Skip to main content
user12075's user avatar
user12075's user avatar
user12075's user avatar
user12075
  • Member for 8 years, 7 months
  • Last seen more than 4 years ago
39 votes
Accepted

What is Monte Carlo dropout?

15 votes
Accepted

What is the difference between SGD classifier and the Logisitc regression?

10 votes
Accepted

What to do if training loss decreases but validation loss does not decrease?

6 votes

How does tensor product/multiplication work in TensorFlow?

4 votes
Accepted

Combining spatial input with a label as input for CNN using Keras

4 votes

Why is my neural net getting a poor accuracy?

4 votes
Accepted

Interpretation of the loss function for word2vec

4 votes
Accepted

Tensorflow: how to look up and average a different amount of embedding vectors per training instance, with multiple training instances per minibatch?

3 votes
Accepted

LSTM future steps prediction with shifted y_train relatively to X_train

3 votes

Why is the reported loss different from the mean squared error calculated on the train data?

3 votes
Accepted

How to add numbers to the axes of a graph?

3 votes
Accepted

What does the one function $\mathbf{1}_{i,y^{(t)}}$ exactly mean in backward propagation of RNN in the book "Deep learning" of Bengio

2 votes
Accepted

Should I use rescale parameters for data augmentation?

2 votes

What does GlobalMaxPooling1D() do to output of LSTM unit in Keras?

2 votes

Error when box plot

2 votes
Accepted

Data augmentation in deep learning

2 votes
Accepted

How to correctly pass Word2Vec vectors as input to an LSTM

2 votes

How to replace short words into full words from tweets using python

2 votes

Is there a dataset with news articles and their headlines?

2 votes
Accepted

Policy Gradients - gradient Log probabilities favor less likely actions?

2 votes
Accepted

What's the best metric for evaluate an estimator for a multi class problem with class imbalance dataset?

2 votes
Accepted

Appending DataFrames to lists in a dictionary - why does it seem like the list is being referenced by each new DataFrame?

2 votes

Small dataset in Time series

2 votes
Accepted

How to interpret a drastic accuracy loss while training a neuronal net (CNN)?

2 votes

Which NN architecture solves my problem?

2 votes

Any tool to load large csv files quickly on windows 7

2 votes

How to model compositional data?

2 votes

Frequency for a time series

2 votes

EGAN Paper With Confusing Notation

2 votes
Accepted

What mu and sigma vector really mean in VAE?