Lerner Zhang's user avatar
Lerner Zhang's user avatar
Lerner Zhang's user avatar
Lerner Zhang
  • Member for 8 years, 2 months
  • Last seen this week
52 votes

What does kernel size mean?

42 votes

Maximum likelihood method vs. least squares method

34 votes

When should I use a variational autoencoder as opposed to an autoencoder?

20 votes

Is binary logistic regression a special case of multinomial logistic regression when the outcome has 2 levels?

15 votes

What is the difference between Conv1D and Conv2D?

13 votes

Why does logistic regression produce well-calibrated models?

11 votes
Accepted

Dynamic graphs versus static graphs in deep learning libraries

10 votes

Gradient backpropagation through ResNet skip connections

8 votes

Intuition on the Kullback–Leibler (KL) Divergence

7 votes

Why do we minimize the negative likelihood if it is equivalent to maximization of the likelihood?

7 votes

Understanding LSTM units vs. cells

7 votes

What is the benefit of the truncated normal distribution in initializing weights in a neural network?

7 votes

Hidden Markov Model vs Recurrent Neural Network

6 votes
Accepted

introductory machine learning concept questions

6 votes

What exactly is a hypothesis space in machine learning?

6 votes

Structure of Recurrent Neural Network (LSTM, GRU)

6 votes

Where should I place dropout layers in a neural network?

5 votes

What is the role of the logarithm in Shannon's entropy?

5 votes

Meaning of model calibration

5 votes

Why do we use the mean-field approximation for variational Bayes?

5 votes

Does independence imply conditional independence?

5 votes
Accepted

Why use sinusoidal along embedding dimension in positional encoding in transformers?

4 votes

Multivariate time series forecasting and LSTM: When should I separate time series in different inputs

4 votes
Accepted

Understanding dropout method: one mask per batch, or more?

4 votes

If the curse of dimensionality exists, how does embedding search work?

4 votes

What is the reason that a likelihood function is not a pdf?

4 votes

Need help to understand Maximum Likelihood Estimation for multivariate normal distribution?

4 votes

How to manually calculate the intercept and coefficient in logistic regression

4 votes

Relationship between KL divergence and entropy

4 votes

What is the difference between a multiclass and a multilabel problem?

1
2 3 4 5
7