From 3d7cfc40c170f93ac88909f40ca0208269ee26a9 Mon Sep 17 00:00:00 2001 From: Lydorn Date: Mon, 10 Jul 2017 15:43:47 +0200 Subject: Update lrn.md Fixed typo "locaitons " -> "location" in line 17 --- docs/tutorial/layers/lrn.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'docs') diff --git a/docs/tutorial/layers/lrn.md b/docs/tutorial/layers/lrn.md index 2fbef734..f5e48292 100644 --- a/docs/tutorial/layers/lrn.md +++ b/docs/tutorial/layers/lrn.md @@ -14,7 +14,7 @@ title: Local Response Normalization (LRN) - `local_size` [default 5]: the number of channels to sum over (for cross channel LRN) or the side length of the square region to sum over (for within channel LRN) - `alpha` [default 1]: the scaling parameter (see below) - `beta` [default 5]: the exponent (see below) - - `norm_region` [default `ACROSS_CHANNELS`]: whether to sum over adjacent channels (`ACROSS_CHANNELS`) or nearby spatial locaitons (`WITHIN_CHANNEL`) + - `norm_region` [default `ACROSS_CHANNELS`]: whether to sum over adjacent channels (`ACROSS_CHANNELS`) or nearby spatial locations (`WITHIN_CHANNEL`) The local response normalization layer performs a kind of "lateral inhibition" by normalizing over local input regions. In `ACROSS_CHANNELS` mode, the local regions extend across nearby channels, but have no spatial extent (i.e., they have shape `local_size x 1 x 1`). In `WITHIN_CHANNEL` mode, the local regions extend spatially, but are in separate channels (i.e., they have shape `1 x local_size x local_size`). Each input value is divided by $$(1 + (\alpha/n) \sum_i x_i^2)^\beta$$, where $$n$$ is the size of each local region, and the sum is taken over the region centered at that value (zero padding is added where necessary). -- cgit v1.2.3