Skip to main content
Data Science

Return to Question

Became Hot Network Question
added links, clarified question, proper quotation
Source Link
TwinPenguins
TwinPenguins
  • 4.4k
  • 3
  • 20
  • 54

I came across this question from the 3rd chapter of the book 'neuralnetworksanddeeplearning'Neural Networks and Deep Learning by michael nielsenMichael Nielsen, this is a question givena question given in his exercise.

One way of expanding the MNIST training data is to use small rotations of training images. What's a problem that might occur if we allow arbitrarily large rotations of training images?

"One way of expanding the MNIST training data is to use small rotations of training images. What's a problem that might occurI would happy if we allow arbitrarilysomeone explain why large rotations of training images?"would be problematic.

I came across this question from the 3rd chapter of the book 'neuralnetworksanddeeplearning' by michael nielsen, this is a question given in his exercise.

"One way of expanding the MNIST training data is to use small rotations of training images. What's a problem that might occur if we allow arbitrarily large rotations of training images?"

I came across this question from the 3rd chapter of the book Neural Networks and Deep Learning by Michael Nielsen, this is a question given in his exercise.

One way of expanding the MNIST training data is to use small rotations of training images. What's a problem that might occur if we allow arbitrarily large rotations of training images?

I would happy if someone explain why large rotations would be problematic.

Source Link
yashdk
yashdk
  • 169
  • 1
  • 1
  • 4

Artificially expanding the datasets through rotation of images in MNIST

I came across this question from the 3rd chapter of the book 'neuralnetworksanddeeplearning' by michael nielsen, this is a question given in his exercise.

"One way of expanding the MNIST training data is to use small rotations of training images. What's a problem that might occur if we allow arbitrarily large rotations of training images?"