Skip to content

Commit

Permalink
[FR & EN] YouTube subtitles (#796)
Browse files Browse the repository at this point in the history
* fix unicode

* fix unicode

* fix unicode

* fix unicode

* fix unicode

* fix unicode

* Update practicum05.sbv

* fix unicode

* fix unicode

* fix unicode

* fix unicode

* fix unicode

* fix unicode

* fix unicode

* fix unicode

* fix unicode

* fix unicode

* fix unicode

* fix unicode

* fix timers

* tweaking

* Update lecture01.sbv

* Update practicum01.sbv

* Create lecture02.sbv

* Create practicum02.sbv

* Update lecture03.sbv

* Create practicum03.sbv

* Create practicum04.sbv

* Create lecture05.sbv

* Create practicum05.sbv

* Create practicum06.sbv

* Create practicum07.sbv

* Create practicum08.sbv

* Create practicum09.sbv

* Create practicum10.sbv

* Create practicum11.sbv

* Create practicum12.sbv

* Create practicum13.sbv

* Create practicum14.sbv

* Create practicum15A.sbv

* Create practicum15B.sbv

* Create lecture06.sbv

* Create lecture07.sbv

* Create lecture08.sbv

* Create lecture09.sbv

* Create lecture10.sbv

* Create lecture11.sbv

* Create lecture13.sbv

* Create lecture14.sbv

* twitter account + message

Added an information message in case French subtitles are added to YouTube before V2 of the site is deployed.
And it was time for me to create a twitter account 🙃

* Update lecture02.sbv

* Update lecture02.sbv

* Update practicum02.sbv

* Update practicum02.sbv

* Update lecture03.sbv

* Update lecture05.sbv

* Update practicum05.sbv

* Update practicum05.sbv

* Update lecture06.sbv

* Update lecture06.sbv

* Update practicum06.sbv

* Update practicum06.sbv

* Update practicum07.sbv

* Update practicum07.sbv

* Update practicum09.sbv

* Update practicum09.sbv

* Update practicum11.sbv

* Update practicum12.sbv

* Update practicum12.sbv

* Update practicum13.sbv

* Update practicum13.sbv

* Update practicum13.sbv

* Update practicum15A.sbv

* Update practicum15A.sbv

* Update docs/en/week15/practicum15A.sbv

Co-authored-by: Alfredo Canziani <[email protected]>
  • Loading branch information
lbourdois and Atcold authored Oct 19, 2021
1 parent a568303 commit 90fad5e
Show file tree
Hide file tree
Showing 49 changed files with 69,664 additions and 3,719 deletions.
13 changes: 5 additions & 8 deletions docs/en/week01/lecture01.sbv
Original file line number Diff line number Diff line change
Expand Up @@ -3167,19 +3167,19 @@ It's a two layer neural net,
where the first layer, which is symbolized by this function K here,

1:21:10.830,1:21:16.550
each unit in the first layer compares the input vector X to one of the training samples X^i's.
each unit in the first layer compares the input vector X to one of the training samples Xⁱ.

1:21:16.560,1:21:19.850
OK, so you take your training samples, let's say you have a thousand of them—

1:21:20.160,1:21:22.789
so you have a thousand X^i's, from i = 1 to 1,000,
so you have a thousand Xⁱ, from i = 1 to 1,000,

1:21:23.190,1:21:26.360
and you have some function K that is going to compare X and X^i.

1:21:26.520,1:21:31.490
Good example of a function to compare the two is you take the dot product between X and X^i, and you pass the result
Good example of a function to compare the two is you take the dot product between X and Xⁱ, and you pass the result

1:21:31.490,1:21:32.790
through,
Expand All @@ -3191,14 +3191,11 @@ like, exponential minus square or something. So you get a Gaussian
response,

1:21:39.300,1:21:42.800
as a function of the distance between X and X^i, OK.
as a function of the distance between X and Xⁱ, OK.

1:21:42.800,1:21:45.559
So it's a way of comparing to two vectors, doesn't matter what it is.

1:21:46.980,1:21:48.510


1:21:48.510,1:21:54.019
And, then you take those scores coming out of this K function that compares the input to every sample and

Expand Down Expand Up @@ -3287,7 +3284,7 @@ that doesn't solve the problem.
You can use a two-layer neural net, OK. So this is the top right here. The first layer is a nonlinear function

1:24:07.310,1:24:13.820
F applied to the product of a matrix W^0 by input vector; and then the second layer multiplied by the second matrix; and then
F applied to the product of a matrix W by input vector; and then the second layer multiplied by the second matrix; and then

1:24:14.040,1:24:16.040
passes it through another non-linearity.
Expand Down
374 changes: 187 additions & 187 deletions docs/en/week02/lecture02.sbv

Large diffs are not rendered by default.

Loading

0 comments on commit 90fad5e

Please sign in to comment.