Skip to main content

Questions tagged [affine-transformations]

The tag has no usage guidance.

Filter by
Sorted by
Tagged with
-1 votes
0 answers
30 views

Find an explicit mapping in the two-dimensional space to transform the linearly nonseparable dataset into a linearly separable one

Q: Find an explicit mapping in the two-dimensional space to transform the linearly nonseparable dataset into a linearly separable one. Show the transformed data points on a plot. I tried many non ...
Ankit Basu's user avatar
0 votes
0 answers
24 views

How does the relu nonlinearity allow for nonlinear polynomial transformations?

Since the neural network nonlinearities allow for nonlinear transformations that can stretch and squish the function, how can the ReLU activation function do this? I think for the sigmoid nonlinearity ...
Vivek Reddy's user avatar
0 votes
1 answer
75 views

What is the expression for projective transformation?

The following are the two types are projections that are generally used in image processing Affine transformation Projective transformation Affine transformation is a backbone operation in neural ...
hanugm's user avatar
  • 3,930
1 vote
0 answers
23 views

Is there any concept like 'applying affine transformation on multiple inputs'?

Affine transformation on $X$ is a transformation of the following form $$Y = wX + b$$ In general, $w, X, Y$ and $b$ tensors. We generally call tensor $X$ as an input to affine transformation or the ...
hanugm's user avatar
  • 3,930
1 vote
0 answers
94 views

Which product operation should be used in affine transformation?

Affine transformation as I am aware can be expressed as either dot product followed by addition or a matrix multiplication followed by addition $$a.x+b$$ $$a^{T}x + b$$ where the first one is based on ...
hanugm's user avatar
  • 3,930
1 vote
0 answers
52 views

If you have a very distorted image, would affine transformations applied to images make object detection algorithms make more mistakes?

If you have a very distorted video/image, would affine transformations of the images make object detection algorithms make more mistakes compared to a normal camera?
James's user avatar
  • 71