Search icon CANCEL
Subscription
0
Cart icon
Your Cart (0 item)
Close icon
You have no products in your basket yet
Arrow left icon
Explore Products
Best Sellers
New Releases
Books
Videos
Audiobooks
Learning Hub
Free Learning
Arrow right icon
Arrow up icon
GO TO TOP
Hands-On Neural Networks

You're reading from   Hands-On Neural Networks Learn how to build and train your first neural network model using Python

Arrow left icon
Product type Paperback
Published in May 2019
Publisher Packt
ISBN-13 9781788992596
Length 280 pages
Edition 1st Edition
Languages
Tools
Arrow right icon
Authors (2):
Arrow left icon
Leonardo De Marchi Leonardo De Marchi
Author Profile Icon Leonardo De Marchi
Leonardo De Marchi
Laura Mitchell Laura Mitchell
Author Profile Icon Laura Mitchell
Laura Mitchell
Arrow right icon
View More author details
Toc

Table of Contents (16) Chapters Close

Preface 1. Section 1: Getting Started FREE CHAPTER
2. Getting Started with Supervised Learning 3. Neural Network Fundamentals 4. Section 2: Deep Learning Applications
5. Convolutional Neural Networks for Image Processing 6. Exploiting Text Embedding 7. Working with RNNs 8. Reusing Neural Networks with Transfer Learning 9. Section 3: Advanced Applications
10. Working with Generative Algorithms 11. Implementing Autoencoders 12. Deep Belief Networks 13. Reinforcement Learning 14. Whats Next? 15. Other Books You May Enjoy

Understanding word embeddings

Embedding is a mathematical structure contained within another instance. If we are embedding an object X in an object Y, we will be preserving the structure of the objects and so the instance.

Word embedding is a technique to map words to vectors, creating a multidimensional space that will allow the creation of similar representations for similar words. Each word is represented by a single vector with often tens or hundreds of dimensions, in contrast to other representations such as one-hot encoding that can have thousands or even millions of dimensions.

When we have words in the form of vectors, we end up using all mathematical techniques that we would on pure numbers. Also when transformed into vectors, words will keep the same proprieties that numbers have.

It also means that we could start doing operations as follows:

King - man + woman =queen...

lock icon The rest of the chapter is locked
Register for a free Packt account to unlock a world of extra content!
A free Packt account unlocks extra newsletters, articles, discounted offers, and much more. Start advancing your knowledge today.
Unlock this book and the full library FREE for 7 days
Get unlimited access to 7000+ expert-authored eBooks and videos courses covering every tech area you can think of
Renews at $19.99/month. Cancel anytime
Banner background image