Unsupervised Deep Learning in Python

Autoencoders + Restricted Boltzmann Machines for Deep Neural Networks in Theano, + t-SNE and PCA
4.6 (92 ratings)
Instead of using a simple lifetime average, Udemy calculates a
course's star rating by considering a number of different factors
such as the number of ratings, the age of ratings, and the
likelihood of fraudulent ratings.
2,699 students enrolled
$120
Take This Course
  • Lectures 31
  • Length 3 hours
  • Skill Level Intermediate Level
  • Languages English
  • Includes Lifetime access
    30 day money back guarantee!
    Available on iOS and Android
    Certificate of Completion
Wishlisted Wishlist

How taking a course works

Discover

Find online courses made by experts from around the world.

Learn

Take your courses with you and learn anywhere, anytime.

Master

Learn and practice real-world skills and achieve your goals.

About This Course

Published 5/2016 English

Course Description

This course is the next logical step in my deep learning, data science, and machine learning series. I’ve done a lot of courses about deep learning, and I just released a course about unsupervised learning, where I talked about clustering and density estimation. So what do you get when you put these 2 together? Unsupervised deep learning!

In these course we’ll start with some very basic stuff - principal components analysis (PCA), and a popular nonlinear dimensionality reduction technique known as t-SNE (t-distributed stochastic neighbor embedding).

Next, we’ll look at a special type of unsupervised neural network called the autoencoder. After describing how an autoencoder works, I’ll show you how you can link a bunch of them together to form a deep stack of autoencoders, that leads to better performance of a supervised deep neural network. Autoencoders are like a non-linear form of PCA.

Last, we’ll look at restricted Boltzmann machines (RBMs). These are yet another popular unsupervised neural network, that you can use in the same way as autoencoders to pretrain your supervised deep neural network. I’ll show you an interesting way of training restricted Boltzmann machines, known as Gibbs sampling, a special case of Markov Chain Monte Carlo, and I’ll demonstrate how even though this method is only a rough approximation, it still ends up reducing other cost functions, such as the one used for autoencoders. This method is also known as Contrastive Divergence or CD-k. As in physical systems, we define a concept called free energy and attempt to minimize this quantity.

Finally, we’ll bring all these concepts together and I’ll show you visually what happens when you use PCA and t-SNE on the features that the autoencoders and RBMs have learned, and we’ll see that even without labels the results suggest that a pattern has been found.

All the materials used in this course are FREE. Since this course is the 4th in the deep learning series, I will assume you already know calculus, linear algebra, and Python coding. You'll want to install Numpy and Theano for this course. These are essential items in your data analytics toolbox.

If you are interested in deep learning and you want to learn about modern deep learning developments beyond just plain backpropagation, including using unsupervised neural networks to interpret what features can be automatically and hierarchically learned in a deep learning system, this course is for you.

This course focuses on "how to build and understand", not just "how to use". Anyone can learn to use an API in 15 minutes after reading some documentation. It's not about "remembering facts", it's about "seeing for yourself" via experimentation. It will teach you how to visualize what's happening in the model internally. If you want more than just a superficial look at machine learning models, this course is for you.


NOTES:

All the code for this course can be downloaded from my github: /lazyprogrammer/machine_learning_examples

In the directory: unsupervised_class2

Make sure you always "git pull" so you have the latest version!

HARD PREREQUISITES / KNOWLEDGE YOU ARE ASSUMED TO HAVE:

  • calculus
  • linear algebra
  • probability
  • Python coding: if/else, loops, lists, dicts, sets
  • Numpy coding: matrix and vector operations, loading a CSV file


TIPS (for getting through the course):

  • Watch it at 2x.
  • Take handwritten notes. This will drastically increase your ability to retain the information.
    • Write down the equations. If you don't, I guarantee it will just look like gibberish.
  • Ask lots of questions on the discussion board. The more the better!
  • Realize that most exercises will take you days or weeks to complete.


USEFUL COURSE ORDERING:

  • (The Numpy Stack in Python)
  • Linear Regression in Python
  • Logistic Regression in Python
  • (Supervised Machine Learning in Python)
  • (Bayesian Machine Learning in Python: A/B Testing)
  • Deep Learning in Python
  • Practical Deep Learning in Theano and TensorFlow
  • (Supervised Machine Learning in Python 2: Ensemble Methods)
  • Convolutional Neural Networks in Python
  • (Easy NLP)
  • (Cluster Analysis and Unsupervised Machine Learning)
  • Unsupervised Deep Learning
  • (Hidden Markov Models)
  • Recurrent Neural Networks in Python
  • Natural Language Processing with Deep Learning in Python


What are the requirements?

  • Knowledge of calculus and linear algebra
  • Python coding skills
  • Some experience with Numpy and Theano
  • Know how gradient descent is used to train machine learning models
  • Install Python, Numpy, and Theano
  • Some probability and statistics knowledge
  • Code a feedforward neural network in Theano

What am I going to get from this course?

  • Understand the theory behind principal components analysis (PCA)
  • Know why PCA is useful for dimensionality reduction, visualization, de-correlation, and denoising
  • Derive the PCA algorithm by hand
  • Write the code for PCA
  • Understand the theory behind t-SNE
  • Use t-SNE in code
  • Understand the limitations of PCA and t-SNE
  • Understand the theory behind autoencoders
  • Write an autoencoder in Theano
  • Understand how stacked autoencoders are used in deep learning
  • Write a stacked denoising autoencoder in Theano
  • Understand the theory behind restricted Boltzmann machines (RBMs)
  • Understand why RBMs are hard to train
  • Understand the contrastive divergence algorithm to train RBMs
  • Write your own RBM and deep belief network (DBN) in Theano
  • Visualize and interpret the features learned by autoencoders and RBMs

Who is the target audience?

  • Students and professionals looking to enhance their deep learning repertoire
  • Students and professionals who want to improve the training capabilities of deep neural networks
  • Students and professionals who want to learn about the more modern developments in deep learning

What you get with this course?

Not for you? No problem.
30 day money back guarantee.

Forever yours.
Lifetime access.

Learn on the go.
Desktop, iOS and Android.

Get rewarded.
Certificate of completion.

Curriculum

Section 1: Introduction and Outline
Introduction and Outline
Preview
01:55
Where does this course fit into your deep learning studies?
Preview
02:57
Section 2: Principal Components Analysis
What does PCA do?
Preview
06:14
PCA derivation
04:22
MNIST visualization, finding the optimal number of principal components
03:39
PCA objective function
02:05
Section 3: t-SNE (t-distributed Stochastic Neighbor Embedding)
t-SNE Theory
04:28
t-SNE on the Donut
05:51
t-SNE on XOR
04:36
t-SNE on MNIST
02:12
Section 4: Autoencoders
Autoencoders
03:20
Denoising Autoencoders
01:55
Stacked Autoencoders
03:32
Writing the autoencoder class in code
11:55
Writing the deep neural network class in code
12:42
Testing greedy layer-wise autoencoder training vs. pure backpropagation
03:33
Cross Entropy vs. KL Divergence
04:39
Deep Autoencoder Visualization Description
01:32
Deep Autoencoder Visualization in Code
11:14
Section 5: Restricted Boltzmann Machines
09:31

What is a restricted Boltzmann machine? How is it related to neural networks? Why is it difficult to train a RBM?

Deriving Conditional Probabilities from Joint Probability
06:18
02:45

Learn how to train an RBM using contrastive divergence / Gibbs sampling

RBM in Code + Testing a greedily pre-trained deep belief network on MNIST
14:24
Section 6: The Vanishing Gradient Problem
The Vanishing Gradient Problem Description
03:07
The Vanishing Gradient Problem Demo in Code
12:17
Section 7: Extras + Visualizing what features a neural network has learned
Exercises on feature visualization and interpretation
02:07
BONUS: Where to get Udemy coupons and FREE deep learning material
Preview
01:24
BONUS: How to derive the free energy formula
06:32
Section 8: BONUS: Application of PCA / SVD to NLP (Natural Language Processing)
02:30

We use SVD to visualize the words in book titles. You'll see how related words can be made to appear close together in 2 dimensions using the SVD transformation.

BONUS: Latent Semantic Analysis in Code
10:08
Section 9: Appendix
How to install Numpy, Scipy, Matplotlib, Pandas, IPython, Theano, and TensorFlow
17:22

Students Who Viewed This Course Also Viewed

  • Loading
  • Loading
  • Loading

Instructor Biography

Lazy Programmer Inc., Data scientist and big data engineer

I am a data scientist, big data engineer, and full stack software engineer.

For my masters thesis I worked on brain-computer interfaces using machine learning. These assist non-verbal and non-mobile persons communicate with their family and caregivers.

I have worked in online advertising and digital media as both a data scientist and big data engineer, and built various high-throughput web services around said data. I've created new big data pipelines using Hadoop/Pig/MapReduce. I've created machine learning models to predict click-through rate, news feed recommender systems using linear regression, Bayesian Bandits, and collaborative filtering and validated the results using A/B testing.

I have taught undergraduate and graduate students in data science, statistics, machine learning, algorithms, calculus, computer graphics, and physics for students attending universities such as Columbia University, NYU, Humber College, and The New School. 

Multiple businesses have benefitted from my web programming expertise. I do all the backend (server), frontend (HTML/JS/CSS), and operations/deployment work. Some of the technologies I've used are: Python, Ruby/Rails, PHP, Bootstrap, jQuery (Javascript), Backbone, and Angular. For storage/databases I've used MySQL, Postgres, Redis, MongoDB, and more.

Ready to start learning?
Take This Course