Functional Map of the World - [ML Challenge]

---

IARPA, The Intelligence Advanced Research Project Activity, has created a machine learning challenge and posted it on iarpa.gov. It's about creating algorithms to classify building and land use.

In their words:

"The Functional Map of the World (fMoW) Challenge seeks to foster breakthroughs in the automated analysis of overhead imagery by harnessing the collective power of the global data science and machine learning communities.

The challenge will publish one of the largest publicly available satellite-image datasets to date, with more than one million points of interest from around the world. The dataset contains satellite-specific metadata that researchers can exploit to build a competitive algorithm that classifies facility, building, and land use." [source]

So, this is a call for all coders with the required skill set. The challenge was opened in September 2017 and the final submissions are in December 2017. Prizes will be awarded in February 2018.

First prize gets $25,000, second gets $16,000. Third, fourth and fifth get $12,000, $8,000 and $5,000. Additionally, there are a few more prizes.

They not only provided all the resources necessary to be able to do the challenge, but they also link a few tutorials that are very helpful for machine learning and deep learning. So, they kindof put a lot of stuff on the plate so that the competitors would !only have to put in the work.

While this may not be as rewarding as some Kaggle competitions, I guess the first three prizes are big enough to incentivize a small team of 2 or 3 individuals. For the full details and for registrations, please visit their official page:

Functional Map of the World - [ML Challenge]

---

To stay in touch with me, follow @cristi

---

Cristi Vlad Self-Experimenter and Author