2
votes
Can a concept/feature be represented using more than one layer of a Neural Network?
You cannot reason in a mathematical way over features in my opinion, as they are not defined. However, you can think of deep neurons as a hierarchy of always more high level concepts, as observed in ...
2
votes
Is it possible to reconstruct convolutional layers' input using transposed convolution?
Alexander has some great explanations above.
After doing some more research myself I came up with some understandings as well.
One interpretation of transposed convolution is that it can be seen as ...
2
votes
Accepted
Is it possible to reconstruct convolutional layers' input using transposed convolution?
You're not able reconstruct convolutional layers' inputs using transposed convolutions (in most cases). The term invert is a bit confusing here -- I interpret this to mean inverting the space of ...
2
votes
How translation invariance is achieved in CNNs?
Take a vector: $V_1 = [v_1, v_2, ..., v_n]$
Calculate the max: $m_1 = \max V_1 = v_i$
Shuffle the vector: $V_2 = mix(V_1)$
Calculate the max: $m_2 = \max V_2 = v_j$
The only possible outcome is that $...
2
votes
Temporally Non-Aware RNN
Listen, this is not an answer to your question, but it seems that you are missing the whole point of convolution.
Simplified explanation:
Convolution is just a weighted sum of the neighbors of a pixel
...
1
vote
Accepted
What is the best lightweight alternative to VGG16 for image fingerprinting?
If you are looking for lightweights architecture, take a look at backbones designed for mobile such as MobileNet V3 or GhostNet V2 .
1
vote
When training a CNN, what are the hyperparameters to tune first?
It depends a lot on what type of architecture you are using. However, most of the standard architectures are quite stable and there is no need for much hypreparameter tuning.
Choose whether you want ...
1
vote
Image segmentation with varying resolution
Usually the solution would be just to add padding, and use a model that is trained to handle padding.
In other words, fix a resolution, and then downscale the image you are handling to fit in that ...
1
vote
How translation invariance is achieved in CNNs?
When you apply a convolutional layer to an image $x$, you obtain a certain list of values:
$$h_1(x), h_2(x), h_3(x), ..., h_n(x) \tag 1$$
where each $h_i$ is just the function that applies the ...
Only top scored, non community-wiki answers of a minimum length are eligible
Related Tags
convolutional-neural-networks × 1144neural-networks × 310
deep-learning × 289
machine-learning × 149
computer-vision × 137
image-recognition × 101
convolution × 71
classification × 63
object-detection × 62
keras × 58
training × 54
image-processing × 50
tensorflow × 46
convolutional-layers × 46
image-segmentation × 43
filters × 42
recurrent-neural-networks × 40
python × 36
backpropagation × 36
comparison × 34
reference-request × 33
datasets × 31
object-recognition × 29
pytorch × 28
terminology × 26