ML+X Forum: Unsupervised Learning Applications

Join the ML Community on Tuesday, Nov. 1st, 12-1pm, to learn how unsupervised learning methods can help researchers understand molecular networks and predict disease phenotypes. These two talks will highlight graph representation learning methods, variational autoencoders, and several approaches to validating unsupervised learning results — which is never an easy task without ground-truth labels! 

1. Comparison of deep and shallow graph representation learning algorithms for detecting modules in molecular networks — Zhiwei Song
2. JAMIE: Joint variational autoencoders for multi-modal imputation and embedding — Noah Cohen
   

RSVP for the post-event social: Want to discuss ML projects and connect with the presenters following this event? Come to the ML Community's monthly social — ML+Coffee. Learn more and register.

Join the ML Community google group: The ML Community has a google group it uses to send reminders about its upcoming events. If you aren't already a member of the google group, you can use this link to join. Note that you have to be signed into a google account to join the group. If you have any trouble joining, please email faciltator@datascience.wisc.edu.

Apply to present your ML application at the ML+X forum: If you are working on an ML application (e.g., regression, classification, clustering, NLP, reinforcement learning, etc.), and are interested in sharing your project with others this fall, please fill out this google form indicating which date(s) work for your schedule.