user avatar
user avatar
user avatar
Hugh Perkins
  • Member for 10 years, 3 months
  • Last seen more than a week ago
28 votes

What are "residual connections" in RNNs?

22 votes
Accepted

Gradient backpropagation through ResNet skip connections

17 votes
Accepted

How to train LSTM model on multiple time series data?

15 votes
Accepted

Data augmentation on training set only?

13 votes
Accepted

Can a standard deviation of raw scores be reported as a standard deviation of percentages?

11 votes

What is the reason that the Adam Optimizer is considered robust to the value of its hyper parameters?

10 votes

Modern Use Cases of Restricted Boltzmann Machines (RBM's)?

10 votes

What is the difference between regular PCA and probabilistic PCA?

9 votes

What is the root cause of the class imbalance problem?

8 votes

need intuition: why is there no winning strategy to this game?

7 votes

How to interpret the results when both ridge and lasso separately perform well but produce different coefficients

6 votes
Accepted

How do we incorporate new information into a Dirichlet prior distribution?

6 votes
Accepted

How to distinguish episodic task and continuous tasks?

5 votes
Accepted

Interpret predictions of black box models

5 votes
Accepted

LSTM clarification on output

5 votes

What are the benefits of using ReLU over softplus as activation functions?

5 votes

deep learning - word embedding with parts of speech

4 votes

How to find derivative of softmax function for the purpose of gradient descent?

4 votes
Accepted

In the Metropolis algorithm, if the ratio of probabilities $r$ is less than $1$, why not directly reject instead of accepting with probability $r$?

4 votes
Accepted

How to train a CNN with multiple heads?

4 votes
Accepted

What does alignment between input and output mean for recurrent neural network

4 votes

When is $\mathbb{E}\left[\frac{1}{\sum X_{i}}\right] = \frac{1}{\mathbb{E}\left[\sum X_{i}\right]}$?

3 votes
Accepted

What are nodes in RNN/LSTM?

3 votes
Accepted

Assumptions on class priors in expectation-maximization?

3 votes

MCMC: invalid covariance matrix due to numerical error

3 votes

Restricted Boltzmann Machine : how is it used in machine learning?

3 votes

What problem does Residual Nets solve that batch normalization does not solve?

3 votes
Accepted

Sequence to Sequence models: Why is the start sequence (e.g. "</s>") required?

3 votes
Accepted

If z is uniform normal is $f(z;\theta)$ a normal distribution

3 votes
Accepted

Deep neural networks versus tall neural networks