krzysztof/landing_page
1
0
Fork 0
mirror of https://github.com/qdrant/landing_page.git synced 2026-09-30 16:38:31 +02:00
Code Issues Packages Projects Releases Wiki Activity

min -> \min

Browse Source
This commit is contained in:
Luis Cossío
2023-12-08 10:50:07 +01:00
committed by timvisee
parent ad81ac79ac
commit 71e56a56bf
2 changed files with 2 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files
qdrant-landing/content/documentation/concepts/explore.md
+1 -1
View File
@@ -569,7 +569,7 @@ Conversely, in the absence of a target, a rigid integer-by-integer function does
We can directly associate the score function to a loss function, where 0.0 is the maximum score a point can have, which means it is only in positive areas. As soon as a point exists closer to a negative example, its loss will simply be the difference of the positive and negative similarities.
$$
\text{context score} = \sum min(s(v^+_i) - s(v^-_i), 0.0)
\text{context score} = \sum \min(s(v^+_i) - s(v^-_i), 0.0)
$$
Where $v^+_i$ and $v^-_i$ are the positive and negative examples of each pair, and $s(v)$ is the similarity function.