What does a Foundational Model of Earth look like? Clay Foundation: Bruno Sanchez-Andrade Nuño - MBM#67
Minds Behind Maps
Foundational Models and their Versatility
This chapter explores the concept of foundational models and their flexibility compared to task-specific models like image segmentation. It delves into pre-training models on large datasets and fine-tuning for specific tasks, showcasing how foundational models enable options like freezing layers and creating embeddings. The discussion also highlights the application of transformers in creating a universal learner for Earth observation at scale through mechanisms like masked auto encoders.
00:00
Transcript
Play full episode
Remember Everything You Learn from Podcasts
Save insights instantly, chat with episodes, and build lasting knowledge - all powered by AI.
