Experiments/AI

• A paper that uses OFF to predict the #ecoscore from the product name: https://openreview.net/pdf?id=EET32LtDv8
• Today the Guardian reports on how Unit PhD student Yuru Huang and colleagues have used artificial intelligence to predict the healthiness of cafe, takeaway and restaurant menus at outlets across Britain. This information was then used to map which of UK local authorities have the most and least healthy food environments. https://www.mrc-epid.cam.ac.uk/blog/2024/03/08/ai-predicts-healthiness-food-menus/
• https://blog.google/around-the-globe/google-europe/united-kingdom/whats-cooking-how-hellmanns-is-using-google-cloud-ai-to-turn-leftovers-into-meals/
• https://techcrunch.com/2024/03/13/amazon-now-lets-sellers-create-listings-through-a-url-by-using-ai/
• An interesting usecase for Open Products Facts: digitizing bookshelves without even moving the books: https://x.com/simonw/status/1760384912446955962?s=31
• Could it be useful on taxonomies to propagate properties, or do some other things ? https://goo.gle/3w8ogZC
• Giulia Menichetti - Happy to share our paper “Machine learning prediction of the degree of food processing” with this lovely community https://www.nature.com/articles/s41467-023-37457-1
• https://x.com/nutrifyfoodapp/status/1785857854282547655 - FoodVision AI is capable of identifying many common foods

• Segmentation: Vince I had to use https://huggingface.co/briaai/RMBG-1.4 in another context, and I was quite impressed with the results. It works quite well on our own use-case too. Here are a few examples:
•