InAFlash
  • Member for 4 years, 2 months
  • Last seen more than a week ago
4 answers
13 votes
4k views
7 bookmarks
Is Gradient Descent central to every optimizer?
2 answers
12 votes
20k views
8 bookmarks
What is the advantage of using log softmax instead of softmax
3 answers
4 votes
163 views
1 bookmarks
Are dimensionality reduction techniques useful in deep learning
3 answers
3 votes
2k views
1 bookmarks
why do we need row sampling in random forests?
1 answers
3 votes
386 views
training model on random samples from a large dataset
2 answers
2 votes
329 views
Understanding the filter function in Convolution Neural Networks
1 answers
2 votes
132 views
Distribution plot of word embeddings
1 answers
1 votes
78 views
What is a distribution-wise asymmetric measure?
1 answers
1 votes
108 views
Can Sequence to sequence models be used to convert code from one programming language to another?
2 answers
1 votes
128 views
1 bookmarks
What are the differences between logistic and linear regression?
1 answers
1 votes
1k views
1 bookmarks
padding on mnist for LeNet Architecture
1 answers
1 votes
76 views
how to encode labels for relationship extraction
1 answers
1 votes
67 views
Isn't the depth of a convolutional layer, the number of colors (or colorspace size)?
2 answers
0 votes
2k views
1 bookmarks
ValueError in CNN+RNN model in keras
1 answers
0 votes
2k views
Does Convolution kernel size affect number of channels?
1 answers
0 votes
76 views
Understanding Exclusive-OR predictions in Elman network
1 answers
0 votes
576 views
1 bookmarks
Outputs of an LSTM Cell
1 answers
0 votes
464 views
training when Multiple labels per image
3 answers
0 votes
264 views
can machine learning/Deep learning used to minimize an objective function?
1 answers
0 votes
462 views
why this naming convention for padding as "Same" and "Valid" in keras