oskar/cours
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

eduroam-prg-gm-1-3-245.net.univ-paris-diderot.fr 2025-9-19:10:2:53

Browse Source
This commit is contained in:
oskar
2025-09-19 10:02:53 +02:00
parent 93f6d79129
commit 38917c6afd
2 changed files with 6 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
.obsidian/graph.json vendored
View File

@@ -130,6 +130,6 @@
"repelStrength": 5.263671875, "repelStrength": 5.263671875,
"linkStrength": 1, "linkStrength": 1,
"linkDistance": 30, "linkDistance": 30,
"scale": 2.422433756553115, "scale": 0.15541659193590038,
"close": true "close": true
} }

6
M1 LOGOS .machine learning for NLP.md
View File

@@ -15,6 +15,10 @@ $x_{i} \in \mathbb{R}$ is a scalar
one-hot : boolean vector with all zeroes but one value. Usefull if each dimension represents a word of the vocabulary one-hot : boolean vector with all zeroes but one value. Usefull if each dimension represents a word of the vocabulary
BOW : Bag Of Words
You could represent sentences like that : You could represent sentences like that :
Let our vocabulary be : `V = 'le' 'un' 'garcon' 'lit' 'livre' 'regarde'` Let our vocabulary be : `V = 'le' 'un' 'garcon' 'lit' 'livre' 'regarde'`
Then "le garcon lit le livre" would be written by counting the number of occurences of each word of the sentence in a vector, so `2 0 1 1 1 0` (the formula is ) Then "le garcon lit le livre" would be written by counting the number of occurences of each word of the sentence in a vector, so `2 0 1 1 1 0` (the formula is `sentence +⌿⍤(∘.≡) vocabulary`)
$\cos(u, v) = \frac{u\cdot v}{\|u\| \| v\|}$