user avatar
user avatar
user avatar
user3658307
  • Member for 5 years, 11 months
  • Last seen more than 2 years ago
44 votes
Accepted

Deriving the KL divergence loss for VAEs

6 votes

Bayesian nonparametric answer to deep learning?

6 votes

Why is the log derivative estimator considered of large variance?

5 votes

ADAM Gradient descent oscillates close to minimum

5 votes
Accepted

Generating vector image from a hand drawn picture. Machine Learning

5 votes

Object detection : is deep learning the only way to go?

4 votes

Could anyone explain the terms "Hypothesis space" "sample space" "parameter space" "feature space in machine learning with one concrete example?

4 votes
Accepted

Ornstein-Uhlenbeck process

4 votes
Accepted

Is the first principal component the one with the largest eigenvalue and how to convert it to explained variance?

4 votes
Accepted

covariance to correlation is like mutual information to --?

4 votes

How meaningful is the connection between MLE and cross entropy in deep learning?

3 votes
Accepted

What is a good loss function for object localisation and classification using a cnn?

3 votes
Accepted

On Yolo, and its loss function

3 votes

Understanding the YOLO algorithm

3 votes

Regression as mutual information minimization

3 votes

How to choose an appropriate variational distribution?

3 votes
Accepted

Linear regression with error dispersion dependent on the independent variable

2 votes
Accepted

Where's wrong in my reasoning behind upper bound for reconstruction error?

2 votes

Are analytical derivatives unambiguously superior to numerical derivatives in GMM?

2 votes
Accepted

Choosing the number of labels in a multiclass classification problem

2 votes

Training an Object Detection Model Using with Artificial Data from Video Games

2 votes
Accepted

Why are exogenous variables not used in inference/recognition networks?

2 votes

What are the theoretical/practical reasons to use normal distribution to initialize the weights in Neural Networks?

2 votes
Accepted

What are the shortcomings of calculating the loss in pixel space vs. feature space

1 vote

What is the difference between having input parameters that are independent/dependent in ML tasks?

1 vote

Is it possible to obtain learn specific information about a distribution from a GAN?

1 vote
Accepted

Is this intuition behind understanding what the weights of a plain feedforward neural network are representing correct?

1 vote

In VAEs, why don't we just use a fixed variance for the z distribution?

1 vote

Diversity of generated samples in VAE

1 vote
Accepted

Understand VAE with VamPrior