Artificial Intelligence Stack Exchange

0 votes

0 answers

4 views

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

puradrogasincortar

101

asked 12 hours ago

0 votes

0 answers

35 views

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

Filippo Portera

3

modified yesterday

0 votes

2 answers

25 views

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

NikoNyrh

560

answered Jan 27 at 16:17

1 vote

2 answers

28 views

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

CommunityBot

1

modified Jan 27 at 13:05

2 votes

1 answer

91 views

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

CommunityBot

1

modified Jan 27 at 11:08

0 votes

1 answer

41 views

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

SickerDude43

11

answered Jan 27 at 9:44

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?

Murat Şahin

11

answered Jan 23 at 3:13

1 vote

1 answer

52 views

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

CommunityBot

1

modified Jan 22 at 0:09

2 votes

1 answer

37 views

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

CommunityBot

1

modified Jan 20 at 13:09

0 votes

1 answer

46 views

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

CommunityBot

1

modified Jan 20 at 12:03

1 vote

2 answers

212 views

Which neuron represents which part of the input?

CommunityBot

1

modified Jan 18 at 0:06

2 votes

2 answers

618 views

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

Murat Şahin

11

answered Jan 17 at 23:31

1 vote

1 answer

767 views

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

CommunityBot

1

modified Jan 17 at 18:07

1 vote

1 answer

101 views

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

CommunityBot

1

modified Jan 16 at 15:05

Stack Exchange Network

Explore our questions

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

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

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

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

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

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

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?

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

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

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

Which neuron represents which part of the input?

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

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

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

Hot Network Questions