Escachator's user avatar
Escachator's user avatar
Escachator's user avatar
Escachator
  • Member for 7 years, 8 months
  • Last seen more than a month ago
20 votes
Accepted

How does Gradient Descent and Backpropagation work together?

3 votes
Accepted

how does minibatch for LSTM look like?

3 votes
Accepted

Why do we Softmax at all?

3 votes
Accepted

understanding linear algebra of a forget gate

2 votes

Which scaling size is better? [0,1] or [-1,1] for LSTM?

1 vote

Is there any standard or normal range for the amount of LSTM loss function?

1 vote

80-20 better than full dataset for LightGBM

1 vote

Products classification by name

1 vote

Unstable results when I train a CNN

1 vote

Batch Normalization will disrupt multi-threading?

1 vote

What is a lower bound on the vocabulary size for generating word/sentence embedding using word2vec or skip thought vectors?

1 vote

LSTM -RNN : How to get continuous range output instead of categorical?

1 vote
Accepted

How to put multiple features into RNN input vector

1 vote

Training NLP with multiple text input features

0 votes

What does the "Loss" value given by Keras mean?

0 votes
Accepted

Gradient Boosting RandomSearchCV or GridSearchCV

0 votes

How to train neural word embeddings?

0 votes

How can one use unstructured data for forecasting?

0 votes

Find optimal P(X|Y) given I have a model that has good performance when trained on P(Y|X)

0 votes

What is the difference between "Adding more LSTM layers" or "Adding more units on existence layers"?