Maxim's user avatar
Maxim's user avatar
Maxim's user avatar
Maxim
  • Member for 7 years, 9 months
  • Last seen more than a week ago
31 votes
Accepted

Why ReLU is better than the other activation functions

13 votes

Word2Vec embeddings with TF-IDF

10 votes
Accepted

Why do so many functions used in data science have derivatives of the form f(x)*(1-f(x))?

4 votes

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

2 votes

Transfer learning within Tensorflow's inception model

2 votes

How do neural networks account for outliers?

2 votes
Accepted

RNN: why Wx + Uh instead of W[x,h]

1 vote
Accepted

How to associate array of class probabilities with corresponding image in keras?

1 vote
Accepted

Word2Vec, softmax function

1 vote

Datasets in NLP research papers

1 vote

Do numerical inaccuracies play any role in training neural networks?