Data Science Stack Exchange
Data Science Stack Exchange

Questions tagged [convolution]

For use when discussing the commutative and linear, but not associative operator interpreted on functions and distributions.

The convolution of the functions $f(t)$, $g(t)$ (interpreted on $]-\infty,\infty[$) is defined as

$$(f * g)(t)=\int_{-\infty}^{\infty} f(t)g(x-t)dt$$

Or in the discrete case,

$$(f * g)(n) = \sum_{k \in D} f(k) g(n - k)$$

enter image description here

285 questions
4
votes
2 answers

Why does a randomly initialised convolution kernel correspond to an edge detector?

In this nice tutorial about CNNs, the authors build a single-layer CNN. The initial convolution weights are set randomly, according to a uniform distribution. By the end of this scetion, the authors note that the randomly initialised kernel behaves…
Emiswelt
  • 143
  • 4
2
votes
0 answers

How can I inverse a transposed convolutional layer?

I am interested in inversing a transposed convolution operation (or "deconvolution", and not straightforward convolution). A transposed convolution usually maps data points from a smaller feature space (latent space) onto a much larger feature space…
Kang Min Yoo
  • 121
  • 1
2
votes
0 answers

When should I use dilated convolution?

I read the wavenet paper and I am clear about why they used Dilated Convolution. According to it they used this for give the causal property for the model. Where they wanted to introduced a sequential behavior . But lot of posts say it can use to…
Shamane Siriwardhana
  • 827
  • 1
  • 8
  • 25
2
votes
1 answer

What exactly means CNN is position equivariant

There is quite a good explanation which fully comply with my vision. But seems it lacks one final step. As Jean states, moving an object significantly in the input image will cause the change in which neuron is activated in the yellow layer (the one…
noname7619
  • 323
  • 2
  • 9
1
vote
1 answer

Output of a convolutional layer

Is the calculated output correct?
PeterBe
  • 83
  • 2
  • 10
0
votes
1 answer

1x1 Convolution learnable parameters

Here is a code snippet wherein I add two convolution layers one with 3x3 filter followed by a layer with 1x1 filter. While I am sure how the parameters are calculated for 3x3 filter, I could not figure out the learnable parameter calculation for 1x1…
Ananth Subramanian
  • 1
0
votes
1 answer

Сlassification using convolutional layers

I have a simple neural network of 2 layers, recognizing 10 classes: self.layer1 = nn.Sequential( nn.Conv2d(1, 32, kernel_size=5, stride=1, padding=2), nn.ReLU(), nn.MaxPool2d(kernel_size=2, stride=2)) self.fc1 = nn.Linear(14 * 14 * 32,…
Hey
  • 1
  • 2