舉報 
會員
Intelligent Projects Using Python
ThisbookwillbeaperfectcompanionifyouwanttobuildinsightfulprojectsfromleadingAIdomainsusingPython.ThebookcoversdetailedimplementationofprojectsfromallthecoredisciplinesofAI.Westartbycoveringthebasicsofhowtocreatesmartsystemsusingmachinelearninganddeeplearningtechniques.YouwillassimilatevariousneuralnetworkarchitecturessuchasCNN,RNN,LSTM,tosolvecriticalnewworldchallenges.Youwilllearntotrainamodeltodetectdiabeticretinopathyconditionsinthehumaneyeandcreateanintelligentsystemforperformingavideo-to-texttranslation.YouwillusethetransferlearningtechniqueinthehealthcaredomainandimplementstyletransferusingGANs.LateryouwilllearntobuildAI-basedrecommendationsystems,amobileappforsentimentanalysisandapowerfulchatbotforcarryingcustomerservices.YouwillimplementAItechniquesinthecybersecuritydomaintogenerateCaptchas.Lateryouwilltrainandbuildautonomousvehiclestoself-driveusingreinforcementlearning.YouwillbeusinglibrariesfromthePythonecosystemsuchasTensorFlow,Kerasandmoretobringthecoreaspectsofmachinelearning,deeplearning,andAI.Bytheendofthisbook,youwillbeskilledtobuildyourownsmartmodelsfortacklinganykindofAIproblemswithoutanyhassle.
最新章節
- Leave a review - let other readers know what you think
- Other Books You May Enjoy
- Summary
- Using the trained generator to create CAPTCHAs for use
- The quality of CAPTCHAs during training
- Invoking the training
品牌：中圖公司
上架時間：2021-07-02 12:33:38
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：2021-07-02 14:11:25
- Other Books You May Enjoy
- Summary
- Using the trained generator to create CAPTCHAs for use
- The quality of CAPTCHAs during training
- Invoking the training
- Data preprocessing
- Noise distribution
- Training the GAN
- Discriminator network
- Generator network
- Optimizing the GAN loss
- CAPTCHA generation through adversarial learning
- Accuracy on the test data set
- Training the CAPTCHA breaker
- Data generator
- Converting the CAPTCHA characters to classes
- Pre-processing the CAPTCHA images
- Captcha breaker CNN architecture
- Generating data for training a CAPTCHA breaker
- Generating basic CAPTCHAs
- Breaking CAPTCHAs with deep learning
- Technical requirements
- CAPTCHA from a Deep-Learning Perspective
- Summary
- Results from the training
- Helper functions
- Putting it all together
- The environment for the self-driving car
- Designing the agent
- Implementing the Double Deep Q network
- Discretizing actions for deep Q learning
- Implementing an autonomous self-driving car
- Double deep Q learning
- Formulating the cost function
- Deep Q learning
- Learning the Q value function
- Markov decision process
- Technical requirements
- Autonomous Self-Driving Car Through Reinforcement Learning
- Summary
- Results of inference on some input tweets
- Invoking the training
- Putting it all together
- Generating output responses from the model
- Training the model
- Loss function for training the model
- Defining the model
- Replacing anonymized screen names
- Tokenizing the text into word indices
- Creating data for training the chatbot
- Customer support on Twitter
- Building a sequence-to-sequence model
- A sequence-to-sequence model using an LSTM
- Chatbot architecture
- Technical requirements
- Conversational AI Chatbots for Customer Service
- Summary
- Testing the mobile app
- The core logic of the Android app
- App interface page design
- Creating a word-to-token dictionary for inference
- Freezing the model to a protobuf format
- The batch generator
- Training the model
- Building the model
- Preprocessing the movie review text
- Movie review rating in an Android app
- Building an Android mobile app using TensorFlow mobile
- Technical requirements
- Mobile App for Movie Review Sentiment Analysis
- Summary
- Inference using the trained RBM
- Training the RBM
- Building the RBM network for collaborative filtering
- Processing the input
- Collaborative filtering implementation using RBM
- Collaborative filtering using RBMs
- Contrastive divergence
- Restricted Boltzmann machines for recommendation
- Training model with SVD++ on the Movie Lens 100k dataset
- SVD++
- The deep learning-based latent factor model
- Deep learning for latent factor collaborative filtering
- Latent factorization-based recommendation system
- What is a recommender system?
- Technical requirements
- The Intelligent Recommender System
- Summary
- Results from evaluation
- Inference function
- Inference with unseen test videos
- Training results
- Training the model
- Creating a word vocabulary for the captions
- Building the loss for each mini-batch
- Decoding stage
- Encoding stage
- Definition of the model variables
- Building the model
- Building the train and test dataset
- Processing the labelled captions of the video
- Processing video images to create CNN features
- Data for the video-captioning system
- A sequence-to-sequence video-captioning system
- CNNs and LSTMs in video captioning
- Technical requirements
- Video Captioning Application
- Summary
- Sample images generated by DiscoGAN
- Monitoring the generator and the discriminator loss
- Invoking the training
- Important parameter values for GAN training
- Building the training process
- Building the network and defining the cost functions
- The discriminators of the DiscoGAN
- The generators of the DiscoGAN
- Preprocess the Images
- Learning to generate natural handbags from sketched outlines
- CycleGAN
- DiscoGAN
- Technical requirements
- Style Transfer in Fashion Industry using GANs
- Summary
- Implementing the embeddings-based NMT
- Embeddings layer
- Word vector embeddings
- Building the inference model
- Training the model
- Loss function for the neural translation machine
- Defining a model for neural machine translation
- Processing the input data
- Implementing a sequence-to-sequence neural translation machine
- Inference using the encoder–decoder model
- The encoder–decoder model
- Neural machine translation
- Translation model
- Perplexity for language models
- Language model
- Statistical machine-learning systems
- Generation phase
- Lexical transfer phase
- The analysis phase
- Rule-based machine translation
- Technical requirements
- Neural Machine Translation
- Summary
- Using the keras sequential utils as generator
- Performing regression instead of categorical classification
- Inference at testing time
- Results from the categorical classification
- Dynamic mini batch creation during training
- Python implementation of the training process
- Model checkpoints based on validation log loss
- Cross-validation
- The optimizer and initial learning rate
- The ResNet50 transfer learning network
- The InceptionV3 transfer learning network
- The VGG16 transfer learning network
- Network architecture
- Additional image generation through affine transformation
- Reflection
- Scaling
- Translation
- Rotation
- Additional data generation using affine transformation
- Preprocessing the images
- Taking class imbalances into account
- Formulating the loss function
- The diabetic retinopathy dataset
- Transfer learning and detecting diabetic retinopathy
- Introduction to transfer learning
- Technical requirements
- Transfer Learning
- Summary
- Autoencoders
- Restricted Boltzmann machines
- Transfer learning
- Deep Q-learning
- Q-learning
- Reinforcement learning
- Generative adversarial networks
- Long short-term memory (LSTM) cells
- Recurrent neural networks (RNNs)
- Convolutional neural networks
- The backpropagation method of training neural networks
- The softmax activation unit
- Rectified linear unit (ReLU)
- The hyperbolic tangent activation function
- Sigmoid activation units
- Linear activation units
- Neural activation units
- Neural networks
- Foundations of Artificial Intelligence Based Systems
- Reviews
- Get in touch
- Conventions used
- Code in action
- 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 author
- Contributors
- Packt.com
- Why subscribe?
- About Packt
- Intelligent Projects Using Python
- Copyright and Credits
- Title Page
- coverpage
- coverpage
- Title Page
- Copyright and Credits
- Intelligent Projects Using Python
- About Packt
- 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
- Download the color images
- Code in action
- Conventions used
- Get in touch
- Reviews
- Foundations of Artificial Intelligence Based Systems
- Neural networks
- Neural activation units
- Linear activation units
- Sigmoid activation units
- The hyperbolic tangent activation function
- Rectified linear unit (ReLU)
- The softmax activation unit
- The backpropagation method of training neural networks
- Convolutional neural networks
- Recurrent neural networks (RNNs)
- Long short-term memory (LSTM) cells
- Generative adversarial networks
- Reinforcement learning
- Q-learning
- Deep Q-learning
- Transfer learning
- Restricted Boltzmann machines
- Autoencoders
- Summary
- Transfer Learning
- Technical requirements
- Introduction to transfer learning
- Transfer learning and detecting diabetic retinopathy
- The diabetic retinopathy dataset
- Formulating the loss function
- Taking class imbalances into account
- Preprocessing the images
- Additional data generation using affine transformation
- Rotation
- Translation
- Scaling
- Reflection
- Additional image generation through affine transformation
- Network architecture
- The VGG16 transfer learning network
- The InceptionV3 transfer learning network
- The ResNet50 transfer learning network
- The optimizer and initial learning rate
- Cross-validation
- Model checkpoints based on validation log loss
- Python implementation of the training process
- Dynamic mini batch creation during training
- Results from the categorical classification
- Inference at testing time
- Performing regression instead of categorical classification
- Using the keras sequential utils as generator
- Summary
- Neural Machine Translation
- Technical requirements
- Rule-based machine translation
- The analysis phase
- Lexical transfer phase
- Generation phase
- Statistical machine-learning systems
- Language model
- Perplexity for language models
- Translation model
- Neural machine translation
- The encoder–decoder model
- Inference using the encoder–decoder model
- Implementing a sequence-to-sequence neural translation machine
- Processing the input data
- Defining a model for neural machine translation
- Loss function for the neural translation machine
- Training the model
- Building the inference model
- Word vector embeddings
- Embeddings layer
- Implementing the embeddings-based NMT
- Summary
- Style Transfer in Fashion Industry using GANs
- Technical requirements
- DiscoGAN
- CycleGAN
- Learning to generate natural handbags from sketched outlines
- Preprocess the Images
- The generators of the DiscoGAN
- The discriminators of the DiscoGAN
- Building the network and defining the cost functions
- Building the training process
- Important parameter values for GAN training
- Invoking the training
- Monitoring the generator and the discriminator loss
- Sample images generated by DiscoGAN
- Summary
- Video Captioning Application
- Technical requirements
- CNNs and LSTMs in video captioning
- A sequence-to-sequence video-captioning system
- Data for the video-captioning system
- Processing video images to create CNN features
- Processing the labelled captions of the video
- Building the train and test dataset
- Building the model
- Definition of the model variables
- Encoding stage
- Decoding stage
- Building the loss for each mini-batch
- Creating a word vocabulary for the captions
- Training the model
- Training results
- Inference with unseen test videos
- Inference function
- Results from evaluation
- Summary
- The Intelligent Recommender System
- Technical requirements
- What is a recommender system?
- Latent factorization-based recommendation system
- Deep learning for latent factor collaborative filtering
- The deep learning-based latent factor model
- SVD++
- Training model with SVD++ on the Movie Lens 100k dataset
- Restricted Boltzmann machines for recommendation
- Contrastive divergence
- Collaborative filtering using RBMs
- Collaborative filtering implementation using RBM
- Processing the input
- Building the RBM network for collaborative filtering
- Training the RBM
- Inference using the trained RBM
- Summary
- Mobile App for Movie Review Sentiment Analysis
- Technical requirements
- Building an Android mobile app using TensorFlow mobile
- Movie review rating in an Android app
- Preprocessing the movie review text
- Building the model
- Training the model
- The batch generator
- Freezing the model to a protobuf format
- Creating a word-to-token dictionary for inference
- App interface page design
- The core logic of the Android app
- Testing the mobile app
- Summary
- Conversational AI Chatbots for Customer Service
- Technical requirements
- Chatbot architecture
- A sequence-to-sequence model using an LSTM
- Building a sequence-to-sequence model
- Customer support on Twitter
- Creating data for training the chatbot
- Tokenizing the text into word indices
- Replacing anonymized screen names
- Defining the model
- Loss function for training the model
- Training the model
- Generating output responses from the model
- Putting it all together
- Invoking the training
- Results of inference on some input tweets
- Summary
- Autonomous Self-Driving Car Through Reinforcement Learning
- Technical requirements
- Markov decision process
- Learning the Q value function
- Deep Q learning
- Formulating the cost function
- Double deep Q learning
- Implementing an autonomous self-driving car
- Discretizing actions for deep Q learning
- Implementing the Double Deep Q network
- Designing the agent
- The environment for the self-driving car
- Putting it all together
- Helper functions
- Results from the training
- Summary
- CAPTCHA from a Deep-Learning Perspective
- Technical requirements
- Breaking CAPTCHAs with deep learning
- Generating basic CAPTCHAs
- Generating data for training a CAPTCHA breaker
- Captcha breaker CNN architecture
- Pre-processing the CAPTCHA images
- Converting the CAPTCHA characters to classes
- Data generator
- Training the CAPTCHA breaker
- Accuracy on the test data set
- CAPTCHA generation through adversarial learning
- Optimizing the GAN loss
- Generator network
- Discriminator network
- Training the GAN
- Noise distribution
- Data preprocessing
- Invoking the training
- The quality of CAPTCHAs during training
- Using the trained generator to create CAPTCHAs for use
- Summary
- Other Books You May Enjoy
- Leave a review - let other readers know what you think 更新時間：2021-07-02 14:11:25
