Book Overview & Buying
Table Of Contents

Python Deep Learning Cookbook

By : Indra den Bakker

3.7 (3)

Buy this Book

Python Deep Learning Cookbook

3.7 (3)

By: Indra den Bakker

Buy this Book

Overview of this book

Deep Learning is revolutionizing a wide range of industries. For many applications, deep learning has proven to outperform humans by making faster and more accurate predictions. This book provides a top-down and bottom-up approach to demonstrate deep learning solutions to real-world problems in different areas. These applications include Computer Vision, Natural Language Processing, Time Series, and Robotics. The Python Deep Learning Cookbook presents technical solutions to the issues presented, along with a detailed explanation of the solutions. Furthermore, a discussion on corresponding pros and cons of implementing the proposed solution using one of the popular frameworks like TensorFlow, PyTorch, Keras and CNTK is provided. The book includes recipes that are related to the basic concepts of neural networks. All techniques s, as well as classical networks topologies. The main purpose of this book is to provide Python programmers a detailed list of recipes to apply deep learning to common and not-so-common scenarios.

Preface

What this book covers

What you need for this book

Who this book is for

Conventions

Reader feedback

Customer support

Free Chapter

Programming Environments, GPU Computing, Cloud Solutions, and Deep Learning Frameworks

Introduction

Setting up a deep learning environment

Launching an instance on Amazon Web Services (AWS)

Launching an instance on Google Cloud Platform (GCP)

Installing CUDA and cuDNN

Installing Anaconda and libraries

Connecting with Jupyter Notebooks on a server

Building state-of-the-art, production-ready models with TensorFlow

Intuitively building networks with Keras

Using PyTorch’s dynamic computation graphs for RNNs

Implementing high-performance models with CNTK

Building efficient models with MXNet

Defining networks using simple and efficient code with Gluon

Feed-Forward Neural Networks

Introduction

Understanding the perceptron

Implementing a single-layer neural network

Building a multi-layer neural network

Getting started with activation functions

Experiment with hidden layers and hidden units

Implementing an autoencoder

Tuning the loss function

Experimenting with different optimizers

Improving generalization with regularization

Adding dropout to prevent overfitting

Convolutional Neural Networks

Introduction

Applying pooling layers

Optimizing with batch normalization

Understanding padding and strides

Experimenting with different types of initialization

Implementing a convolutional autoencoder

Applying a 1D CNN to text

Recurrent Neural Networks

Introduction

Implementing a simple RNN

Adding Long Short-Term Memory (LSTM)

Using gated recurrent units (GRUs)

Implementing bidirectional RNNs

Character-level text generation

Reinforcement Learning

Introduction

Implementing policy gradients

Implementing a deep Q-learning algorithm

Generative Adversarial Networks

Introduction

Understanding GANs

Implementing Deep Convolutional GANs (DCGANs)

Upscaling the resolution of images with Super-Resolution GANs (SRGANs)

Computer Vision

Introduction

Augmenting images with computer vision techniques

Classifying objects in images

Localizing an object in images

Segmenting classes in images with U-net

Scene understanding (semantic segmentation)

Finding facial key points

Recognizing faces

Transferring styles to images

Natural Language Processing

Introduction

Analyzing sentiment

Translating sentences

Summarizing text

Speech Recognition and Video Analysis

Introduction

Implementing a speech recognition pipeline from scratch

Identifying speakers with voice recognition

Understanding videos with deep learning

Time Series and Structured Data

Introduction

Predicting stock prices with neural networks

Predicting bike sharing demand

Using a shallow neural network for binary classification

Game Playing Agents and Robotics

Introduction

Learning to drive a car with end-to-end learning

Learning to play games with deep reinforcement learning

Genetic Algorithm (GA) to optimize hyperparameters

Hyperparameter Selection, Tuning, and Neural Network Learning

Introduction

Visualizing training with TensorBoard and Keras

Working with batches and mini-batches

Using grid search for parameter tuning

Learning rates and learning rate schedulers

Comparing optimizers

Determining the depth of the network

Adding dropouts to prevent overfitting

Making a model more robust with data augmentation

Network Internals

Introduction

Visualizing training with TensorBoard

Analyzing network weights and more

Freezing layers

Storing the network topology and trained weights

Pretrained Models

Introduction

Large-scale visual recognition with GoogLeNet/Inception

Extracting bottleneck features with ResNet

Leveraging pretrained VGG models for new classes

Fine-tuning with Xception

Comparing optimizers

In Chapter 2, Feed-Forward Neural Networks, we briefly demonstrated the use of different optimizers. Of course, we only used a test set of size 1. As for other machine learning algorithms, the most used and well-known optimizer for deep learning is Stochastic Gradient Descent (SGD). Other optimizers are variants of SGD that try to speed up convergence by adding heuristics. Also, some optimizers have fewer hyperparameters to tune. The table shown in the Chapter 2, Feed-Forward Neural Networks, is an overview of the most commonly used optimizers in deep learning.

One could argue that the choice largely depends on the user's ability to tune the optimizer. There is definitely no ideal solution that works best for all problems. However, some optimizers have fewer parameters to tune and have proven to outperform other optimizers with default...

Tech Concepts

Programming languages

Tech Tools