UW-Madison Research Bazaar 2020

Geospatial data users exist in every discipline, and training to support the work is currently met by various courses, workshops, and online resources. Yet, many users cannot access this material, or desire further support for their geospatial projects. To meet the needs of students and researchers across campus, there is interest in developing new geospatial opportunities for the UW-Madison community. The proposed concurrent session is a platform to hear from the community about improving geospatial training and consultation on campus. Through facilitated small and large group conversations, this session will identify campus needs and make connections with individuals in the community who wish to actively support this endeavor. The intended audience is campus geospatial data users, educators, and explorers.
RSVP: https://www.sco.wisc.edu/uw-geo/research-bazaar-rsvp/

Despite its popularity among computational researchers, machine learning remains elusive to experimental biologists. Most machine learning courses and tutorials require substantial background knowledge in coding and mathematics, which many biologists may lack. Bioinformatics workshops for biologists assume less coding experience, but participants are often taught to mechanically run through a software pipeline for certain tasks without learning the best practices in various stages of the workflow. Instead, our educational objective is to equip biologists with the proper mindset when engaging with machine learning in their research and the ability to critically analyze machine learning applications in their domain. Our ml4bio workshop teaches machine learning literacy, that is, how to set up learning problems, reason about learning algorithms, assess trained models, and communicate with machine learning experts. We developed interactive software with a graphical interface and hands-on activities that explain some of the most frequently used classification algorithms in biological research. The software and interactive exercises guide participants through a full cycle of the machine learning workflow while doing proper model training, validation, selection, and testing. 

All participants should bring a laptop and install the software before coming to the workshop. No prior machine learning or coding experience is necessary. This workshop is intended for beginners in the machine learning field. The work-in-progress workshop materials and timetable can be found at https://gitter-lab.github.io/ml-bio-workshop/index.html The workshop follows The Carpentries Code of Conduct. The instructors have taught three pilot versions of the workshop, and one is a UW-Madison assistant professor.