What do you get with Print?

Instant access to your digital eBook copy whilst your Print order is Shipped

Colour book shipped to your preferred address

Download this book in EPUB and PDF formats

Access this title in our online reader with advanced features

DRM FREE - Read whenever, wherever and however you want

AI Assistant (beta) to help accelerate your learning

Deep Learning for Time Series Cookbook

Getting Started with PyTorch

In this chapter, we’ll explore PyTorch, a leading deep learning library in Python.

We go over several operations that are useful for understanding how neural networks are built using PyTorch. Besides tensor operations, we will also explore how to train different types of neural networks. Specifically, we will focus on feedforward, recurrent, long short-term memory (LSTM), and 1D convolutional networks.

In later chapters, we will also cover other types of neural networks, such as transformers. Here, we will use synthetic data for demonstrative purposes, which will help us showcase both the implementation and theory behind each model.

Upon completing this chapter, you will have gained a robust understanding of PyTorch, equipping you with the tools for more advanced deep learning projects.

In this chapter, we will cover the following recipes:

Installing PyTorch
Basic operations in PyTorch
Advanced operations in PyTorch

Key benefits

Learn the fundamentals of time series analysis and how to model time series data using deep learning

Explore the world of deep learning with PyTorch and build advanced deep neural networks

Gain expertise in tackling time series problems, from forecasting future trends to classifying patterns and anomaly detection

Purchase of the print or Kindle book includes a free PDF eBook

Description

Most organizations exhibit a time-dependent structure in their processes, including fields such as finance. By leveraging time series analysis and forecasting, these organizations can make informed decisions and optimize their performance. Accurate forecasts help reduce uncertainty and enable better planning of operations. Unlike traditional approaches to forecasting, deep learning can process large amounts of data and help derive complex patterns. Despite its increasing relevance, getting the most out of deep learning requires significant technical expertise. This book guides you through applying deep learning to time series data with the help of easy-to-follow code recipes. You’ll cover time series problems, such as forecasting, anomaly detection, and classification. This deep learning book will also show you how to solve these problems using different deep neural network architectures, including convolutional neural networks (CNNs) or transformers. As you progress, you’ll use PyTorch, a popular deep learning framework based on Python to build production-ready prediction solutions. By the end of this book, you'll have learned how to solve different time series tasks with deep learning using the PyTorch ecosystem.

What you will learn

Grasp the core of time series analysis and unleash its power using Python

Understand PyTorch and how to use it to build deep learning models

Discover how to transform a time series for training transformers

Understand how to deal with various time series characteristics

Tackle forecasting problems, involving univariate or multivariate data

Master time series classification with residual and convolutional neural networks

Get up to speed with solving time series anomaly detection problems using autoencoders and generative adversarial networks (GANs)

What do you get with Print?

Instant access to your digital eBook copy whilst your Print order is Shipped

Colour book shipped to your preferred address

Download this book in EPUB and PDF formats

Access this title in our online reader with advanced features

DRM FREE - Read whenever, wherever and however you want

AI Assistant (beta) to help accelerate your learning

Frequently bought together

€37.99

€38.99

€37.99

Total € 114.97

Filter reviews by

All

Amazon verified reviews

Amazon Customer May 06, 2024

"Deep Learning for Time Series Cookbook" by Vitor Cerqueira and Luís Roque is a comprehensive guide for those interested in forecasting, classification, and anomaly detection in time series data. The book caters to readers with a basic knowledge of Python and machine learning, offering practical code snippets to reinforce learning. Each chapter covers essential concepts progressively, from basic time series fundamentals to advanced techniques like N-BEATS and Temporal Fusion Transformers. Topics include univariate and multivariate forecasting, hyperparameter optimization, time series classification using various models, and anomaly detection using autoencoders and generative adversarial networks.Overall, this book is a valuable resource for anyone embarking on their time series modeling journey, providing a blend of theoretical explanations and hands-on examples. It's recommended for readers seeking a practical guide to implementing diverse time series analysis techniques, making it a must-read for those interested in mastering this domain.

Amazon Verified review

Amazon Kunde Apr 17, 2024

This is neither an introductory book nor something to read from cover to cover.But if you've already read an introduction into pyTorch and you're working on some kind of Time Series Project - this is what you wanna have on your desk!Dozens of great examples and answers to those typical questions "I want to do xyz, i know it needed something from statsmodels, but what was that again?". It's not just examples/answers but also combined with explanations on HOW and WHY you'd do things as they are described.Really a great book for the more experienced pyTorch user!

hugomcroque May 11, 2024

While trying to learn how NeuralForecast works, I ended up using this book to obtain working code to get me started. It is a good resource for that, you can grab code to get started on almost every task in time series analysis. I also learned a lot from reading the probabilistic forecasting chapter, very interesting!

Didi Apr 21, 2024

Time series forecasting - making predictions based on historical data - is an important subfield of statistics and machine learning (ML). Following the deep learning (DL) revolution that has completely transformed the fields of computer vision and natural language processing in recent years, the field of time series modeling and analysis is now also being revolutionized by DL-based approaches.This book is a unique and comprehensive guide to time series forecasting, classification, and analysis using DL. This practical guide begins with an introduction to time series modeling using Python, including topics such as time series visualization, resampling, and dealing with missing data. It proceeds with an introduction to the PyTorch and PyTorch Lightning libraries and their use for time series forecasting, followed by a description of advanced DL architectures and methods for forecasting, such as the use of transformers and probabilistic forecasting. The last part of the book describes a variety of methods for solving the important problems of time series classification and anomaly detection.To get the most out of this book, readers are expected to have some familiarity with Python, and preferably also with its popular data manipulation libraries such as pandas and NumPy. The accompanying GitHub repo is well-organized and very helpful in reinforcing the concepts described in the book.This book is a wonderful, up-to-date resource for researchers, data scientists, and software engineers interested in building DL-based time series forecasting and analysis models in Python. Highly recommended!

TM May 10, 2024

I have been enrolled in a data science program, and one of my instructors recommended using this book for our time series module. It is very well structured and provides a comprehensive overview of the topic. What I appreciate most is how it gradually increases in complexity. The basics are covered with sufficient detail to help you understand the fundamentals. You then quickly move on to solving real time series forecasting problems, which is motivating and gives a sense of progress. I also learned many new concepts; for example, I was unfamiliar with global time series forecasting models and what sets them apart. The book offers state-of-the-art examples with models such as N-BEATS and Temporal Fusion Transformers. In later chapters, it explores other methods of producing forecasts, for example, by generating probabilistic outputs. By the end, I felt my understanding of time series forecasting was quite strong, and I can now discuss the topic with friends who have been working in this field for many years in the industry.