explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2024-11-11 04:08:09 +03:00
Code Issues Packages Projects Releases Wiki Activity

Merge pull request #1724 from mpuels/patch-7

Browse Source 
doc: Fix minor mistakes
This commit is contained in:
Ines Montani 2017-12-17 12:09:17 +00:00 committed by GitHub
commit 4befd8bd44
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 3 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
website/usage/_training/_tips.jade
View File

@ -4,7 +4,7 @@ p
| There are lots of conflicting "recipes" for training deep neural
| networks at the moment. The cutting-edge models take a very long time to
| train, so most researchers can't run enough experiments to figure out
| what's #[em really] going on. For what it's worth, here's a recipe seems
| what's #[em really] going on. For what it's worth, here's a recipe that seems
| to work well on a lot of NLP problems:
+list("numbers")
@ -113,7 +113,7 @@ p
+h(3, "tips-param-avg") Parameter averaging
p
| The last part of our optimisation recipe is #[strong parameter averaging],
| The last part of our optimization recipe is #[strong parameter averaging],
| an old trick introduced by
| #[+a("https://cseweb.ucsd.edu/~yfreund/papers/LargeMarginsUsingPerceptron.pdf") Freund and Schapire (1999)],
| popularised in the NLP community by
@ -126,7 +126,7 @@ p
p
| The trick is to store the moving average of the weights during training.
| We don't optimise this average – we just track it. Then when we want to
| We don't optimize this average – we just track it. Then when we want to
| actually use the model, we use the averages, not the most recent value.
| In spaCy (and #[+a(gh("thinc")) Thinc]) this is done by using a
| context manager, #[+api("language#use_params") #[code use_params]], to