DEEPLIZARD Demo

Interactive Visual by deeplizard

Max Pooling Operation in Neural Networks

In deep learning, max pooling is a type of operation that is typically added to convolutional neural networks following individual convolutional layers. When added to a network, max pooling reduces the size of images by reducing the number of pixels in the output from the previous convolutional layer.

DEEPLIZARD Message notifications

Demo Tips

Here are some helpful tips to consider when using the app:

  • Hover over the pixel values in the output to see the corresponding window in the input.
  • Try different values for the filter parameters to see how filter size and stride affect the output.
  • The application works on mobile but performs best on desktop. We tested on a limited number of mobile devices. Let us know if you run into issues on your device.
Max Pooling Demo Application settings

Input

Output