Building Unsupervised Learning Models with TensorFlow

Unsupervised learning techniques work with huge data sets to find patterns within the data. This course teaches you the details of clustering and autoencoding, two versatile unsupervised learning techniques, and how to implement them in TensorFlow.
Course info
Rating
(20)
Level
Intermediate
Updated
Oct 24, 2017
Duration
3h 3m
Table of contents
Course Overview
Introduction to Unsupervised Learning
Clustering Using Unsupervised Learning
Understanding Neurons and Neural Networks
Autoencoders Using Unsupervised Learning
Description
Course info
Rating
(20)
Level
Intermediate
Updated
Oct 24, 2017
Duration
3h 3m
Description

Unsupervised learning techniques are powerful, but under utilized and often not well understood. In this course, Building Unsupervised Learning Models with TensorFlow, you'll learn the various characteristics and features of clustering models such as K-means clustering and hierarchical clustering. First, you'll dive into building a k-means clustering model in TensorFlow. Next, you'll discover autoencoders in detail, which are a type of artificial neural network used for unsupervised learning. Finally, you'll explore encodings or representation of data for dimensionality reduction of problems. By the end of this course, you'll have a better understanding of how you can work with unlabeled data using unsupervised learning techniques.

About the author
About the author

A problem solver at heart, Janani has a Masters degree from Stanford and worked for 7+ years at Google. She was one of the original engineers on Google Docs and holds 4 patents for its real-time collaborative editing framework.

More from the author
Scraping Your First Web Page with Python
Beginner
2h 39m
Nov 5, 2019
More courses by Janani Ravi
Section Introduction Transcripts
Section Introduction Transcripts

Course Overview
Hi, and welcome to this course on Building Unsupervised Learning Models with TensorFlow. I'll introduce myself first. My name is Janani Ravi, and I have a master's degree in electrical engineering from Stanford, and have worked at companies such as Microsoft, Google, and Flipkart. At Google, I was one of the first engineers working on real-time collaborative editing in Google Docs, and I hold four patents for its underlying technologies. I currently work on my own startup, Loonycorn, a studio for high quality video content. Unsupervised learning techniques are powerful but underutilized, and often not well understood. This course details clustering and autoencoding, two versatile, unsupervised learning techniques, and then implements them in TensorFlow. We'll focus on the various characteristics and features of clustering models and implement real examples in TensorFlow. We'll intuitively understand how the k-means clustering algorithm works, as well as hierarchical clustering. We'll then go on to implement a hands-on demo in Python using TensorFlow APIs of the k-means clustering algorithm. Autoencoders are a kind of artificial neural network used for unsupervised learning. It is used to learn encodings or representation of data for dimensionality reduction problems. Autoencoders can be used to implement principal component analysis, a popular mathematical technique for dimensionality reduction. This course will discuss the different kinds of autoencoders, such as a stacked autoencoder with dropout and a denoising autoencoder, and implement these in TensorFlow.