Search icon CANCEL
Arrow left icon
Explore Products
Best Sellers
New Releases
Books
Videos
Audiobooks
Learning Hub
Conferences
Free Learning
Arrow right icon
Arrow up icon
GO TO TOP
Deep Learning for Beginners

You're reading from   Deep Learning for Beginners A beginner's guide to getting up and running with deep learning from scratch using Python

Arrow left icon
Product type Paperback
Published in Sep 2020
Publisher Packt
ISBN-13 9781838640859
Length 432 pages
Edition 1st Edition
Languages
Tools
Arrow right icon
Authors (2):
Arrow left icon
Pablo Rivas Pablo Rivas
Author Profile Icon Pablo Rivas
Pablo Rivas
Dr. Pablo Rivas Dr. Pablo Rivas
Author Profile Icon Dr. Pablo Rivas
Dr. Pablo Rivas
Arrow right icon
View More author details
Toc

Table of Contents (20) Chapters Close

Preface 1. Section 1: Getting Up to Speed
2. Introduction to Machine Learning FREE CHAPTER 3. Setup and Introduction to Deep Learning Frameworks 4. Preparing Data 5. Learning from Data 6. Training a Single Neuron 7. Training Multiple Layers of Neurons 8. Section 2: Unsupervised Deep Learning
9. Autoencoders 10. Deep Autoencoders 11. Variational Autoencoders 12. Restricted Boltzmann Machines 13. Section 3: Supervised Deep Learning
14. Deep and Wide Neural Networks 15. Convolutional Neural Networks 16. Recurrent Neural Networks 17. Generative Adversarial Networks 18. Final Remarks on the Future of Deep Learning 19. Other Books You May Enjoy

Learning for a purpose

In Chapter 3, Preparing Data, we discussed how to prepare data for two major types of problems: regression and classification. In this section, we will cover the technical differences between classification and regression in more detail. These differences are important because they will limit the type of machine learning algorithms you can use to solve your problem.

Classification

How do you know whether your problem is classification? The answer depends on two major factors: the problem you are trying to solve and the data you have to solve your problem. There might be other factors, for sure, but these two are by far the most significant.

If your purpose is to make a model that, given some input, will determine whether the response or output of the model is to distinguish between two or more distinct categories, then you have a classification problem. Here is a non-exhaustive list of examples of classification problems:

  • Given an image, indicate what number it...
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