undefined | Better HN

0 pointsaiwabdn5y ago0 comments

Main reason for now is that the cosine similarity used as context function is not suitable for natural images like those in Imagenet. We are experimenting some extensions based on convolutions for such use cases.

0 comments

p1esk5y ago

What would you say is the best real world application for this class of networks?

aiwabdnOP5y ago

Possibly some scenarios in RL where online learning is involved

j / k navigate · click thread line to collapse

0 pointsaiwabdn5y ago0 comments

Main reason for now is that the cosine similarity used as context function is not suitable for natural images like those in Imagenet. We are experimenting some extensions based on convolutions for such use cases.

0 comments

p1esk5y ago

What would you say is the best real world application for this class of networks?

aiwabdnOP5y ago

Possibly some scenarios in RL where online learning is involved

j / k navigate · click thread line to collapse