Deep learning is called the “new electricity” for modern science and technology. Getting a good understanding of 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 deep neural networks, convoluted neural networks, sequence models, generative adversarial networks, etc.
We will not follow any textbooks, 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 still stick with Python for most of the illustrations.
This is the 3rd time we are teaching this course. Yet, the course material is still very much under development, so you should anticipate major changes in the course material from previous years.
- Boosting (Notes 01/10 )
- Unsupervised learning (Notes 01/12-02/02)
- Neural networks and projection pursuit (Notes: 02/02 )
- Deep feedforward network (Notes: 02/07 02/09+02/16 )
- Computation (Notes: 02/21 02/23)
- Regularization (Notes: 02/23)
- CNN (Notes: 03/16)
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)