# Max-plus Operators Applied to Filter Selection and Model Pruning in Neural Networks

## TL;DR

This paper explores how Max-plus operators can be used in neural networks for filter selection and model pruning, demonstrating efficiency and robustness across various architectures.

## Contribution

It introduces a novel application of Max-plus layers for filter importance selection and model pruning, extending morphological neural network concepts.

## Key findings

- Max-plus layers effectively select important filters without performance loss
- Pruning based on Max-plus layers reduces model redundancy
- Max-plus networks share characteristics with Maxout networks

## Abstract

Following recent advances in morphological neural networks, we propose to study in more depth how Max-plus operators can be exploited to define morphological units and how they behave when incorporated in layers of conventional neural networks. Besides showing that they can be easily implemented with modern machine learning frameworks , we confirm and extend the observation that a Max-plus layer can be used to select important filters and reduce redundancy in its previous layer, without incurring performance loss. Experimental results demonstrate that the filter selection strategy enabled by a Max-plus is highly efficient and robust, through which we successfully performed model pruning on different neural network architectures. We also point out that there is a close connection between Maxout networks and our pruned Max-plus networks by comparing their respective characteristics. The code for reproducing our experiments is available online.