Hands-On Deep Learning Architectures with Python电子书

About Packt

Why subscribe?

Packt.com

Contributors

About the authors

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

Section 1: The Elements of Deep Learning

Getting Started with Deep Learning

Artificial intelligence

Machine learning

Supervised learning

Regression

Classification

Unsupervised learning

Reinforcement learning

Deep learning

Applications of deep learning

Self-driving cars

Image translation

Machine translation

Encoder-decoder structure

Chatbots

Building the fundamentals

Biological inspiration

ANNs

Activation functions

Linear activation

Sigmoid activation

Tanh activation

ReLU activation

Softmax activation

TensorFlow and Keras

Setting up the environment

Introduction to TensorFlow

Installing TensorFlow CPU

Installing TensorFlow GPU

Testing your installation

Getting to know TensorFlow

Building a graph

Creating a Session

Introduction to Keras

Sequential API

Functional API

Summary

Deep Feedforward Networks

Evolutionary path to DFNs

Architecture of DFN

Training

Loss function

Regression loss

Mean squared error (MSE)

Mean absolute error

Classification loss

Cross entropy

Gradient descent

Types of gradient descent

Batch gradient descent

Stochastic gradient descent

Mini-batch gradient descent

Backpropagation

Optimizers

Train, test, and validation

Training set

Validation set

Test set

Overfitting and regularization

L1 and L2 regularization

Dropout

Early stopping

Building our first DFN

MNIST fashion data

Getting the data

Visualizing data

Normalizing and splitting data

Model parameters

One-hot encoding

Building a model graph

Adding placeholders

Adding layers

Adding loss function

Adding an optimizer

Calculating accuracy

Running a session to train

The easy way

Summary

Restricted Boltzmann Machines and Autoencoders

What are RBMs?

The evolution path of RBMs

RBM architectures and applications

RBM and their implementation in TensorFlow

RBMs for movie recommendation

DBNs and their implementation in TensorFlow

DBNs for image classification

What are autoencoders?

The evolution path of autoencoders

Autoencoders architectures and applications

Vanilla autoencoders

Deep autoencoders

Sparse autoencoders

Denoising autoencoders

Contractive autoencoders

Summary

Exercise

Acknowledgements

Section 2: Convolutional Neural Networks

CNN Architecture

Problem with deep feedforward networks

Evolution path to CNNs

Architecture of CNNs

The input layer

The convolutional layer

The maxpooling layer

The fully connected layer

Image classification with CNNs

VGGNet

InceptionNet

ResNet

Building our first CNN

CIFAR

Data loading and pre-processing

Object detection with CNN

R-CNN

Faster R-CNN

You Only Look Once (YOLO)

Single Shot Multibox Detector

TensorFlow object detection zoo

Summary

Mobile Neural Networks and CNNs

Evolution path to MobileNets

Architecture of MobileNets

Depth-wise separable convolution

The need for depth-wise separable convolution

Structure of MobileNet

MobileNet with Keras

MobileNetV2

Motivation behind MobileNetV2

Structure of MobileNetV2

Linear bottleneck layer

Expansion layer

Inverted residual block

Overall architecture

Implementing MobileNetV2

Comparing the two MobileNets

SSD MobileNetV2

Summary

Section 3: Sequence Modeling

Recurrent Neural Networks

What are RNNs?

The evolution path of RNNs

RNN architectures and applications

Architectures by input and output

Vanilla RNNs

Vanilla RNNs for text generation

LSTM RNNs

LSTM RNNs for text generation

GRU RNNs

GRU RNNs for stock price prediction

Bidirectional RNNs

Bidirectional RNNs for sentiment classification

Summary

Section 4: Generative Adversarial Networks (GANs)

Generative Adversarial Networks

What are GANs?

Generative models

Adversarial – training in an adversarial manner

The evolution path of GANs

GAN architectures and implementations

Vanilla GANs

Deep convolutional GANs

Conditional GANs

InfoGANs

Summary

Section 5: The Future of Deep Learning and Advanced Artificial Intelligence

New Trends of Deep Learning

New trends in deep learning

Bayesian neural networks

What our deep learning models don't know – uncertainty

How we can obtain uncertainty information – Bayesian neural networks

Capsule networks

What convolutional neural networks fail to do

Capsule networks – incorporating oriental and relative spatial relationships

Meta-learning

One big challenge in deep learning – training data

Meta-learning – learning to learn

Metric-based meta-learning

Summary

Other Books You May Enjoy

Leave a review - let other readers know what you think