English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Zendy Plus

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Zendy Tools

Zendy Open

Following recent advances in morphological neural networks, we propose tostudy in more depth how Max-plus operators can be exploited to definemorphological units and how they behave when incorporated in layers ofconventional neural networks. Besides showing that they can be easilyimplemented with modern machine learning frameworks , we confirm and extend theobservation that a Max-plus layer can be used to select important filters andreduce redundancy in its previous layer, without incurring performance loss.Experimental results demonstrate that the filter selection strategy enabled bya Max-plus is highly efficient and robust, through which we successfullyperformed model pruning on different neural network architectures. We alsopoint out that there is a close connection between Maxout networks and ourpruned Max-plus networks by comparing their respective characteristics. Thecode for reproducing our experiments is available online.

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