Throughout the five modules of this course, we're going to show you how you can use Google's

open source TensorFlow library for your deep learning applications.

In module 1, after introducing you to the TensorFlow library and walking you through

a 'hello, world' example, we'll go over a few basic machine learning algorithms.

This will include linear regression, nonlinear regression, and logistic regression.

In addition, we'll cover the different activation functions provided by the library.

In module 2, we'll introduce you to the convolutional neural network, a powerful model that's capable

of object recognition.

Like the brain, it works by passing the inputs through a sequence of increasingly complex

layers.

We'll explain the convolution operation in detail, and then we'll show you how to build

a convolutional net with TensorFlow, in order to recognize handwritten digits.

In module 3, we'll provide an overview of sequential data and recurrent neural networks,

as well as the long short-term memory model.

We'll also go over recursive neural tensor networks and a few natural language processing

applications.

In module 4, we'll introduce you to unsupervised learning.

Our main focus will be on the restricted Boltzmann machine, which detects patterns by reconstructing

its input.

After creating and training a Restricted Boltzmann machine in TensorFlow, we'll show you how

to build a movie recommendation system.

Module 5 will explain the concept of an autoencoder, an unsupervised learning model for detecting

patterns.

The module includes a TensorFlow implementation of an autoencoder, as well as an implementation

of a Deep Belief Network.

There's a lot to go over, but after completing this course, you'll be well on your way to

using TensorFlow in your own applications.

Thanks for watching, and we hope you'll enjoy 'Deep Learning with TensorFlow'!