You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
{{ message }}
This repository has been archived by the owner on Nov 29, 2023. It is now read-only.
Paper is mostly about language models, but has an interesting idea for searching for similar text to help the model learn, and seems to work well. I believe we talked about that at some point, using similarity search, for satellite predictions, and this seems to say it works for nlp at least.
Possible Implementation
Have a database of similar historical PV data to search from, or satellite images, and use something like faiss for fast search. Then would be able to include historical past and future gsp data as well for those days to help with predictions
The text was updated successfully, but these errors were encountered:
Detailed Description
https://medium.com/syncedreview/deepminds-retro-retrieval-enhanced-transformer-retrieves-from-trillions-of-tokens-achieving-c54313fec51d
Context
Paper is mostly about language models, but has an interesting idea for searching for similar text to help the model learn, and seems to work well. I believe we talked about that at some point, using similarity search, for satellite predictions, and this seems to say it works for nlp at least.
Possible Implementation
Have a database of similar historical PV data to search from, or satellite images, and use something like faiss for fast search. Then would be able to include historical past and future gsp data as well for those days to help with predictions
The text was updated successfully, but these errors were encountered: