This forum is inactive. Browsing/searching possible.
Connect your moderator Slack workspace to receive post notifications:
word2vec algorithm
Lectures
·
85
·
1
·
11 Jan '21
Hello,
I'm afraid I don't understand the word2vec algorithm. For the positive sampling do we jus…
Previous Year's Course Notes on Graphical Models
Lectures
·
87
·
2
·
11 Jan '21
Greetings,
Would it be possible for us to access previous year's course notes on graphical model…
function (matrix) convexity
Lectures
·
66
·
1
·
11 Jan '21
Hi,
I am a bit confused as to how convexity is defined with respect to 2 matrices Z,W. Even just…
loss function and sgd
Lectures
·
101
·
3
·
11 Jan '21
Hello,
I remember in the labs sometimes emphasis was placed on how to implement SGD based on the…
Data augmentation
Lectures
·
73
·
2
·
11 Jan '21
In lecture 9b (Data augmentation for neural networks), is the rotation of the numbers here (Data au…
gans loss functions
Lectures
·
124
·
3
·
10 Jan '21
Hello,
I am a bit lost trying to understand the different formulation used to describe GANS. In …
Questions about GAN Objective
Lectures
·
197
·
4
·
10 Jan '21
Greetings,
I have 3 questions related to the GAN training objective (in lecture notes 12a, page …
Alternating GAN algorithm
Lectures
·
154
·
5
·
10 Jan '21
Hello there !
I have some troubles with the formulation of the parameter updates to train the gene…
Closed form solution for MAE ost finction
Lectures
·
68
·
2
·
10 Jan '21
Hello,
Can someone please help with the derivation of the close form solution for the 1 paramete…
MLE for Laplace distribution
Lectures
·
39
·
1
·
10 Jan '21
Can someone show me how to do the MLE for Laplace distribution?
Thanks in advance
Computational cost
Lectures
·
168
·
4
·
9 Jan '21
If the cost to compute \( \mathbf{e}\) is
$$
O(N*D) + O(N)
$$
and the cost to compute \(…
Representation power
Lectures
·
143
·
3
·
8 Jan '21
Dear TAs,
I'm struggling to understand why on a bounded domain, neural nets can **not** approxim…
generalization error bounds
Lectures
·
63
·
1
·
8 Jan '21
Hi!
I am having difficulty grasping the steps taken in 'a little thought' to obtain expression s…
exponential family- invertibility of link function
Lectures
·
63
·
1
·
8 Jan '21
Hello,
in al the examples investigated we saw a one to one relationship between E[phi(y)] and et…
minibatch implementation
Lectures
·
73
·
3
·
8 Jan '21
Good evening,
Looking online I find different ways to implement minibatch GD. Some select B rand…
bias-variance decomposition: what exactly is variance
Lectures
·
66
·
1
·
8 Jan '21
hi,
In bias-variance decomposition derivation I understand that the bias term is a measure of th…
Maximum log likelihood ?
Lectures
·
100
·
2
·
7 Jan '21
Dear TAs,
I'm struggling to understand where the log comes from.
Is this the maximum likeli…
log of count for co-occurence matrix
Lectures
·
112
·
3
·
7 Jan '21
Hello,
If we used log(#occurence) then the sparse count matrix will have lots of undefined log(0…
Why does adding w*sgn(w) subject perturbed data to upper bound of max norm (epsilon)?
Lectures
·
54
·
1
·
7 Jan '21
In the paper describing the fast gradient sign method, the authors explain why adversarial samples …
soft clustering
Lectures
·
104
·
3
·
6 Jan '21
Hello,
I am having a hard time understanding what the color gradient represents on the graph fro…