4.67 out of 5
4.67
1538 reviews on Udemy

Unsupervised Deep Learning in Python

Theano / Tensorflow: Autoencoders, Restricted Boltzmann Machines, Deep Neural Networks, t-SNE and PCA
Instructor:
Lazy Programmer Inc.
16,616 students enrolled
English [Auto]
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 and Tensorflow
Understand how stacked autoencoders are used in deep learning
Write a stacked denoising autoencoder in Theano and Tensorflow
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 and Tensorflow
Visualize and interpret the features learned by autoencoders and RBMs

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, Theano, and Tensorflow 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.

Suggested Prerequisites:

  • calculus

  • linear algebra

  • probability

  • Python coding: if/else, loops, lists, dicts, sets

  • Numpy coding: matrix and vector operations, loading a CSV file

  • can write a feedforward neural network in Theano or Tensorflow

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.

  • Write code yourself, don’t just sit there and look at my code.

WHAT ORDER SHOULD I TAKE YOUR COURSES IN?:

  • Check out the lecture “What order should I take your courses in?” (available in the Appendix of any of my courses, including the free Numpy course)

Introduction and Outline

1
Introduction and Outline
2
Where does this course fit into your deep learning studies?
3
How to Succeed in this Course
4
Where to get the code and data
5
Tensorflow or Theano - Your Choice!
6
What are the practical applications of unsupervised deep learning?

Principal Components Analysis

1
What does PCA do?
2
How does PCA work?
3
Why does PCA work? (PCA derivation)
4
PCA only rotates
5
MNIST visualization, finding the optimal number of principal components
6
PCA implementation
7
PCA for NLP
8
PCA objective function
9
PCA Application: Naive Bayes
10
SVD (Singular Value Decomposition)
11
Suggestion Box

t-SNE (t-distributed Stochastic Neighbor Embedding)

1
t-SNE Theory
2
t-SNE Visualization
3
t-SNE on the Donut
4
t-SNE on XOR
5
t-SNE on MNIST

Autoencoders

1
Autoencoders
2
Denoising Autoencoders
3
Stacked Autoencoders
4
Writing the autoencoder class in code (Theano)
5
Testing our Autoencoder (Theano)
6
Writing the deep neural network class in code (Theano)
7
Autoencoder in Code (Tensorflow)
8
Testing greedy layer-wise autoencoder training vs. pure backpropagation
9
Cross Entropy vs. KL Divergence
10
Deep Autoencoder Visualization Description
11
Deep Autoencoder Visualization in Code
12
An Autoencoder in 1 Line of Code

Restricted Boltzmann Machines

1
Basic Outline for RBMs
2
Introduction to RBMs
3
Motivation Behind RBMs
4
Intractability
5
Neural Network Equations
6
Training an RBM (part 1)
7
Training an RBM (part 2)
8
Training an RBM (part 3) - Free Energy
9
RBM Greedy Layer-Wise Pretraining
10
RBM in Code (Theano) with Greedy Layer-Wise Training on MNIST
11
RBM in Code (Tensorflow)

The Vanishing Gradient Problem

1
The Vanishing Gradient Problem Description
2
The Vanishing Gradient Problem Demo in Code

Extras + Visualizing what features a neural network has learned

1
Exercises on feature visualization and interpretation

Applications to NLP (Natural Language Processing)

1
Application of PCA and SVD to NLP (Natural Language Processing)

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.

2
Latent Semantic Analysis in Code
3
Application of t-SNE + K-Means: Finding Clusters of Related Words

Applications to Recommender Systems

1
Recommender Systems Section Introduction
2
Why Autoencoders and RBMs work
3
Data Preparation and Logistics
4
Data Preprocessing Code
5
AutoRec
6
AutoRec in Code
7
Categorical RBM for Recommender System Ratings
8
Recommender RBM Code pt 1
9
Recommender RBM Code pt 2
10
Recommender RBM Code pt 3
11
Recommender RBM Code Speedup

Theano and Tensorflow Basics Review

1
(Review) Theano Basics
2
(Review) Theano Neural Network in Code
3
(Review) Tensorflow Basics
4
(Review) Tensorflow Neural Network in Code
5
(Review) Keras Basics
6
(Review) Keras in Code pt 1
7
(Review) Keras in Code pt 2

Setting Up Your Environment

1
Windows-Focused Environment Setup 2018
2
How to install Numpy, Scipy, Matplotlib, Pandas, IPython, Theano, and TensorFlow

Extra Help With Python Coding for Beginners

1
How to Code by Yourself (part 1)
2
How to Code by Yourself (part 2)
3
Proof that using Jupyter Notebook is the same as not using it
4
Python 2 vs Python 3
5
Is Theano Dead?

Effective Learning Strategies for Machine Learning

1
How to Succeed in this Course (Long Version)
2
Is this for Beginners or Experts? Academic or Practical? Fast or slow-paced?
3
What order should I take your courses in? (part 1)
4
What order should I take your courses in? (part 2)

Appendix / FAQ

1
What is the Appendix?
2
BONUS: Where to get Udemy coupons and FREE deep learning material
You can view and review the lecture materials indefinitely, like an on-demand channel.
Definitely! If you have an internet connection, courses on Udemy are available on any device at any time. If you don't have an internet connection, some instructors also let their students download course lectures. That's up to the instructor though, so make sure you get on their good side!
4.7
4.7 out of 5
1538 Ratings

Detailed Rating

Stars 5
994
Stars 4
422
Stars 3
74
Stars 2
26
Stars 1
23
30-Day Money-Back Guarantee

Includes

10 hours on-demand video
Full lifetime access
Access on mobile and TV
Certificate of Completion

Custom Sidebar

This theme offers completely unlimited custom sidebars down to the individual post and page level. For this specific sidebar:

  1. Go into Theme Options >> Custom Sidebars and create a new sidebar
  2. Go into Appearance >> Widgets and find the new sidebar you created and add widgets (for instance this is a standard text widget)
  3. Go to any page or post and choose the custom sidebar in the layout options
Latest Reviews
Try a different filter
Top Ten This Week
1
[Udemy] The Complete Angular 9+ Course for Beginners (Step by Step)
2
[Udemy] Full Stack Web Developer with AI & ML Integration|Hindi|Urdu
3
[Udemy] Unity Game Development: Create A 3D Beat Em Up Game
4
[Udemy] CCA Hadoop & Spark Developer Practice Test (CCA175)-2019
5
[Udemy] Learn Python Programming for Absolute Beginners

6
[Udemy] Create a web application with python + Django + PostgreSQL
7
[Udemy] Create Multi Level Marketing Website – MLM with WordPress
8
[Udemy] Unity game development, make games in just 4 hours
9
[Udemy] ArchiMate 3.0 Crash Course
10
[Udemy]REST WCF Service in ASP.NET

WP Twitter Auto Publish Powered By : XYZScripts.com
Skip to toolbar