands-On Artificial Intelligence for Beginners
VirtualAssistants,suchasAlexaandSiri,processourrequests,Google'scarshavestartedtoreadaddresses,andAmazon'spricesandNetflix'srecommendedvideosaredecidedbyAI.ArtificialIntelligenceisoneofthemostexcitingtechnologiesandisbecomingincreasinglysignificantinthemodernworld.Hands-OnArtificialIntelligenceforBeginnerswillteachyouwhatArtificialIntelligenceisandhowtodesignandbuildintelligentapplications.ThisbookwillteachyoutoharnesspackagessuchasTensorFlowinordertocreatepowerfulAIsystems.YouwillbeginwithreviewingtherecentchangesinAIandlearninghowartificialneuralnetworks(ANNs)haveenabledmoreintelligentAI.You'llexplorefeedforward,recurrent,convolutional,andgenerativeneuralnetworks(FFNNs,RNNs,CNNs,andGNNs),aswellasreinforcementlearningmethods.Intheconcludingchapters,you'lllearnhowtoimplementthesemethodsforavarietyoftasks,suchasgeneratingtextforchatbots,andplayingboardandvideogames.Bytheendofthisbook,youwillbeabletounderstandexactlywhatyouneedtoconsiderwhenoptimizingANNsandhowtodeployandmaintainAIapplications.
最新章節
- Leave a review - let other readers know what you think
- Other Books You May Enjoy
- References
- Summary
- Testing deep learning algorithms
- Testing and maintaining your applications
品牌：中圖公司
上架時間：2021-06-10 18:26:46
出版社：Packt Publishing
本書數字版權由中圖公司提供，并由其授權上海閱文信息技術有限公司制作發行
- Leave a review - let other readers know what you think 更新時間：2021-06-10 19:34:36
- Other Books You May Enjoy
- References
- Summary
- Testing deep learning algorithms
- Testing and maintaining your applications
- Scaling out with distributed TensorFlow
- Scaling your applications
- Using an API to Predict
- Deploying for online learning on GCP
- Training on GCP
- Training and deploying with the Google Cloud Platform
- Building a TensorFlow client
- Utilizing docker
- Deploying models with TensorFlow Serving
- Deploying your applications
- Introduction
- Technical requirements
- Deploying and Maintaining AI Applications
- References
- Summary
- Implementation of DDPG
- Deep Deterministic Policy Gradients
- The critic
- The actor
- The actor–critic network
- Hindsight experience replay
- Experience replay buffer
- Setting up a deep deterministic policy gradients model
- Installing the MuJoCo Python package
- Configuring your MuJoCo files
- Signing up for a free trial of MuJoCo
- Downloading the MuJoCo binary files
- MuJoCo physics engine
- Setting up your environment
- Introduction
- Technical requirements
- Deep Learning for Robotics
- Summary
- Deep learning in asset management
- Predicting events with a convolutional neural network
- Neural Tensor Networks for event embeddings
- Generating word embeddings
- Gathering stock price data
- Event-driven trading platforms
- Backtesting your algorithm
- Price prediction utilizing LSTMs
- Managing market data
- Creating an artificial trader
- Basic trading functions
- Building a trading platform
- Deep learning in trading
- Introduction to AI in finance
- Requirements
- Deep Learning for Finance
- Summary
- Running the network
- Training the network
- Training methods
- Choosing action
- Experience replay buffer
- Utilizing a target network
- Constructing a Deep Q–network
- Networks for video games
- AlphaGo in action
- AlphaGo value network
- AlphaGo policy network
- AlphaGo and intelligent game-playing AIs
- Understanding game trees
- Networks for board games
- Introduction
- Technical requirements
- Deep Learning for Game Playing
- Summary
- Constructing a basic agent
- GloVe
- Training Word2vec models
- Word2vec
- Word embeddings
- Technical requirements
- Deep Learning for Intelligent Agents
- Summary
- Extensions on policy optimization
- Policy optimization
- Q–learning
- The Bellman equation
- Value functions
- Policies
- Rewards
- Markov processes
- Principles of reinforcement learning
- Technical requirements
- Reinforcement Learning
- References
- Summary
- Boltzmann machines
- Hidden Markov models
- Fully visible belief nets
- Other forms of generative models
- Training GANs
- Generator network
- Discriminator network
- Generative adversarial networks
- Utilizing a VAE
- Training and optimizing VAEs
- Decoder
- Encoder
- Structure
- Variational autoencoders
- Building an autoencoder
- Network architecture
- Autoencoders
- Getting to AI – generative models
- Technical requirements
- Generative Models
- Summary
- Neural turing machines
- Bidirectional RNNs
- Extensions of RNNs
- Generating image captions
- Attention mechanisms
- Neural machine translation
- Sequence processing with RNNs
- GRUs
- LSTM
- Memory units – LSTMs and GRUs
- Backpropagation through time
- Many-to-many
- Many-to-one
- One-to-many
- Vanilla recurrent neural networks
- Basic structure
- The building blocks of RNNs
- Technical requirements
- Recurrent Neural Networks
- Summary
- CNNs for image tagging
- The training process
- Fully connected layers
- Pooling layers
- Layer parameters and structure
- Convolutional layers
- Overview of CNNs
- Convolutional Neural Networks
- Summary
- Saving model checkpoints
- Managing a TensorFlow model
- Forwardprop and backprop with MNIST
- Backpropagation
- Forward propagation
- Putting it all together
- The training process
- Regularization
- Utilizing the Adam optimizer in our MNIST example
- Learning rates
- Stochastic gradient descent
- Defining a loss function in our MNIST example
- Using cross-entropy for binary classification problems
- Using a loss function for simple regression
- Loss functions
- Utilizing weights and biases in our MNIST example
- Weights and bias factors
- Modern approaches to activation functions
- Historically popular activation functions
- Activation functions
- Setting up network parameters in our MNIST example
- Naming and sizing neural networks
- Network layers
- Network building blocks
- Technical requirements
- Your First Artificial Neural Networks
- Summary
- The future – TPUs and more
- Basic GPU operations
- With Windows
- With Linux (Ubuntu)
- Installing GPU libraries and drivers
- CPUs GPUs and other compute frameworks
- GCP Cloud ML Engine
- GCP cloud storage
- Google Cloud Platform basics
- AWS Sagemaker
- S3 Storage
- EC2 and virtual machines
- AWS basics
- Cloud computing essentials
- Wrapping up
- Basic building blocks
- Keras
- The PyTorch graph
- Basic building blocks
- PyTorch
- The TensorFlow graph
- Basic building blocks
- TensorFlow
- TensorFlow PyTorch and Keras
- Technical requirements
- Platforms and Other Essentials
- Summary
- Hyperparameter optimization
- K-fold cross-validation
- Overfitting and underfitting
- Basic tuning
- Unsupervised learning algorithms
- Random forests
- Supervised learning algorithms
- Constructing basic machine learning algorithms
- Bayes' rule for conditional probability
- Chain rule for joint probability
- Conditional and joint probability
- Probability density functions
- Probability mass functions
- Probability distributions
- The probability space and general theory
- Basic statistics and probability theory
- Element–wise operations
- Scalar operations
- Matrix math
- Tensors
- Matrices
- Vectors
- Scalars
- The building blocks – scalars vectors matrices and tensors
- Applied math basics
- Technical requirements
- Machine Learning Basics
- Summary
- Deep learning and the future – 2012-Present
- The modern era takes hold – 1997-2005
- Rebirth –1980–1987
- The beginnings of AI –1950–1974
- The History of AI
- 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
- Packt.com
- Why subscribe?
- Packt Upsell
- Title Page
- coaverpage
- coaverpage
- Title Page
- Packt Upsell
- Why subscribe?
- Packt.com
- 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 History of AI
- The beginnings of AI –1950–1974
- Rebirth –1980–1987
- The modern era takes hold – 1997-2005
- Deep learning and the future – 2012-Present
- Summary
- Machine Learning Basics
- Technical requirements
- Applied math basics
- The building blocks – scalars vectors matrices and tensors
- Scalars
- Vectors
- Matrices
- Tensors
- Matrix math
- Scalar operations
- Element–wise operations
- Basic statistics and probability theory
- The probability space and general theory
- Probability distributions
- Probability mass functions
- Probability density functions
- Conditional and joint probability
- Chain rule for joint probability
- Bayes' rule for conditional probability
- Constructing basic machine learning algorithms
- Supervised learning algorithms
- Random forests
- Unsupervised learning algorithms
- Basic tuning
- Overfitting and underfitting
- K-fold cross-validation
- Hyperparameter optimization
- Summary
- Platforms and Other Essentials
- Technical requirements
- TensorFlow PyTorch and Keras
- TensorFlow
- Basic building blocks
- The TensorFlow graph
- PyTorch
- Basic building blocks
- The PyTorch graph
- Keras
- Basic building blocks
- Wrapping up
- Cloud computing essentials
- AWS basics
- EC2 and virtual machines
- S3 Storage
- AWS Sagemaker
- Google Cloud Platform basics
- GCP cloud storage
- GCP Cloud ML Engine
- CPUs GPUs and other compute frameworks
- Installing GPU libraries and drivers
- With Linux (Ubuntu)
- With Windows
- Basic GPU operations
- The future – TPUs and more
- Summary
- Your First Artificial Neural Networks
- Technical requirements
- Network building blocks
- Network layers
- Naming and sizing neural networks
- Setting up network parameters in our MNIST example
- Activation functions
- Historically popular activation functions
- Modern approaches to activation functions
- Weights and bias factors
- Utilizing weights and biases in our MNIST example
- Loss functions
- Using a loss function for simple regression
- Using cross-entropy for binary classification problems
- Defining a loss function in our MNIST example
- Stochastic gradient descent
- Learning rates
- Utilizing the Adam optimizer in our MNIST example
- Regularization
- The training process
- Putting it all together
- Forward propagation
- Backpropagation
- Forwardprop and backprop with MNIST
- Managing a TensorFlow model
- Saving model checkpoints
- Summary
- Convolutional Neural Networks
- Overview of CNNs
- Convolutional layers
- Layer parameters and structure
- Pooling layers
- Fully connected layers
- The training process
- CNNs for image tagging
- Summary
- Recurrent Neural Networks
- Technical requirements
- The building blocks of RNNs
- Basic structure
- Vanilla recurrent neural networks
- One-to-many
- Many-to-one
- Many-to-many
- Backpropagation through time
- Memory units – LSTMs and GRUs
- LSTM
- GRUs
- Sequence processing with RNNs
- Neural machine translation
- Attention mechanisms
- Generating image captions
- Extensions of RNNs
- Bidirectional RNNs
- Neural turing machines
- Summary
- Generative Models
- Technical requirements
- Getting to AI – generative models
- Autoencoders
- Network architecture
- Building an autoencoder
- Variational autoencoders
- Structure
- Encoder
- Decoder
- Training and optimizing VAEs
- Utilizing a VAE
- Generative adversarial networks
- Discriminator network
- Generator network
- Training GANs
- Other forms of generative models
- Fully visible belief nets
- Hidden Markov models
- Boltzmann machines
- Summary
- References
- Reinforcement Learning
- Technical requirements
- Principles of reinforcement learning
- Markov processes
- Rewards
- Policies
- Value functions
- The Bellman equation
- Q–learning
- Policy optimization
- Extensions on policy optimization
- Summary
- Deep Learning for Intelligent Agents
- Technical requirements
- Word embeddings
- Word2vec
- Training Word2vec models
- GloVe
- Constructing a basic agent
- Summary
- Deep Learning for Game Playing
- Technical requirements
- Introduction
- Networks for board games
- Understanding game trees
- AlphaGo and intelligent game-playing AIs
- AlphaGo policy network
- AlphaGo value network
- AlphaGo in action
- Networks for video games
- Constructing a Deep Q–network
- Utilizing a target network
- Experience replay buffer
- Choosing action
- Training methods
- Training the network
- Running the network
- Summary
- Deep Learning for Finance
- Requirements
- Introduction to AI in finance
- Deep learning in trading
- Building a trading platform
- Basic trading functions
- Creating an artificial trader
- Managing market data
- Price prediction utilizing LSTMs
- Backtesting your algorithm
- Event-driven trading platforms
- Gathering stock price data
- Generating word embeddings
- Neural Tensor Networks for event embeddings
- Predicting events with a convolutional neural network
- Deep learning in asset management
- Summary
- Deep Learning for Robotics
- Technical requirements
- Introduction
- Setting up your environment
- MuJoCo physics engine
- Downloading the MuJoCo binary files
- Signing up for a free trial of MuJoCo
- Configuring your MuJoCo files
- Installing the MuJoCo Python package
- Setting up a deep deterministic policy gradients model
- Experience replay buffer
- Hindsight experience replay
- The actor–critic network
- The actor
- The critic
- Deep Deterministic Policy Gradients
- Implementation of DDPG
- Summary
- References
- Deploying and Maintaining AI Applications
- Technical requirements
- Introduction
- Deploying your applications
- Deploying models with TensorFlow Serving
- Utilizing docker
- Building a TensorFlow client
- Training and deploying with the Google Cloud Platform
- Training on GCP
- Deploying for online learning on GCP
- Using an API to Predict
- Scaling your applications
- Scaling out with distributed TensorFlow
- Testing and maintaining your applications
- Testing deep learning algorithms
- Summary
- References
- Other Books You May Enjoy
- Leave a review - let other readers know what you think 更新時間：2021-06-10 19:34:36
