Artificial Intelligence
pi-tau's user avatar
pi-tau's user avatar
pi-tau's user avatar
pi-tau
  • Member for 8 months
  • Last seen more than a week ago
Profile Activity
Stats
612
reputation
16k
reached
38
answers
1
question
top 3% this year
Communities
Badges
View all badges
This user doesn’t have any gold badges yet.
This user doesn’t have any silver badges yet.
9
bronze badges
Top tags
View all tags
21
Score
13
Posts
33
Posts %
19
Score
10
Posts
26
Posts %
9
Score
15
Posts
38
Posts %
8
Score
4
Posts
10
Posts %
6
Score
5
Posts
13
Posts %
4
Score
5
Posts
13
Posts %
Top posts
View all questions and answers
All Questions Answers
Score Newest
answer
5
Can someone help me understand the intuition behind the query, key and value matrices in the transformer architecture?
Jul 24
answer
4
Is there a proper initialization technique for the weight matrices in multi-head attention?
Mar 25
answer
3
Why in Multi-Head Attention implementation should we use $3$ linear layers for Q, K, V instead of $3 * h$ layers?
Jul 25
answer
3
Which situation will helpful using encoder or decoder or both in transformer model?
Jul 29
answer
3
One to one relation between state + action -> reward
Sep 12
answer
2
Understanding KL Stopping and KL Cutoff for the PPO algorithm
Sep 19
answer
2
Filling replay buffer with expert trajectories for PPO/DQN
Sep 5
answer
2
Why use a "square root" in the scaled dot product
Sep 25
answer
2
How to expand reconstruction error to mean squared error in Variational AutoEncoder?
Aug 4
answer
2
If a residual block learns to approximate the identity function, should we reinitialize the weights?
Aug 24

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.