dr_domi/udlbook
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

"TO DO" > "TODO

Browse Source 
In [commit 6072ad4](6072ad4), @KajvanRijn kindly changed all "TO DO" to "TODO" in the code blocks. That's useful. In addition, it should be changed (as here) in the instructions. Then there's no doubt or issue for anyone searching all instances.
This commit is contained in:
Mark Gotham
2025-02-11 15:11:06 +00:00
parent 666cbb02d5
commit 9649ce382b
69 changed files with 78 additions and 78 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
Notebooks/Chap07/7_3_Initialization.ipynb
View File

@@ -32,7 +32,7 @@
"\n",
"This notebook explores weight initialization in deep neural networks as described in section 7.5 of the book.\n",
"\n",
"Work through the cells below, running each cell in turn. In various places you will see the words \"TO DO\". Follow the instructions at these places and make predictions about what is going to happen or write code to complete the functions.\n",
"Work through the cells below, running each cell in turn. In various places you will see the words \"TODO\". Follow the instructions at these places and make predictions about what is going to happen or write code to complete the functions.\n",
"\n",
"Contact me at udlbookmail@gmail.com if you find any mistakes or have any suggestions."
],
@@ -191,10 +191,10 @@
"# You can see that the values of the hidden units are increasing on average (the variance is across all hidden units at the layer\n",
"# and the 1000 training examples\n",
"\n",
"# TO DO\n",
"# TODO\n",
"# Change this to 50 layers with 80 hidden units per layer\n",
"\n",
"# TO DO\n",
"# TODO\n",
"# Now experiment with sigma_sq_omega to try to stop the variance of the forward computation exploding"
],
"metadata": {
@@ -340,10 +340,10 @@
"# You can see that the gradients of the hidden units are increasing on average (the standard deviation is across all hidden units at the layer\n",
"# and the 100 training examples\n",
"\n",
"# TO DO\n",
"# TODO\n",
"# Change this to 50 layers with 80 hidden units per layer\n",
"\n",
"# TO DO\n",
"# TODO\n",
"# Now experiment with sigma_sq_omega to try to stop the variance of the gradients exploding\n"
],
"metadata": {