User Tools

Site Tools


private:unsupervised

Differences

This shows you the differences between two versions of the page.

Link to this comparison view

Both sides previous revision Previous revision
private:unsupervised [2020/03/05 08:30]
admin [Why is dot product so dominant?]
private:unsupervised [2020/03/05 09:50] (current)
admin [Orthonormal weights]
Line 72: Line 72:
   * exact methods - decompose a (n,n) matrix into (n-1, n-1) and ensure each step maintains orthonormal - has to be n steps to backprop through which can't be good.   * exact methods - decompose a (n,n) matrix into (n-1, n-1) and ensure each step maintains orthonormal - has to be n steps to backprop through which can't be good.
   * approximate methods - enforce rows or columns to be unit vector and then minimise Tr(W W^T - I) using (say) LMS   * approximate methods - enforce rows or columns to be unit vector and then minimise Tr(W W^T - I) using (say) LMS
 +  * near exact - use exp(W) and approximate the exp - http://​proceedings.mlr.press/​v97/​lezcano-casado19a/​lezcano-casado19a.pdf
  
 ==== Embedding daat onto unit sphere === ==== Embedding daat onto unit sphere ===
private/unsupervised.txt ยท Last modified: 2020/03/05 09:50 by admin