diff options
| author | Vasil Zlatanov <v@skozl.com> | 2018-12-13 16:51:58 +0000 |
|---|---|---|
| committer | Vasil Zlatanov <v@skozl.com> | 2018-12-13 16:51:58 +0000 |
| commit | b5d3bed9a9548c80eb457b61fb5ff33de3f77a8c (patch) | |
| tree | ff9b2521aaf265124364d4274994eccd425aae12 | |
| parent | 1b3a472579c755c46a1a92922954cc0dad9bb30c (diff) | |
| download | vz215_np1915-b5d3bed9a9548c80eb457b61fb5ff33de3f77a8c.tar.gz vz215_np1915-b5d3bed9a9548c80eb457b61fb5ff33de3f77a8c.tar.bz2 vz215_np1915-b5d3bed9a9548c80eb457b61fb5ff33de3f77a8c.zip | |
s/label/ref/
| -rwxr-xr-x | report/paper.md | 2 |
1 files changed, 1 insertions, 1 deletions
diff --git a/report/paper.md b/report/paper.md index 2789923..a20e943 100755 --- a/report/paper.md +++ b/report/paper.md @@ -71,7 +71,7 @@ identification is shown in red. Magnitude normalization is a common technique, used to equalize feature importance. Applying magnitude normalization (scaling feature vectors to unit length) had a negative effect re-identification. Furthemore standartization by removing feature mean and deviation -also had negative effect on performance as seen on figure \label{fig:baselineacc}. This may +also had negative effect on performance as seen on figure \ref{fig:baselineacc}. This may be due to the fact that we are removing feature scaling that was introduced by the Neural network, such that some of the features are more significant than the others. By standartizing our features at this point, we remove such scaling and may be losing using useful metrics. |