Deep Learning Fundamentals — Part Three

This is the Third part of the Deep Learning Fundamentals series, if you didn’t read the last two parts yet, read them before reading this one, here are the links:

Deep Learning Fundamentals — Part One

Deep Learning Fundamentals — Part Two

In this post, we’re going to talk about how to choose a deep net and the options you have based on the type of applications you are building.

Picking the right kind of net

First thing you need to decide, is what you are going to build? are you trying to build a classifier? or if you’re trying to find patterns in your data. Let’s see what kind of options we can have for different use cases.

If you’re interested in unsupervised learning , then your best choice here is to use either a RBM ( Restricted Boltzmann Machine ) or an autoencoder.

If you have labeled data for supervised learning and you want to build a classifier, you have a bunch of options, depending on your application:

• If you’re application is a Text…