Skip to main content
Cross Validated
Avelina's user avatar
Avelina's user avatar
Avelina's user avatar
Avelina
  • Member for 3 years, 5 months
  • Last seen more than a month ago
Profile Activity
Stats
1,168
reputation
69k
reached
23
answers
11
questions
Communities
About

Masters Degree in Computer Science from University of St Andrews.
Working on Machine Learning PhD at St Andrews.

Experience with Graphics, HPC, Machine Learning and GPU programming.

Favorite langs: C++, CUDA, GLSL
Other langs: JS, Python, Java, Scala, Haskell

Hobies: Music production, 3D modelling, playing Elite Dangerous

Badges
View all badges
This user doesn’t have any gold badges yet.
5
silver badges
19
bronze badges
Top tags
View all tags
40
Score
19
Posts
56
Posts %
30
Score
18
Posts
53
Posts %
14
Score
5
Posts
15
Posts %
10
Score
6
Posts
18
Posts %
8
Score
3
Posts
9
Posts %
7
Score
6
Posts
18
Posts %
Top posts
View all questions and answers
answer
9
Embedding data into a larger dimension space
Jun 4, 2021
answer
7
Using batchnorm and dropout simultaneously?
Jun 6, 2021
question
6
Why do large LMs use the transpose of the word embeddings matrix in the classification head?
Aug 7, 2022
answer
6
How to choose a batch size and the number of epochs while training a NN
Jun 4, 2021
answer
5
Validation loss increases while Training loss decrease
Jun 9, 2021
question
4
Categorical cross-entropy vs Binary cross-entropy for multi-class classification with mixup
Jun 29, 2021
answer
4
The receptive field of a stack of dilated convolution layers with exponentially increasing dilation
Jul 12, 2021
question
3
Underperforming SELUs - How to correctly constrain layer weights in TF/Keras?
Jun 6, 2021
answer
3
Does training time of CNN includes the validation time performed after every epoch?
Jun 4, 2021
answer
3
Using 3-channel (RGB) model for classification 4-channel (RGBY) images
Jun 4, 2021