From 5e9a2d4713ef222e2d3e02f5cbf70fe1f13f8ed8 Mon Sep 17 00:00:00 2001 From: Jan Nils Ferner Date: Wed, 18 Jan 2017 06:20:02 +0100 Subject: [PATCH] Swag (#70) * abstract * Add style cleanup * Extra swag * Sacv * aishent --- sections/convolutional neural networks/subsampling/poolers.tex | 1 - 1 file changed, 1 deletion(-) diff --git a/sections/convolutional neural networks/subsampling/poolers.tex b/sections/convolutional neural networks/subsampling/poolers.tex index f422776..065ea34 100644 --- a/sections/convolutional neural networks/subsampling/poolers.tex +++ b/sections/convolutional neural networks/subsampling/poolers.tex @@ -1,6 +1,5 @@ Despite the kernels doing a great job at making the image smaller, the resulting data is still quite too big to work with. For that reason one can use poolers, which are nothing but dull compression algorithms. - The most used pooler is the max pooler. \cite{Graham2014} \\ This simple unit traditionally takes four adjacent pixels, then determines the darkest one, and simply concatenates the four original pixels into this smaller single one. Repeat this process over the whole image, and you just scaled it to one fourth of it's original size. \ No newline at end of file