Skip to main content
Share Your Experience: Take the 2024 Developer Survey
generic_user's user avatar
generic_user's user avatar
generic_user's user avatar
generic_user
  • Member for 7 years, 2 months
  • Last seen more than a month ago
11 votes
2 answers
4k views

Does batch normalization mean that sigmoids work better than ReLUs?

6 votes
1 answer
303 views

What is the point of tensors in CNNs? Why not simply reshape the data into matrices?

4 votes
2 answers
145 views

Seeking advice on database architecture -- given my problem, what tools should I learn?

2 votes
1 answer
34 views

How are neural nets combined to form intelligent systems?

2 votes
1 answer
86 views

How to think about prediction error that is not convex in hyperparameter, or over the course of training

2 votes
1 answer
30 views

Training pipelines where featurization/NLP is more expensive than backprop

1 vote
0 answers
650 views

Does it ever make sense for upper layers to have more nodes than lower layers?

1 vote
1 answer
487 views

Architecture for multivariate multi-time-series model where some features are TS specific and some features are global

1 vote
0 answers
225 views

loss = function(iteration) gets super wobbly once it gets near the bottom

1 vote
1 answer
205 views

Does anyone know how google play music's recommendation engine works?

1 vote
1 answer
154 views

Dropout without the averaging

0 votes
2 answers
143 views

What is valued more in the data science job market, statistical analysis or data processing?