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)
Both books can be read for free online.

The programming language used in this course will be Python. There are some adaptions of deep learning framework into R, but they are still very premature. Please find below some quick tutorials for Python.

Lecture Notes:
Lecture 1: Introduction to Deep Learning (link)
Lecture 2: Deep Forward Neural Networks (link)
Lecture 3: Computation for Neural Networks (link)
Lecture 4: Regularization for Neural Networks (link)
Lecture 5: Convoluted Neural Networks (link)
Lecture 6: Sequence Models (link)
Lecture 7: Applications to Genomics I (link)
Lecture 8: Generative Models I (Linear Factor Models) (link)
Lecture 9: Generative Models II (Autoencoders) (link)
Lecture 10: Generative Models III (DBM and GANs) (link)

Code Snippet:
1. a first example of a neural network using keras (link)
2. cat vs. dog (link)
3. Toy example of AlexNet using Google colab (link)
4. Use LSTM to generate text (link)

Python Tutorials using Jupyter Notebook.
1. Quick Introduction to string, array, list and dictionary (link)
2. Numpy intro (link)
3. Matplotlib (link)