diff options
| -rw-r--r-- | docs/tutorial/layers.md | 2 |
1 files changed, 1 insertions, 1 deletions
diff --git a/docs/tutorial/layers.md b/docs/tutorial/layers.md index 8dd67275..5f8f519c 100644 --- a/docs/tutorial/layers.md +++ b/docs/tutorial/layers.md @@ -111,7 +111,7 @@ The `CONVOLUTION` layer convolves the input image with a set of learnable filter - `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`) -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 $$(1 + (\alpha/n) \sum_i x_i)^\beta$$, 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). +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). #### im2col |