5 citations · 8 across the 2 of their papers we have counts for
2 papers
cs.CV2022★ 5 cited
Bio-inspired Min-Nets Improve the Performance and Robustness of Deep Networks
Philipp Grüning, Erhardt Barth
Min-Nets are inspired by end-stopped cortical cells with units that output the minimum of two learned filters. We insert such Min-units into state-of-the-art deep networks, such as…
cs.CV2020★ 3 cited
Feature Products Yield Efficient Networks
Philipp Grüning, Thomas Martinetz, Erhardt Barth
We introduce Feature-Product networks (FP-nets) as a novel deep-network architecture based on a new building block inspired by principles of biological vision. For each input featu…