Diversity and International Fellowships for Deep Learning Part 2

Applications are now open for Deep Learning Part 2, to be offered at the University of San Francisco Data Institute on Monday evenings, Feb 27-April 10. The course will cover integrating multiple cutting-edge deep learning techniques, as well as combining classic machine learning techniques with deep learning.

In part 1, we worked hard to curate a diverse group of participants, because we’d observed that artificial intelligence is missing out because of its lack of diversity. A study of 366 companies found that ethnically diverse companies are 35% more likely to perform well financially, and teams with more women perform better on collective intelligence tests. Scientific papers written by diverse teams receive more citations and have higher impact factors.

Everyone benefited from having a class full of curious coders from a variety of backgrounds. We had a number of students interested in using deep learning for social good, including Sara Hooker, founder and executive director of Delta Analytics, which partners non-profits with data scientists. She is now working on a project to use audio data streamed from recycled cell phones in endangered forests to track harmful human activity. Another student was a former Literature PhD student interested in analyzing gender and language in Github commits. Several students connected over their shared interest in Alzheimer’s research. International fellow Samar Haider is a researcher applying natural language processing to his native language of Urdu, one of the 70 different spoken languages in Pakistan, many of which have not been well-studied and are in need of the additional resources deep learning can provide. Another international fellow said he never expected to be using so many command line tools (we provide scripts and guidance to walk you through the setup) and he ended up creating an Amazon Machine Image which saved memory to share with the rest of the class.

One of the ways we achieved this great outcome was by, together with USF Data Institute, sponsoring diversity fellowships and international fellowships. It was such a success that we’ve decided to do it again.

I am saddened and angered that President Trump is banning immigrants from certain countries from entering the US, even when they have visas and green cards. The deep learning community is suffering from its lack of diversity already, and we are trying to fight that. We can’t change government policy at fast.ai, but we can do our little bit: we will again offer free remote international fellowships for those selected outside San Francisco to attend classes virtually, have access to all the same online resources, and be a part of our community. People of all religions and from all countries, including Iran, Iraq, Libya, Somalia, Syria, Sudan, and Yemen, are welcome and encouraged to apply.

Diversity fellowship are full or partial tuition waivers to attend the in-person course in San Francisco for women, people of Color, LGBTQ people, or veterans. We are looking for applicants who have shown the ability to follow through on projects and a significant level of intellectual curiosity.

International fellowships allow those who can not get to San Francisco to attend virtual classes for free during the same time period as the in-person class and provides access to all the same online resources. (Note that international fellowships do not provide an official completion certificate through USF). Our international fellows from part 1 contributed greatly to the community.

Both fellowships require completion of part 1. When applying, please let us know about any way that you have contributed to the student community (such as forum posts, pull requests, or open source projects). To apply, email your resume to rachel@fast.ai and datainstitute@usfca.edu, along with a note of whether you are interested in the diversity or international fellowships and a brief paragraph on how you want to use deep learning. Note that to be eligible, you must have completed Deep Learning Part 1, either in person, or through our MOOC. Deep Learning Part 1 involves approximately 70 hours of work, so if you haven’t finished yet, you should get studying. The deadline to apply is 2/13.