Gerry P's user avatar
Gerry P's user avatar
Gerry P's user avatar
Gerry P
  • Member for 4 years, 1 month
  • Last seen more than 1 year ago
  • Scottsdale, AZ, USA
5 votes

Would it be ethical to allow an AI to make life-or-death medical decisions?

3 votes

Would this relatively small dataset be enough to train a CNN?

3 votes

What kind of optimizer is suggested to use for binary classification of similar images?

3 votes
Accepted

Why do we regularize the variational autoencoder with a normal distribution?

3 votes

What is the difference between batch and mini-batch gradient decent?

2 votes

How to estimate the accuracy upper limit of any CNN model over a computer vision classification task

2 votes
Accepted

Is it legal to construct a public image database (for deep learning) with images from the internet?

2 votes
Accepted

Why does this model have 12 parameters?

2 votes

Is a VGG-based CNN model sometimes better for image classfication than a modern architecture?

2 votes

Should neural nets be deeper the more complex the learning problem is?

2 votes
Accepted

When would bias regularisation and activation regularisation be necessary?

1 vote

How to train the images of various sizes?

1 vote

What to do if CNN cannot overfit a training set on adding dropout?

1 vote
Accepted

House price inflation modelling

1 vote

My CNN model performs bad on new (self-created) pictures, what are possible reasons?

1 vote

Which neural network to use for optical mark recognition?

1 vote

How are non-linear surfaces formed in the training of a neural network?

1 vote
Accepted

Is radial basis function network appropriate for small datasets?

1 vote

Is there an online tool that can predict accuracy given only the dataset?

1 vote

How to deal with random weights initialization in hyperparameters tuning?

1 vote

How is a validation set used to tune the hyperparameters in a non-biased way, if the new models depends on the values of these?

1 vote
Accepted

Is this model overfitted or not?

1 vote

Should I apply image processing techniques to the inputs of convolution networks?

1 vote

Is the choice of the optimiser relevant when doing object detection?

1 vote

Aren't all discrete convolutions (not just 2D) linear transforms?

1 vote

Running 10 epochs on the Food-101 dataset

1 vote
Accepted

What happens if I train a network for more epochs, without using early stopping?

1 vote

Are there tools to help clean a large dataset so that it only contains faces?

1 vote

How to best make use of learning rate scheduling in reinforcement learning?

0 votes

How can I train a neural network to describe the characteristics of a picture?