# Tag Info

0

No, because each output from a convolution layer only looks at a local region of the image. A convolution layer cannot do any global transformation, only local ones. Convolution layers must have translation invariance which means if it converts an eyeball to a tail at one position, it'll also convert the same eyeball to the same tail if it's found at a ...

1

Learning "border effects" is another reason to use padding at least in convolutional neural networks. This paper specifically looks at 2D CNNs for image processing. In my experience, I use pre-padding with 1D CNNs for NLP so my model can learn morphological affixes.

0

Probably closely related to the problem of interest would be something akin Neural Radiance Fields (NeRF for short) https://www.matthewtancik.com/nerf. The model takes several images from different angles and view of the scene and learns a 3d representation of the scene, that can be used to sample novel views of this scene (not present in the training data). ...

1

The convolution operation performed by most CNNs that you will find (on the web) assumes that the signals/functions are discrete and 2-dimensional (e.g. images can be viewed as 2-dimensional discrete signals), although this does not have to be the case. In fact, 1D and 3D convolutions are also implemented in several deep learning libraries (see here for an ...

0

Without the specific context, I cannot give a definitive answer, but it's very likely that a "differentiable architecture" refers to a neural network that represents/computes a differentiable function (so you need to use differentiable activation functions, such as the sigmoid), i.e. you can take the partial derivatives of the loss function with ...

1

It is true that when using local attention with a window of size 5, the "receptive field" is the same as a CNN with kernel size 5 (or two CNN layers with kernel size 3). However, there is a key difference in how the learned weights are applied to the inputs. In a CNN, the values of the many convolutional kernels are learned, but once learned, the ...

2

Neural networks are not invariant to translations, but equivariant, Invariance vs Equivariance Suppose we have input $x$ and the output $y=f(x)$ of some map between spaces $X$ and $Y$. We apply transformation $T$ in the input domain. For general map,output will change in some complicated and unpredictable way. However, for certain class of maps, change of ...

4

Yes, you can fix (or freeze) some of the weights during the training of a neural network. In fact, this is done in the most common form of transfer learning (which is described here). I don't know exactly how this affects learning in general. In transfer learning, this is definitely beneficial, as we are freezing the weights that are associated with the ...

0

I don't think that the input size inconsistency won't leave out spatial information in the Convolutional Neural Network. The image resizing would loose the characteristics of the object on the image. It looks like that you don't want to crop your input image, which looks like being fabricated. I like to suggest these preprocessing before the Convolutional ...

Top 50 recent answers are included