Deep learning is marveled as the “new electricity” for modern science and technology. Getting a good understanding on modern deep learning methods would be critical for statisticians who are interested in “big data” research.
This course covers basic theory and applications for modern deep learning methods in genomics and health informatics. We will survey basic theory for neural networks, convoluted neural networks, sequence models, generative adversarial networks etc.
We will not follow any text books, but a majority of the fundamental deep learning stuff will be taken from the following sources:
1. Deep Learning book by Ian Goodfellow and Yoshua Bengio and Aaron Courville (link)
2. Deep Learning with Python book by Francois Chollet (link)
3. Deep Learning with R book also by Francois Chollet (link)
Both books can be read for free online. In the meantime, many new topics will be drawn directly from research papers.
The programming language used in this course will be Python or R. I am more experienced with deep learning modeling in Python. Yet, more recently, much progress has been made adapting Torch or TensorFlow to R. In this semester, we will explore the usage of both python and R for deep learning models.
This is the 2nd time we are teaching this course. The course material is still very much under development, so you should anticipate major changes in the course material from previous years.
Lecture 1: Introduction to Deep Learning (ppt) (notes 01/25)
Lecture 2: Project Pursuit and Neural Network (ppt) (notes: 01/25 01/27 02/01)
Lecture 3: Deep Feedforward Networks (ppt) (notes: 02/01 02/03 02/08 02/10)
Lecture 4: Computation for Neural Networks (ppt) (notes: 02/22 02/24 03/01)
Lecture 5: Regularization for Neural Networks (ppt) (notes: 03/03 03/08)
Lecture 6: Convoluted Neural Networks (ppt) (notes: 03/15 03/22 03/24 03/31 04/05 04/12)
Lecture 7: Recurrent Neural Networks (ppt) (notes: 04/12 04/14 04/19)
Lecture 8: Generative Models (ppt) (notes: 04/21 04/26 04/28)
Python: all Python script will be written in google colab.
1. Keras helloword using MINST dataset (code)
2. cat vs dog (code)
3. LSTM for generating text (code)
R: all R code is on GitHub
1. Keras helloworld R version (code)
2. Keras implementation of AlexNet (code)
3. Analysis of histology images using AlexNet and data generators (code)
4. Toy implementation of residual networks by defining customized model (code)
Online Learning Materials:
Our course is pretty much self-contained. Compared to many other courses, our course has a stronger emphasis on math foundations of deep learning, and more focus on genomics and health informatics. With that said, you are also encouraged to explore some online resources of deep learning.
1. Andrew Ng’s deep learning course on Coursera (link)
2. Deep Learning in Computer Vision Class from Stanford (link)
3. Deep learning in natural language processing from Stanford (link)
4. Deep learning in genomics by Manolis Kellis (link)