From c965732f120f91592c2f716f4f24e0c0015e6010 Mon Sep 17 00:00:00 2001 From: Roman Shchekin Date: Sat, 24 Mar 2018 17:48:57 +0300 Subject: [PATCH] 8 -> 4 dimensions > The network is able to cram most of the necessary information into these 8-dimensional representations, but not all of it. But in example you used 4-dimensional Dense layer. --- 3.6-classifying-newswires.ipynb | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/3.6-classifying-newswires.ipynb b/3.6-classifying-newswires.ipynb index 687d6ddfe7..1259adc500 100644 --- a/3.6-classifying-newswires.ipynb +++ b/3.6-classifying-newswires.ipynb @@ -923,7 +923,7 @@ "\n", "Our network now seems to peak at ~71% test accuracy, a 8% absolute drop. This drop is mostly due to the fact that we are now trying to \n", "compress a lot of information (enough information to recover the separation hyperplanes of 46 classes) into an intermediate space that is \n", - "too low-dimensional. The network is able to cram _most_ of the necessary information into these 8-dimensional representations, but not all \n", + "too low-dimensional. The network is able to cram _most_ of the necessary information into these 4-dimensional representations, but not all \n", "of it." ] },