Knowledge Sharing Session #7: AI for Agriculture

Welcome to the 7th iteration of our Knowledge Sharing Sessions! This week, we're very excited to introduce Nikos Mylonas and Borja Espejo-Garcia from Eden Library who will speak on AI for Agriculture and the role of Eden Library!

Description: In recent years, automatic pest control has emerged as a promising alternative for reducing the amount of pesticide applied to the field. The use of artificial intelligence through the implementation of deep learning has been one of the engines to boost this progress. However, these techniques usually need very large datasets coping with real-world conditions, which are scarce in the agricultural domain. To address the lack of such datasets, transfer learning techniques can be used. These techniques refer to exploiting what has been learned from one problem into another different problem. The application of agricultural knowledge extracted by pre-trained deep learning architectures for improving the performance of other systems is still open for research and discussion. Our previous results show some promising insights about how relevant it will be to make use of both agricultural datasets and agricultural pre-trained networks for deploying applications that can really cope with the complexity of real-world conditions. In this context, Eden Library aims to close the gap between data availability and novel farming practices, by introducing a database of agriculture images focusing on different crops, enemies and applications. A collection of big amounts of data in one place, can boost vision-based applications and allow users accessing high-quality data for AI tasks.