Connect your moderator Slack workspace to receive post notifications:
logistic regression pytorch
Exercises · 76 · 3 · 24 Nov '20
Hi, In the part of lab 10 on 'Logistic regression in PyTorch' I am not quite sure how the class…
Different dropout used in part 1
Exercises · 94 · 3 · 20 Nov '20
Good evening, I wonder why we used different ways to implement dropout in the first part of the …
Posting the solutions
Exercises · 78 · 2 · 18 Nov '20
Hey, could you please push the solutions for session 9 :) Thanks
Unable to solve problem3
Exercises · 80 · 1 · 15 Nov '20
Good evening, I am unable to solve the first part, where we need to set the gradient to zero in …
Text ex.2
Exercises · 93 · 2 · 9 Nov '20
Hello, in the text for exercise 2: ![a.JPG](https://oknoname-crm1.s3.amazonaws.com/spirit/images/…
Error Google Colab
Exercises · 55 · 2 · 8 Nov '20
Good morning, I've been trying to use Google Colab to complete the problem set but it doesn't wa…
PyTorch Tutorial
Exercises · 71 · 3 · 7 Nov '20
Hey ! I'm a little confused at where to find the 60 min video on Pytorch, I only see the "previe…
Theory 2.1
Exercises · 78 · 2 · 7 Nov '20
Hello, ![a.JPG](https://oknoname-crm1.s3.amazonaws.com/spirit/images/113/c42884ab2c4f4c649acc0fb16…
Why transform the prediction to {-1, 1} label again?
Exercises · 81 · 3 · 6 Nov '20
Hi, In exercise 7 I'm wondering why we use transformation \(y = 2\tilde{y}-1\) when calculating th…
Not able to reach the same visualization of MLP as the problem set
Exercises · 69 · 3 · 6 Nov '20
With : learning rate = 0,01; hidden_size = 2; num_epoch =300; loss function = MSE; 2 linear layers;…
Showing that a function is jointly convex
Exercises · 78 · 2 · 5 Nov '20
Hello, Suppose we are wanting to show that a function \(f(x, y)\) is jointly convex in \(x\) and…
Coordinate Ascent algorithm clarifications
Exercises · 125 · 3 · 1 Nov '20
Hello, The recent discussion (on Discord and on the forum) has really confused me regarding the …
Lab 6 Ex3.1
Exercises · 144 · 2 · 28 Oct '20
Hi ! I was wondering if instead of the given formula, $$P[y_n|x_n;w;r_n] = N(y_n|r_n^Twx_n, \si…
"Identifiable model" ?
Exercises · 160 · 5 · 26 Oct '20
Good evening, While doing the exercice set 6, I did not understand what you meant in the multi-c…
SGD_not_converging
Exercises · 84 · 3 · 21 Oct '20
Hi ! I was wondering if it's normal that for the SGD the loss still varies and so do the weights …
Warmup Questions
Exercises · 82 · 2 · 20 Oct '20
Hi! Would it be possible to get solutions to the warmup questions from problem set 2? or at least s…
Visualization function
Exercises · 56 · 2 · 18 Oct '20
Hi i think there may be a mistake in the implementation of the visualization function in plots.py a…
The effect of ratio_train
Exercises · 127 · 5 · 13 Oct '20
I have one confusion about the ratio which will affect the figure signifiacntly. When I try to mult…
Solutions of exercices (theory part) for last weeks
Exercises · 62 · 3 · 13 Oct '20
Hello, Is it planned that we get access to the solutions of theory exercices of the weeks 3 and …
Excercise 4 loss vs rmse
Exercises · 129 · 6 · 12 Oct '20
Hello, I was wondering why in the first function "cross_validation" we output losses (which is d…