On 10^th January 2025, the Harmony Question Matching Challenge ended, and after having evaluated 276 submissions from 26 participants, the results are now in. 🥳

Congratulations to the competition's winners:

1. First place: José Inés Martínez Berard (@oreug) with MAE=20.348, who won a £500 Amazon voucher 🏅
2. Second place: Rafi Ahmed Riyaz Ahmed Patel (@rafa) with MAE=20.544, who won a £250 Amazon voucher 🥈

The Harmony team will now work with the winners to explore the integration of their solutions into the Harmony tool, which aims to help researchers make better use of existing data by harmonising questionnaire items and measures across different studies using natural language processing.

Harmony is a collaboration between researchers at Ulster University, University College London, the Universidade Federal de Santa Maria and Fast Data Science. The Harmony project has been funded by Wellcome as part of the Wellcome Data Prize in Mental Health and by the Economic and Social Research Council (ESRC).

If you found this challenge interesting, check out the Harmony Questionnaire Parsing Challenge (a token classification competition), which is open until 28th March.

Following in-person finals held at University College London and Harvard University this weekend, ClimateHack.AI 2023–24 has just finished, and the winners can be announced! 🥳

On behalf of ClimateHack.AI, I would like to massively congratulate (i) Areel, Carter and Trevor from the University of Waterloo (Canada); (ii) Andrew, Grace, Tim and Val from the University of California, Berkeley (United States); and (iii) Tom and Michael from the University of Bristol (United Kingdom). 🏆

Today, we are proud to be launching ClimateHack.AI 2023-24: an international grand challenge with a £20k prize pool bringing together students at 18 universities across the UK, the US and Canada to help tackle climate change with AI. 🌍

Students will be competing to develop state-of-the-art machine learning methods for more accurately forecasting near-term site-level solar photovoltaic power generation using 600 gigabytes of satellite imagery, weather forecasts and air quality forecasts.

The competition has been organised in collaboration with Open Climate Fix, a non-profit lab focused on rapidly cutting greenhouse gas emissions, and is supported this year by Newcross Healthcare, University College London, PGIM Real Estate via their RealAssetX innovation lab, and Climate X.

At DOXA AI, our ultimate mission is to foster an international machine learning community best placed to tackle some of humanity's most pressing challenges, such as climate change. We passionately believe in the transformative power of AI to build a better world, and we hope you will join us on that journey.

Stay tuned for more! 🚀