Gilad Deutsch
  • Member for 1 year, 9 months
  • Last seen more than a month ago
3 answers
21 votes
4k views
5 bookmarks
Why do most deep learning papers not include an implementation?
4 answers
9 votes
2k views
7 bookmarks
Should neural nets be deeper the more complex the learning problem is?
1 answers
5 votes
151 views
Loss function for choosing a subset of objects
1 answers
2 votes
56 views
A model for each sub-problem vs one model for the whole problem
0 answers
2 votes
51 views
Can a typical supervised learning problem be solved with reinforcement learning methods?
4 answers
2 votes
386 views
Reinforcement Learning (and specifically REINFORCE algorithm) for one-round "games"
1 answers
2 votes
55 views
1 bookmarks
Does net with ReLU not learn when output < 0?
2 answers
1 votes
109 views
Should batch-normalization/dropout/activation-function layers be used after the last fully connected layer?
1 answers
1 votes
56 views
Why are denser layers needed in computer vision neural nets?
0 answers
0 votes
16 views
knowledge data base or model for "terms" containment
0 answers
0 votes
11 views
Increased performance using monotonic constraints with neural networks