Artificial Intelligence Stack Exchange is a question and answer site for people interested in conceptual questions about life and challenges in a world where "cognitive" functions can be mimicked in purely digital environment. It only takes a minute to sign up.

Sign up to join this community
Anybody can ask a question
Anybody can answer
The best answers are voted up and rise to the top

Explore our questions

0 votes
0 answers
4 views

Are there any advantages of encoding an image as a graph to use in Graph Convolutional Networks?

0 votes
0 answers
35 views

How could we implement a simple example of a Graph Convolutional layer of a Neural Network?

0 votes
2 answers
25 views

Would it be a problem to use non-squared images for a CNN model?

1 vote
2 answers
28 views

Dealing with incomplete file sets for a CNN for medical imaging regression problem

2 votes
1 answer
91 views

How to embed game grid state with walls as an input to neural network

0 votes
1 answer
41 views

Why do deep neural networks(not residual nets) suffer from poor performance?

0 votes
1 answer
14 views

How can I use CNN to make a cumulative count of the number of occurrences of each of the different objects in all the images in the test set?

1 vote
1 answer
52 views

Why is training all layers at a time effective for a multi-layer autoencoder?

2 votes
1 answer
37 views

Is there any interpretation method suitable for CNNs which do regression tasks?

0 votes
1 answer
46 views

What would be a good cost function based on both saliency-maps and labels?

1 vote
2 answers
212 views

Which neuron represents which part of the input?

2 votes
2 answers
618 views

Why does the number of feature maps increases in the VGG model?

1 vote
1 answer
767 views

In Faster R-CNN, how can I get the predicted bounding box given the neural network's output?

1 vote
1 answer
101 views

How does a VGG-based Style-Loss incorporate color information?

Browse more Questions