user avatar
user avatar
user avatar
Gilad Deutsch
  • Member for 2 years, 3 months
  • Last seen more than a month ago
23 votes
3 answers
4k views

Why do most deep learning papers not include an implementation?

9 votes
4 answers
2k views

Should neural nets be deeper the more complex the learning problem is?

5 votes
1 answer
161 views

Loss function for choosing a subset of objects

3 votes
1 answer
61 views

A model for each sub-problem vs one model for the whole problem

2 votes
1 answer
62 views

Does net with ReLU not learn when output < 0?

2 votes
4 answers
427 views

Reinforcement Learning (and specifically REINFORCE algorithm) for one-round "games"

2 votes
0 answers
54 views

Can a typical supervised learning problem be solved with reinforcement learning methods?

1 vote
1 answer
67 views

Why are denser layers needed in computer vision neural nets?

1 vote
2 answers
134 views

Should batch-normalization/dropout/activation-function layers be used after the last fully connected layer?