Cross Validated
Jindřich's user avatar
Jindřich's user avatar
Jindřich's user avatar
Jindřich
  • Member for 4 years, 4 months
  • Last seen this week
Profile Activity
Stats
3,179
reputation
95k
reached
107
answers
1
question
Communities
About

Researcher in natural language processing and neural machine translation, delved in deep learning, coding in Python, TensorFlow and PyTorch, Vim lover.

Badges
View all badges
This user doesn’t have any gold badges yet.
7
silver badges
20
bronze badges
Top tags
View all tags
105
Score
39
Posts
36
Posts %
104
Score
66
Posts
61
Posts %
83
Score
21
Posts
19
Posts %
69
Score
22
Posts
20
Posts %
42
Score
26
Posts
24
Posts %
36
Score
14
Posts
13
Posts %
Top posts
View all questions and answers
All Questions Answers
Score Newest
answer
27
Why are residual connections needed in transformer architectures?
Feb 21, 2022
answer
10
Why do attention models need to choose a maximum sentence length?
Jun 7, 2019
answer
9
Self Attention for Variable Length Sequence Classification
Sep 24, 2020
answer
9
Meaning of the value matrix in self-attention
Aug 10, 2020
answer
8
What are the advantages of combining BiLSTM and CRF?
Mar 30, 2020
question
6
Clustering with large number of clusters
Nov 2, 2020
answer
5
Encoding Layers in the Transformer
Jun 5, 2019
answer
5
Difference between non-contextual and contextual word embeddings
Jan 20, 2020
answer
5
Word embeddings - Pre-trained tokenizers vs more involved methods
Sep 10, 2020
answer
4
Transformer based decoding
May 31, 2019
Top network posts
View all network posts
45
Pytorch LSTM vs LSTMCell
28
Why Bert transformer uses [CLS] token for classification instead of average over all tokens?
28
what the difference between att_mask and key_padding_mask in MultiHeadAttnetion
15
BERT sentence embeddings from transformers
14
How are the TokenEmbeddings in BERT created?

Your privacy

By clicking “Accept all cookies”, you agree Stack Exchange can store cookies on your device and disclose information in accordance with our Cookie Policy.