Skip to main content
Artificial Intelligence

Return to Question

added 12 characters in body; edited tags; edited title
Source Link
nbro
nbro
  • 41.4k
  • 12
  • 114
  • 205

How to implement an "unknown" class in NNmulti-class classification with neural networks?

For example, I need to detect classes for MNIST data. But I want to have not 10 classes for digits, but also I want to have 11th class "not a digit". So, so that any letter (except "O" of course:) ), any other type of image, or random noise would be classified as "not a digit".

Or Similarly, with CIFAR-10, I want to have the 11th "unknown" class to classify any image that containcontains something out of the available 10 classes rangeof CIFAR-10.

So, how to implement such a feature? Maybe Maybe there are some examples somewhere, preferable with Keras.

How to implement an "unknown" class in NN classification?

For example I need to detect classes for MNIST data. But I want to have not 10 classes for digits but also I want to have 11th class "not a digit". So that any letter (except "O" of course:) ), any other type of image or random noise would be classified as "not a digit".

Or with CIFAR-10 I want to have 11th "unknown" class to classify any image that contain something out of classes range.

So how to implement such feature? Maybe there are some examples somewhere, preferable with Keras.

How to implement an "unknown" class in multi-class classification with neural networks?

For example, I need to detect classes for MNIST data. But I want to have not 10 classes for digits, but also I want to have 11th class "not a digit", so that any letter, any other type of image, or random noise would be classified as "not a digit". Similarly, with CIFAR-10, I want to have the 11th "unknown" class to classify any image that contains something out of the available 10 classes of CIFAR-10.

So, how to implement such a feature? Maybe there are some examples somewhere, preferable with Keras.

Source Link
Sergey Kravchenko
Sergey Kravchenko
  • 311
  • 1
  • 2
  • 5

How to implement an "unknown" class in NN classification?

For example I need to detect classes for MNIST data. But I want to have not 10 classes for digits but also I want to have 11th class "not a digit". So that any letter (except "O" of course:) ), any other type of image or random noise would be classified as "not a digit".

Or with CIFAR-10 I want to have 11th "unknown" class to classify any image that contain something out of classes range.

So how to implement such feature? Maybe there are some examples somewhere, preferable with Keras.