How to define a morphology operation in a Neural Network as an activation function?

Question

I recently completed a task to study how to use morphological operation as an activation function for neural networks. But I had no idea and didn't know how to use keras for custom functionality. Can anyone provide Suggestions or related papers?

This [link](https://arxiv.org/pdf/1901.00109.pdf) might be helpful for you query. — Ankish Bansal, May 02 '19 at 03:52

score 0 · Answer 1 · answered May 27 '19 at 18:05

I don't know if morphological operations will work as activation function. I don't think so. I think you should use or combine morphological operations like dilation and erosion, and, after that, use a ReLU or softmax layer as activation function.

Morphological operations are available in tensorflow, and you can call them in your Keras application.

Reference links:

Thank you very much. I also think the morphological operations cannot work as an activation function. — user9017848, Jul 03 '19 at 04:48

How to define a morphology operation in a Neural Network as an activation function?

1 Answers1