Skip to main content
How are we doing? Please help us improve Stack Overflow. Take our short survey
Shamane Siriwardhana's user avatar
Shamane Siriwardhana's user avatar
Shamane Siriwardhana's user avatar
Shamane Siriwardhana
PhD Candidate University Of Auckland
  • Member for 8 years, 5 months
  • Last seen more than a month ago
Profile Activity
Stats
4,071
reputation
580k
reached
43
answers
61
questions
Communities
About

In love with information retrieval, question answering, and multi-modal deep learning.

Badges
View all badges
7
gold badges
36
silver badges
75
bronze badges
Top tags
View all tags
131
Score
73
Posts
70
Posts %
64
Score
39
Posts
38
Posts %
60
Score
17
Posts
16
Posts %
39
Score
7
Posts
7
Posts %
16
Score
9
Posts
9
Posts %
15
Score
7
Posts
7
Posts %
Top posts
View all questions, answers, and articles
55
Running Tensorflow in Jupyter Notebook
Apr 6, 2017
39
What is the difference between Luong attention and Bahdanau attention?
Jun 9, 2017
36
What is the difference between Luong attention and Bahdanau attention?
May 29, 2017
28
What is the purpose of the ROI layer in a Fast R-CNN?
Apr 15, 2017
16
Why "GELU" activation function is used instead of ReLu in BERT?
Aug 17, 2019
14
CNN: input stride vs. output stride
Jul 27, 2017
13
Pytorch DataLoader fails when the number of examples are not exactly divided by the batch size
Jun 13, 2019
13
Do we need to use beam search in training process?
Jun 14, 2017
13
What does a tensorflow "op" do?
Apr 8, 2017
12
How to handle extremely long LSTM sequence length?
Jun 11, 2017
Top network posts
View all network posts
14
What is the difference between Dilated Convolution and Deconvolution?
13
How and why does Batch Normalization use moving averages to track the accuracy of the model as it trains?
10
How does Tensorflow `tf.train.Optimizer` compute gradients?
8
Why are policy gradient methods preferred over value function approximation in continuous action domains?
8
What is Compatible Function Approximation theorem in reinforcement learning?