Theano / Tensorflow: Autoencoders, Restricted Boltzmann Machines, Deep Neural Networks, t-SNE and PCA
- 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
- Knowledge of calculus and linear algebra
- Python coding skills
- Some experience with Numpy, Theano, and Tensorflow
- 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 or Tensorflow
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.
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:
- linear algebra
- 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.
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
- Artificial Intelligence: Reinforcement Learning in Python
- Natural Language Processing with Deep Learning in Python
- 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