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

Update 6_2_Gradient_Descent.ipynb

Browse Source
This commit is contained in:
udlbook
2024-03-26 17:15:31 -04:00
committed by GitHub
parent 4a5bd9c4d5
commit 7a423507f5
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
Notebooks/Chap06/6_2_Gradient_Descent.ipynb
View File

@@ -265,7 +265,7 @@
"\\frac{\\partial L}{\\partial \\phi_{1}}&\\approx & \\frac{L[\\phi_0, \\phi_1+\\delta]-L[\\phi_0, \\phi_1]}{\\delta}\n", "\\frac{\\partial L}{\\partial \\phi_{1}}&\\approx & \\frac{L[\\phi_0, \\phi_1+\\delta]-L[\\phi_0, \\phi_1]}{\\delta}\n",
"\\end{align}\n", "\\end{align}\n",
"\n", "\n",
"We can't do this when there are many parameters; for a million parameters, we would have to evaluate the loss function two million times, and usually computing the gradients directly is much more efficient." "We can't do this when there are many parameters; for a million parameters, we would have to evaluate the loss function one million plus one times, and usually computing the gradients directly is much more efficient."
] ]
}, },
{ {