👟 Hear the Yell
Brand new shoes, walking blues
Welcome to the one hundred and fifth issue of Monday Morning Data Science from the Fred Hutch Data Science Laboratory. We are excited to show you what we have been working on (Fresh from the Lab), plus links that we think you would be interested in (Our Weekly Bookmarks Bar). Part of the purpose of this newsletter is to start conversations, so if you have a question or there is something you would like to share with us please let us know by responding directly to this email.
Fresh from the Lab
[Blog Post: Notes on FastAPI, LiteStar and HTMX] Fred Hutch OCDO Software Engineer Scott Chamberlain reflects on the modern web application framework landscape, dives into LiteStar’s developer-friendly experience, and discusses how he is using these technologies in the workplace.
[Blog Post: Cancer AI Alliance Unveils First Collaborative AI Platform for Cancer Research] CAIA introduces their federated learning platform, which allows AI models to securely train on de-identified patient data within each cancer center’s own system, ensuring that no individual’s data ever leaves institutional firewalls while still contributing to collective learning.
Our Weekly Bookmarks Bar
[Article: How Does Gradient Descent Work?] We love this interactive explanation of gradient descent because it clearly shows how oscillations along sharp directions are automatically regulated, keeping the optimizer from diverging even when leaving the “stable region.” By introducing the central flow, a smooth, time-averaged trajectory that closely matches gradient descent, the authors make it easy to visualize and predict the long-term behavior of training and turning chaotic oscillations into an understandable and accurate model of optimization.
As always you can contact us by replying directly to this email, or if you work within the Fred Hutch/University of Washington/Seattle Children’s Cancer Consortium you are welcome to join us on the Fred Hutch Data Slack Workspace. For more information about the Fred Hutch Data Science Lab, visit our website: https://hutchdatascience.org/. See you in two weeks!
- The Fred Hutch Data Science Laboratory