User Hugh Perkins

28 votes

What are "residual connections" in RNNs?

answered Jan 1, 2018 at 21:01

22 votes

Accepted

Gradient backpropagation through ResNet skip connections

machine-learning neural-networks conv-neural-network gradient-descent backpropagation

answered Mar 21, 2017 at 8:42

17 votes

Accepted

How to train LSTM model on multiple time series data?

machine-learning time-series statistical-significance lstm artificial-intelligence

answered Jul 25, 2018 at 1:56

15 votes

Accepted

Data augmentation on training set only?

machine-learning deep-learning regularization data-augmentation

answered Dec 31, 2017 at 3:00

13 votes

Accepted

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

mean standard-deviation percentage

answered Oct 4, 2017 at 10:49

11 votes

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

neural-networks deep-learning optimization hyperparameter adam

answered Oct 9, 2017 at 20:35

10 votes

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

references deep-learning restricted-boltzmann-machine generative-models

answered Oct 9, 2017 at 20:46

10 votes

What is the difference between regular PCA and probabilistic PCA?

pca

answered Oct 9, 2017 at 20:56

9 votes

What is the root cause of the class imbalance problem?

classification predictive-models unbalanced-classes scoring-rules

answered Mar 18, 2017 at 23:19

8 votes

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

probability expected-value intuition puzzle

answered Mar 26, 2017 at 21:01

7 votes

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

regression predictive-models feature-selection lasso ridge-regression

answered Mar 14, 2017 at 12:44

6 votes

Accepted

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

bayesian ensemble-learning dirichlet-distribution

answered Oct 9, 2017 at 14:17

6 votes

Accepted

How to distinguish episodic task and continuous tasks?

machine-learning terminology reinforcement-learning

answered Apr 2, 2017 at 8:50

5 votes

Accepted

Interpret predictions of black box models

machine-learning interpretation prediction

answered Mar 27, 2017 at 12:36

5 votes

Accepted

LSTM clarification on output

lstm keras

answered Mar 26, 2017 at 13:24

5 votes

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

machine-learning neural-networks

answered Mar 16, 2017 at 10:03

5 votes

deep learning - word embedding with parts of speech

neural-networks deep-learning natural-language conv-neural-network word-embeddings

answered Feb 12, 2018 at 0:08

4 votes

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

neural-networks backpropagation derivative softmax

answered Feb 12, 2018 at 0:28

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 $r$?

bayesian markov-chain-montecarlo metropolis-hastings rejection-sampling

answered Mar 23, 2017 at 23:51

4 votes

Accepted

How to train a CNN with multiple heads?

machine-learning classification neural-networks conv-neural-network

answered Mar 24, 2017 at 12:10

4 votes

Accepted

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

machine-learning neural-networks recurrent-neural-network

answered Apr 5, 2017 at 12:32

4 votes

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

expected-value

answered Oct 16, 2017 at 8:01

3 votes

Accepted

What are nodes in RNN/LSTM?

terminology lstm recurrent-neural-network

answered Mar 27, 2017 at 8:52

3 votes

Accepted

Assumptions on class priors in expectation-maximization?

machine-learning clustering expectation-maximization unsupervised-learning

answered Mar 27, 2017 at 8:55

3 votes

MCMC: invalid covariance matrix due to numerical error

markov-chain-montecarlo multivariate-normal-distribution

answered Apr 2, 2017 at 7:44

3 votes

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

machine-learning neural-networks deep-learning deep-belief-networks restricted-boltzmann-machine

answered Mar 18, 2017 at 22:13

3 votes

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

machine-learning neural-networks deep-learning

answered Dec 28, 2017 at 0:52

3 votes

Accepted

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

machine-learning neural-networks natural-language

answered Jan 2, 2018 at 2:34

3 votes

Accepted

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

variational-bayes generative-models

answered Nov 25, 2017 at 15:45

3 votes

Accepted

Deep neural networks versus tall neural networks

neural-networks deep-learning

answered Jul 24, 2018 at 0:11

Stack Exchange Network

current community

your communities

more stack exchange communities

106 Answers

What are "residual connections" in RNNs?

Gradient backpropagation through ResNet skip connections

How to train LSTM model on multiple time series data?

Data augmentation on training set only?

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

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

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

What is the difference between regular PCA and probabilistic PCA?

What is the root cause of the class imbalance problem?

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

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

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

How to distinguish episodic task and continuous tasks?

Interpret predictions of black box models

LSTM clarification on output

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

deep learning - word embedding with parts of speech

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

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

How to train a CNN with multiple heads?

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

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

What are nodes in RNN/LSTM?

Assumptions on class priors in expectation-maximization?

MCMC: invalid covariance matrix due to numerical error

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

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

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

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

Deep neural networks versus tall neural networks