最新章節

• Leave a review - let other readers know what you think
• Other Books You May Enjoy
• Code for fish recognition
• Implementing Fish Recognition
• Summary
• Model training

• Leave a review - let other readers know what you think 更新時間：2021-06-24 18:53:26
• Other Books You May Enjoy
• Code for fish recognition
• Implementing Fish Recognition
• Summary
• Model training
• Model optimizer
• Model losses
• Discriminator
• Generator
• Model inputs
• Building the model
• Data analysis and preprocessing
• Intuition
• Semi-supervised learning with Generative Adversarial Networks (GANs)
• Training the model
• Model optimizer
• Model losses
• Generator
• Discriminator
• Model inputs
• Building the model
• Exploring the Data
• Getting the data
• Face generation
• Face Generation and Handling Missing Labels
• Summary
• Sampling from the generator
• Generator samples from training
• Model training
• Optimizers
• Discriminator and generator losses
• Defining the generator and discriminator
• Model hyperparameters
• Building the GAN network
• Discriminator
• Generator
• Leaky ReLU
• Variable scope
• Model inputs
• Simple implementation of GANs
• An intuitive introduction
• Generative Adversarial Networks
• Summary
• More applications
• Image colorization
• Applications of autoencoders
• Model training
• Building the model
• Denoising autoencoders
• Model training
• Building the model
• Dataset
• Convolutional autoencoder
• Model training
• Building the model
• The MNIST dataset
• Compressing the MNIST dataset
• Autoencoder architectures
• Examples of autoencoders
• Introduction to autoencoders
• Autoencoders – Feature Extraction and Denoising
• Summary
• Model training and results analysis
• Building the model
• Data analysis and preprocessing
• Keras
• Sentiment analysis – model implementation
• Exploding and vanishing gradients - recap
• RNNs – sentiment analysis context
• General sentiment analysis architecture
• Neural Sentiment Analysis
• Summary
• Training
• Building the model
• Data analysis and pre-processing
• Skip-gram Word2Vec implementation
• A practical example of the skip-gram architecture
• Building Word2Vec model
• Word2Vec
• Introduction to representation learning
• Representation Learning - Implementing Word Embeddings
• Summary
• Generating text
• Saving checkpoints
• Training the model
• Model hyperparameters
• Building the network
• Optimizer
• Training loss
• RNN output
• Building an LSTM cell
• Inputs
• Model architecture
• Stacked LSTMs
• Building the model
• Mini-batch generation for training
• Implementation of the language model
• Why does LSTM work?
• LSTM networks
• The problem of long-term dependencies
• The vanishing gradient problem
• Language model using Shakespeare data
• Character-level language models
• Examples of RNNs
• Recurrent neural networks architectures
• The intuition behind RNNs
• Recurrent-Type Neural Networks - Language Modeling
• Summary
• Model building and training
• Analysis of transfer values
• Inception model transfer values
• Loading and exploring CIFAR-10
• Solution outline
• CIFAR-10 object detection – revisited
• Differences between traditional machine learning and TL
• The intuition behind TL
• Transfer learning
• Object Detection – Transfer Learning with CNNs
• Summary
• Testing the model
• Model training
• Building the network
• Data analysis and preprocessing
• Loading the CIFAR-10 dataset
• Used packages
• CIFAR-10 – modeling building and training
• Object detection
• Object Detection – CIFAR-10 Example
• Summary
• Model training
• Performance measures
• Cost function
• Building the model
• CNN basic example – MNIST digit classification
• Logits layer
• Fully connected layer
• The pooling step
• Introducing non-linearity
• Convolution step
• Input layer
• Different layers of CNNs
• Applications of CNNs
• Motivation
• The convolution operation
• Introduction to Convolutional Neural Networks
• Summary
• Model training
• Building the model
• Data analysis
• Digit classification – model building and training
• The MNIST data
• MNIST dataset analysis
• Hidden units and architecture design
• Deep Feed-forward Neural Networks - Implementing Digit Classification
• Summary
• Cost function
• Training
• Logistic regression model
• Set model weights and bias
• Why use placeholders?
• Utilizing logistic regression in TensorFlow
• Logistic regression model – building and training
• Linear regression with TensorFlow
• Linear regression model – building and training
• Operations
• Placeholders
• Variables
• Why tensors?
• Defining multidimensional arrays using TensorFlow
• TensorFlow terminologies – recap
• Step 2 – backpropagation and weight updation
• Step 1 – forward propagation
• Training our MLP – the backpropagation algorithm
• The need for multilayer networks
• Feed-forward neural network
• ReLU
• Tanh
• Sigmoid
• Activation functions
• Biological motivation and connections
• Capacity of a single neuron
• TensorFlow in Action - Some Basic Examples
• Summary
• TensorBoard – visualizing learning
• Getting output from TensorFlow
• Mathematical operations
• Placeholders
• Variables
• TensorFlow data types variables and placeholders
• Computational graphs
• The TensorFlow environment
• TensorFlow GPU/CPU installation for Windows
• TensorFlow CPU installation for macOS X
• TensorFlow CPU installation for Ubuntu 16.04
• Installing TensorFlow
• Installing NVIDIA drivers and CUDA 8
• TensorFlow GPU installation for Ubuntu 16.04
• TensorFlow installation
• Get Up and Running with TensorFlow
• Summary
• Breaking the rule of thumb
• Learning visibility
• Bias-variance decomposition
• Titanic example revisited – all together
• Avoiding the curse of dimensionality
• The curse of dimensionality
• Interaction features
• Ticket
• Cabin
• Name
• Derived features
• Binning
• Scaling
• Factorizing
• Dummy features
• Feature transformations
• Using a regression or another simple model to predict the values of missing variables
• Assigning an average value
• Missing value inputting
• Removing any sample with missing values in it
• Missing values
• Titanic example revisited
• Feature construction
• Dimensionality reduction
• Feature selection
• Types of feature engineering
• Feature engineering
• Feature Engineering and Model Complexity – The Titanic Example Revisited
• Summary
• Generalization/true error
• Apparent (training set) error
• Different types of errors
• Data analysis – supervised machine learning
• Data handling and visualization
• Titanic example – model building and training
• Classification and logistic regression
• Linear models for classification
• Using the model for prediction
• Interpreting model coefficients
• Learning model coefficients
• Simple regression model
• Data analysis and visualization
• Understanding the advertising data
• Importing data with pandas
• Dependencies
• Advertising – a financial example
• Motivation
• Linear models for regression
• Data Modeling in Action - The Titanic Example
• Summary
• Data size and industry needs
• Reinforcement learning
• Semi-supervised learning
• Unsupervised learning
• Supervised learning
• Different learning types
• Fish recognition – all together
• Model training and testing
• Model building
• Data analysis pre-processing
• Knowledge base/dataset
• Implementing the fish recognition/detection model
• Missing values
• Prior knowledge
• Selection of a machine learning algorithm
• Overfitting
• Noise
• Feature extraction – feature engineering
• Challenges of learning
• Getting to learn
• Evaluating your model
• Learning process
• Model selection
• Feature selection
• Data pre-processing
• Data cleaning
• Data pre-processing
• Design procedure of data science algorithms
• Understanding data science by an example
• Data Science - A Birds' Eye View
• 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 reviewers
• About the author
• Contributors
• PacktPub.com
• Why subscribe?
• Packt Upsell
• Title Page
• coverpage

• coverpage
• Title Page
• Packt Upsell
• Why subscribe?
• PacktPub.com
• Contributors
• About the author
• About the reviewers
• 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
• Data Science - A Birds' Eye View
• Understanding data science by an example
• Design procedure of data science algorithms
• Data pre-processing
• Data cleaning
• Data pre-processing
• Feature selection
• Model selection
• Learning process
• Evaluating your model
• Getting to learn
• Challenges of learning
• Feature extraction – feature engineering
• Noise
• Overfitting
• Selection of a machine learning algorithm
• Prior knowledge
• Missing values
• Implementing the fish recognition/detection model
• Knowledge base/dataset
• Data analysis pre-processing
• Model building
• Model training and testing
• Fish recognition – all together
• Different learning types
• Supervised learning
• Unsupervised learning
• Semi-supervised learning
• Reinforcement learning
• Data size and industry needs
• Summary
• Data Modeling in Action - The Titanic Example
• Linear models for regression
• Motivation
• Advertising – a financial example
• Dependencies
• Importing data with pandas
• Understanding the advertising data
• Data analysis and visualization
• Simple regression model
• Learning model coefficients
• Interpreting model coefficients
• Using the model for prediction
• Linear models for classification
• Classification and logistic regression
• Titanic example – model building and training
• Data handling and visualization
• Data analysis – supervised machine learning
• Different types of errors
• Apparent (training set) error
• Generalization/true error
• Summary
• Feature Engineering and Model Complexity – The Titanic Example Revisited
• Feature engineering
• Types of feature engineering
• Feature selection
• Dimensionality reduction
• Feature construction
• Titanic example revisited
• Missing values
• Removing any sample with missing values in it
• Missing value inputting
• Assigning an average value
• Using a regression or another simple model to predict the values of missing variables
• Feature transformations
• Dummy features
• Factorizing
• Scaling
• Binning
• Derived features
• Name
• Cabin
• Ticket
• Interaction features
• The curse of dimensionality
• Avoiding the curse of dimensionality
• Titanic example revisited – all together
• Bias-variance decomposition
• Learning visibility
• Breaking the rule of thumb
• Summary
• Get Up and Running with TensorFlow
• TensorFlow installation
• TensorFlow GPU installation for Ubuntu 16.04
• Installing NVIDIA drivers and CUDA 8
• Installing TensorFlow
• TensorFlow CPU installation for Ubuntu 16.04
• TensorFlow CPU installation for macOS X
• TensorFlow GPU/CPU installation for Windows
• The TensorFlow environment
• Computational graphs
• TensorFlow data types variables and placeholders
• Variables
• Placeholders
• Mathematical operations
• Getting output from TensorFlow
• TensorBoard – visualizing learning
• Summary
• TensorFlow in Action - Some Basic Examples
• Capacity of a single neuron
• Biological motivation and connections
• Activation functions
• Sigmoid
• Tanh
• ReLU
• Feed-forward neural network
• The need for multilayer networks
• Training our MLP – the backpropagation algorithm
• Step 1 – forward propagation
• Step 2 – backpropagation and weight updation
• TensorFlow terminologies – recap
• Defining multidimensional arrays using TensorFlow
• Why tensors?
• Variables
• Placeholders
• Operations
• Linear regression model – building and training
• Linear regression with TensorFlow
• Logistic regression model – building and training
• Utilizing logistic regression in TensorFlow
• Why use placeholders?
• Set model weights and bias
• Logistic regression model
• Training
• Cost function
• Summary
• Deep Feed-forward Neural Networks - Implementing Digit Classification
• Hidden units and architecture design
• MNIST dataset analysis
• The MNIST data
• Digit classification – model building and training
• Data analysis
• Building the model
• Model training
• Summary
• Introduction to Convolutional Neural Networks
• The convolution operation
• Motivation
• Applications of CNNs
• Different layers of CNNs
• Input layer
• Convolution step
• Introducing non-linearity
• The pooling step
• Fully connected layer
• Logits layer
• CNN basic example – MNIST digit classification
• Building the model
• Cost function
• Performance measures
• Model training
• Summary
• Object Detection – CIFAR-10 Example
• Object detection
• CIFAR-10 – modeling building and training
• Used packages
• Loading the CIFAR-10 dataset
• Data analysis and preprocessing
• Building the network
• Model training
• Testing the model
• Summary
• Object Detection – Transfer Learning with CNNs
• Transfer learning
• The intuition behind TL
• Differences between traditional machine learning and TL
• CIFAR-10 object detection – revisited
• Solution outline
• Loading and exploring CIFAR-10
• Inception model transfer values
• Analysis of transfer values
• Model building and training
• Summary
• Recurrent-Type Neural Networks - Language Modeling
• The intuition behind RNNs
• Recurrent neural networks architectures
• Examples of RNNs
• Character-level language models
• Language model using Shakespeare data
• The vanishing gradient problem
• The problem of long-term dependencies
• LSTM networks
• Why does LSTM work?
• Implementation of the language model
• Mini-batch generation for training
• Building the model
• Stacked LSTMs
• Model architecture
• Inputs
• Building an LSTM cell
• RNN output
• Training loss
• Optimizer
• Building the network
• Model hyperparameters
• Training the model
• Saving checkpoints
• Generating text
• Summary
• Representation Learning - Implementing Word Embeddings
• Introduction to representation learning
• Word2Vec
• Building Word2Vec model
• A practical example of the skip-gram architecture
• Skip-gram Word2Vec implementation
• Data analysis and pre-processing
• Building the model
• Training
• Summary
• Neural Sentiment Analysis
• General sentiment analysis architecture
• RNNs – sentiment analysis context
• Exploding and vanishing gradients - recap
• Sentiment analysis – model implementation
• Keras
• Data analysis and preprocessing
• Building the model
• Model training and results analysis
• Summary
• Autoencoders – Feature Extraction and Denoising
• Introduction to autoencoders
• Examples of autoencoders
• Autoencoder architectures
• Compressing the MNIST dataset
• The MNIST dataset
• Building the model
• Model training
• Convolutional autoencoder
• Dataset
• Building the model
• Model training
• Denoising autoencoders
• Building the model
• Model training
• Applications of autoencoders
• Image colorization
• More applications
• Summary
• Generative Adversarial Networks
• An intuitive introduction
• Simple implementation of GANs
• Model inputs
• Variable scope
• Leaky ReLU
• Generator
• Discriminator
• Building the GAN network
• Model hyperparameters
• Defining the generator and discriminator
• Discriminator and generator losses
• Optimizers
• Model training
• Generator samples from training
• Sampling from the generator
• Summary
• Face Generation and Handling Missing Labels
• Face generation
• Getting the data
• Exploring the Data
• Building the model
• Model inputs
• Discriminator
• Generator
• Model losses
• Model optimizer
• Training the model
• Semi-supervised learning with Generative Adversarial Networks (GANs)
• Intuition
• Data analysis and preprocessing
• Building the model
• Model inputs
• Generator
• Discriminator
• Model losses
• Model optimizer
• Model training
• Summary
• Implementing Fish Recognition
• Code for fish recognition
• Other Books You May Enjoy
• Leave a review - let other readers know what you think 更新時間：2021-06-24 18:53:26