Deep Learning Architectures

CSI 5180 - Machine Learning for Bioinformatics

Important

Assignment 2 is due on March 26, 2025.

Prepare

Watch these videos:

• What are Convolutional Neural Networks (CNNs)?
  • IBM Technology (6m 20s)
• Image Classification with Convolutional Neural Networks (CNNs)
  • StatQuest (15m 23s)
• Deep Learning at Base-Resolution Reveals Motif Syntax
  • Keynote lecture by Anshul Kundaje at RECOMB/RSG 2019 (46m 52s)

If you have not yet explored it, you might want to review the work by Zou et al. (2019) and its accompanying Google Colab Tutorial, which provides practical insights into the application of convolutional neural networks.

Participate

• slides (PDF)

Practice

I recently read the following publication for one my research projects.

• Kong, Y. & Yu, T. (2018). A graph-embedded deep feedforward network for disease outcome classification and feature selection using gene expression data. Bioinformatics (Oxford, England), 34(21), 3727–3737.

In the process, I created a Jupyter Notebook partially replicating the work: kong_and_yu-2018.

Further Information

• Convolutions in Image Processing
  • Grant Sanderson (3Blue1Brown) (36m 9s)
• But what is a convolution?
  • 3Blue1Brown (23m)

References

Zou, James, Mikael Huss, Abubakar Abid, Pejman Mohammadi, Ali Torkamani, and Amalio Telenti. 2019. “A Primer on Deep Learning in Genomics.” Nature Genetics 51 (1): 12–18. https://doi.org/10.1038/s41588-018-0295-5.