Book Image

The Deep Learning with PyTorch Workshop

By : Hyatt Saleh
Book Image

The Deep Learning with PyTorch Workshop

By: Hyatt Saleh

Overview of this book

Want to get to grips with one of the most popular machine learning libraries for deep learning? The Deep Learning with PyTorch Workshop will help you do just that, jumpstarting your knowledge of using PyTorch for deep learning even if you’re starting from scratch. It’s no surprise that deep learning’s popularity has risen steeply in the past few years, thanks to intelligent applications such as self-driving vehicles, chatbots, and voice-activated assistants that are making our lives easier. This book will take you inside the world of deep learning, where you’ll use PyTorch to understand the complexity of neural network architectures. The Deep Learning with PyTorch Workshop starts with an introduction to deep learning and its applications. You’ll explore the syntax of PyTorch and learn how to define a network architecture and train a model. Next, you’ll learn about three main neural network architectures - convolutional, artificial, and recurrent - and even solve real-world data problems using these networks. Later chapters will show you how to create a style transfer model to develop a new image from two images, before finally taking you through how RNNs store memory to solve key data issues. By the end of this book, you’ll have mastered the essential concepts, tools, and libraries of PyTorch to develop your own deep neural networks and intelligent apps.

Related Content you might be interested in

Current Title:

Small book image
The Deep Learning with PyTorch Workshop
Hyatt Saleh
Jul, 2020 | 330 pages
Small book image
The Machine Learning Workshop
Hyatt Saleh
Jul, 2020 | 286 pages
Small book image
Machine Learning Fundamentals
Hyatt Saleh
Nov, 2018 | 240 pages
Small book image
Deep Learning with PyTorch Quick Start Guide
David Julian
Dec, 2018 | 158 pages
Table of Contents (8 chapters)
Preface
About the Book
1
1. Introduction to Deep Learning and PyTorch
1. Introduction to Deep Learning and PyTorch
Introduction
Why Deep Learning?
Introduction to PyTorch
Summary
Free Chapter
2
2. Building Blocks of Neural Networks
2. Building Blocks of Neural Networks
Introduction
Introduction to Neural Networks
Data Preparation
Building a Deep Neural Network
Summary
3
3. A Classification Problem Using DNN
3. A Classification Problem Using DNN
Introduction
Problem Definition
Dealing with an Underfitted or Overfitted Model
Deploying Your Model
Summary
4
4. Convolutional Neural Networks
4. Convolutional Neural Networks
Introduction
Building a CNN
Data Augmentation
Batch Normalization
Summary
5
5. Style Transfer
5. Style Transfer
Introduction
Style Transfer
Implementation of Style Transfer Using the VGG-19 Network Architecture
Summary
6
6. Analyzing the Sequence of Data with RNNs
6. Analyzing the Sequence of Data with RNNs
Introduction
Recurrent Neural Networks
Long Short-Term Memory Networks
LSTM Networks in PyTorch
Natural Language Processing
Sentiment Analysis in PyTorch
Summary
Appendix
1. Introduction to Deep Learning and PyTorch
2. Building Blocks of Neural Networks
3. A Classification Problem Using DNNs
4. Convolutional Neural Networks
5. Style Transfer
6. Analyzing the Sequence of Data with RNNs

Long Short-Term Memory Networks

As we mentioned previously, RNNs store short-term memory only. This is an issue when dealing with long sequences of data, where the network will have trouble carrying the information from the earlier steps to the final ones.

For instance, take the poem "The Raven," which was written by the famous poet Edgar Alan Poe and is over 1,000 words long. Attempting to process it using a traditional RNN, with the objective of creating a similar related poem, will result in the model leaving out crucial information from the first couple of paragraphs. This, in turn, may result in an output that is unrelated to the initial subject of the poem. For instance, it could ignore that the event occurred at night, and so make the new poem not very scary.

This inability to hold long-term memory occurs because traditional RNNs suffer from a problem called vanishing gradients. This occurs when the gradients, which are used to update the parameters of the network...

Previous Section
End of Section 4
Next Section