chris/fastbook
1
0
Fork 0
mirror of https://github.com/fastai/fastbook.git synced 2025-04-04 18:00:48 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge 0bf496de21 into e8baa81d89

Browse Source
This commit is contained in:
Madalin Tatarciuc 2024-08-31 00:29:40 +03:00 committed by GitHub
commit 49be007238
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
04_mnist_basics.ipynb
View File

@ -3937,7 +3937,7 @@
"source": [
"A very small change in the value of a weight will often not actually change the accuracy at all. This means it is not useful to use accuracy as a loss function—if we do, most of the time our gradients will actually be 0, and the model will not be able to learn from that number.\n",
"\n",
"> S: In mathematical terms, accuracy is a function that is constant almost everywhere (except at the threshold, 0.5), so its derivative is nil almost everywhere (and infinity at the threshold). This then gives gradients that are 0 or infinite, which are useless for updating the model.\n",
"> S: In mathematical terms, accuracy is a function that is constant almost everywhere (except at the threshold, 0.5), so its derivative is null almost everywhere (and infinity at the threshold). This then gives gradients that are 0 or infinite, which are useless for updating the model.\n",
"\n",
"Instead, we need a loss function which, when our weights result in slightly better predictions, gives us a slightly better loss. So what does a \"slightly better prediction\" look like, exactly? Well, in this case, it means that if the correct answer is a 3 the score is a little higher, or if the correct answer is a 7 the score is a little lower.\n",
"\n",