From fd3205cbf91baff616c8d4c705899f28bb736514 Mon Sep 17 00:00:00 2001
From: Mirko Birbaumer <mirko.birbaumer@hslu.ch>
Date: Wed, 9 Dec 2020 20:26:55 +0000
Subject: [PATCH] Text new
Slightly changed text
---
...pyter Notebook Block 4 - Convolutional Neural Networks.ipynb | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/notebooks/Block 4/Jupyter Notebook Block 4 - Convolutional Neural Networks.ipynb b/notebooks/Block 4/Jupyter Notebook Block 4 - Convolutional Neural Networks.ipynb
index 9a555d0..ae34ea6 100644
--- a/notebooks/Block 4/Jupyter Notebook Block 4 - Convolutional Neural Networks.ipynb
+++ b/notebooks/Block 4/Jupyter Notebook Block 4 - Convolutional Neural Networks.ipynb
@@ -3326,7 +3326,7 @@
"- The sparsity of the activations increases with the depth of the layer : in the first layer, all filters are activated by the input image; but in the following layers, more and more filters are blank. This means the pattern encoded by the filter is not found in the input image. \n",
"\n",
"\n",
- "We have just evidenced an important universal characteristics of the representations learned by deep neural networks: the features extracted by a layer become increasingly abstract with the depth of the layer. The activations of higher layers carry less and less information about the specific input being seen, and more and more information about the target (in this case, the class fo the image: cat or dog). A deep neural network effectively acts as an _information distillation pipeline_, with raw data going in (in this case, RGB pictures) and being repeatedly transformed so that irrelevant information is magnified and refined (for example, the specific visual appearance of the image), and useful information is magnified and refined (for example, the class of the image)."
+ "We have just evidenced an important universal characteristics of the representations learned by deep neural networks: the features extracted by a layer become increasingly abstract with the depth of the layer. The activations of higher layers carry less and less information about the specific input being seen, and more and more information about the target (in this case, the class fo the image: cat or dog). A deep neural network effectively acts as an _information distillation pipeline_, with raw data going in (in this case, RGB pictures) and being repeatedly transformed so that irrelevant information is filtered out (for example, the specific visual appearance of the image), and useful information is magnified and refined (for example, the class of the image)."
]
},
{
--
GitLab