Skip to main content
Cross Validated
Variational's user avatar
Variational's user avatar
Variational's user avatar
Variational
  • Member for 3 years, 4 months
  • Last seen more than a month ago
  • San Francisco, CA
Profile Activity
Stats
351
reputation
4k
reached
12
answers
0
questions
Communities
About

Research Engineer at Google DeepMind. Former ML Tech Lead at Startup.

Badges
View all badges
This user doesn’t have any gold badges yet.
1
silver badge
10
bronze badges
Top tags
View all tags
12
Score
7
Posts
58
Posts %
8
Score
5
Posts
42
Posts %
6
Score
3
Posts
25
Posts %
6
Score
3
Posts
25
Posts %
3
Score
2
Posts
17
Posts %
3
Score
2
Posts
17
Posts %
Top posts
View all questions and answers
answer
3
In factor VAE, do you freeze the discriminator weights during the back propagation step for the FVAE loss?
Jul 6, 2023
answer
3
Is concatenating a single integer sufficient for encoding positional embeddings in transformer models?
Jul 12, 2023
answer
2
Cross-validation and model selection of ANN
Jul 5, 2023
answer
2
Why is the layer normalization same with the instance normalization in transformers (or NLP)?
Jul 5, 2023
answer
2
Using Word Embeddings in Clustering and Topic Modelling
Jul 6, 2023
answer
2
Necessity of keys and queries in a decoder-only transformer model
Jul 10, 2023
answer
2
Why does ViTForMaskedImageModeling not construct the original image correctly?
Jul 14, 2023
answer
1
In transformer architecture, Why does Masked Self Attention layer uses additive masks not multiplicative mask?
Jul 5, 2023
answer
1
Considering weights right of the embeddings layer aren't used in Doc2Vec/Word2Vec, is the informative capacity of the embeddings not strongly reduced?
Jul 13, 2023
answer
1
I decomposed only the first four components from PCA/EOF. Can I get the percent variance of each component against the entire dataset?
Jul 14, 2023