this is for holding javascript data
chengds edited textbf_Considerations_The_goal_of__.tex
over 8 years ago
Commit id: 3766d54f2e8ce870fc1ac81cf0edc0a8d8b35896
deletions | additions
diff --git a/textbf_Considerations_The_goal_of__.tex b/textbf_Considerations_The_goal_of__.tex
index 295c03e..fc565ab 100644
--- a/textbf_Considerations_The_goal_of__.tex
+++ b/textbf_Considerations_The_goal_of__.tex
...
The goal of the above HOG scheme is the efficient extraction and detection of features. There is an obvious difference with the convolutional layers of a CNN, which instead learn the features from the data.
One of the goals of quickly learnable part detectors was to allow on-the-fly creation for temporary use.
A problem with neural nets, similar to gmms is the permutability of the solutions due to the sums.