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
Tensorflow has a cool embedding visualizer here and I think some of their features are really cool and should be added to atlas.
For example, when you click on some datapoint X, Tensorflow's visualizer shows you which points are closest to datapoint X in the original space. This helps you to understand how the dimensionality reduction technique preserves and distorts distances.
I think this would be a great feature to add to atlas. Cheers!
The text was updated successfully, but these errors were encountered:
Thanks for the suggestion. Displaying the k-nearest neighbors is prototyped and high on our feature list. if you're interested in helping beta test it when it's ready for public consumption, let me know and we can put you on the list.
I would love to help Beta test this feature and I'd love to be put on the list. And if you ever open source your algorithm, I'd be more than happy to help contribute this feature to Atlas. Cheers!
Tensorflow has a cool embedding visualizer here and I think some of their features are really cool and should be added to atlas.
For example, when you click on some datapoint X, Tensorflow's visualizer shows you which points are closest to datapoint X in the original space. This helps you to understand how the dimensionality reduction technique preserves and distorts distances.
I think this would be a great feature to add to atlas. Cheers!
The text was updated successfully, but these errors were encountered: