Book Image

Advanced Deep Learning with Python

By : Ivan Vasilev

Book Image

Advanced Deep Learning with Python

By: Ivan Vasilev

Overview of this book

In order to build robust deep learning systems, you’ll need to understand everything from how neural networks work to training CNN models. In this book, you’ll discover newly developed deep learning models, methodologies used in the domain, and their implementation based on areas of application. You’ll start by understanding the building blocks and the math behind neural networks, and then move on to CNNs and their advanced applications in computer vision. You'll also learn to apply the most popular CNN architectures in object detection and image segmentation. Further on, you’ll focus on variational autoencoders and GANs. You’ll then use neural networks to extract sophisticated vector representations of words, before going on to cover various types of recurrent networks, such as LSTM and GRU. You’ll even explore the attention mechanism to process sequential data without the help of recurrent neural networks (RNNs). Later, you’ll use graph neural networks for processing structured data, along with covering meta-learning, which allows you to train neural networks with fewer training samples. Finally, you’ll understand how to apply deep learning to autonomous vehicles. By the end of this book, you’ll have mastered key deep learning concepts and the different applications of deep learning models in the real world.

Preface

Who this book is for

What this book covers

To get the most out of this book

Free Chapter

Section 1: Core Concepts

Section 1: Core Concepts

The Nuts and Bolts of Neural Networks

The Nuts and Bolts of Neural Networks

The mathematical apparatus of NNs

A short introduction to NNs

Section 2: Computer Vision

Section 2: Computer Vision

Understanding Convolutional Networks

Understanding Convolutional Networks

Understanding CNNs

Introducing transfer learning

Advanced Convolutional Networks

Advanced Convolutional Networks

Introducing AlexNet

An introduction to Visual Geometry Group

Understanding residual networks

Understanding Inception networks

Introducing Xception

Introducing MobileNet

An introduction to DenseNets

The workings of neural architecture search

Introducing capsule networks

Object Detection and Image Segmentation

Object Detection and Image Segmentation

Introduction to object detection

Introducing image segmentation

Generative Models

Generative Models

Intuition and justification of generative models

Introduction to VAEs

Introduction to GANs

Introducing artistic style transfer

Section 3: Natural Language and Sequence Processing

Section 3: Natural Language and Sequence Processing

Language Modeling

Language Modeling

Understanding n-grams

Introducing neural language models

Implementing language models

Understanding Recurrent Networks

Understanding Recurrent Networks

Introduction to RNNs

Introducing long short-term memory

Introducing gated recurrent units

Implementing text classification

Sequence-to-Sequence Models and Attention

Sequence-to-Sequence Models and Attention

Introducing seq2seq models

Seq2seq with attention

Understanding transformers

Transformer language models

Section 4: A Look to the Future

Section 4: A Look to the Future

Emerging Neural Network Designs

Emerging Neural Network Designs

Introducing Graph NNs

Introducing memory-augmented NNs

Meta Learning

Introduction to meta learning

Metric-based meta learning

Optimization-based learning

Deep Learning for Autonomous Vehicles

Deep Learning for Autonomous Vehicles

Introduction to AVs

Components of an AV system

Introduction to 3D data processing

Imitation driving policy

Driving policy with ChauffeurNet

Other Books You May Enjoy

Other Books You May Enjoy

Leave a review - let other readers know what you think

Customer Reviews

5 star

0

4 star

0

3 star

0

2 star

0

1 star

0

Implementing text classification

Let's recap on this chapter so far. We started by implementing an RNN using only numpy. Then, we continued with an LSTM implementation using primitive PyTorch operations. We'll conclude this arc by training the default PyTorch 1.3.1 LSTM implementation for a text classification problem. This example also requires the torchtext 0.4.0 package. Text classification (or categorization) refers to the task of assigning categories (or labels) depending on its contents. Text classification tasks include spam detection, topic labeling, and sentiment analysis. This type of problem is an example of a many-to-one relationship, which we defined in the Introduction to RNNs section.

In this section, we'll implement a sentiment analysis example over the Large Movie Review Dataset (http://ai.stanford.edu/~amaas/data/sentiment/), which consists of...