rawwar's user avatar
rawwar's user avatar
rawwar's user avatar
rawwar
  • Member for 4 years, 11 months
  • Last seen more than a month ago
20 votes
2 answers
24k views

What is the advantage of using log softmax instead of softmax?

13 votes
4 answers
4k views

Is Gradient Descent central to every optimizer?

4 votes
3 answers
174 views

Are dimensionality reduction techniques useful in deep learning

3 votes
3 answers
3k views

why do we need row sampling in random forests?

3 votes
1 answer
417 views

training model on random samples from a large dataset

2 votes
1 answer
203 views

Distribution plot of word embeddings

2 votes
2 answers
340 views

Understanding the filter function in Convolution Neural Networks

1 vote
1 answer
74 views

Isn't the depth of a convolutional layer, the number of colors (or colorspace size)?

1 vote
1 answer
87 views

how to encode labels for relationship extraction

1 vote
2 answers
133 views

What are the differences between logistic and linear regression?

1 vote
1 answer
1k views

padding on mnist for LeNet Architecture

1 vote
1 answer
111 views

What is a distribution-wise asymmetric measure?

1 vote
1 answer
114 views

Can Sequence to sequence models be used to convert code from one programming language to another?

0 votes
1 answer
550 views

training when Multiple labels per image

0 votes
1 answer
618 views

Outputs of an LSTM Cell

0 votes
1 answer
93 views

Understanding Exclusive-OR predictions in Elman network

0 votes
1 answer
2k views

Does Convolution kernel size affect number of channels?

0 votes
2 answers
2k views

ValueError in CNN+RNN model in keras

0 votes
1 answer
494 views

why this naming convention for padding as "Same" and "Valid" in keras

0 votes
3 answers
376 views

can machine learning/Deep learning used to minimize an objective function?