all AI news
Bio-inspired Min-Nets Improve the Performance and Robustness of Deep Networks. (arXiv:2201.02149v1 [cs.CV])
Jan. 7, 2022, 2:10 a.m. | Philipp Grüning, Erhardt Barth
cs.CV updates on arXiv.org arxiv.org
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 the popular ResNet and DenseNet, and
show that the resulting Min-Nets perform better on the Cifar-10 benchmark.
Moreover, we show that Min-Nets are more robust against JPEG compression
artifacts. We argue that the minimum operation is the simplest way of
implementing an AND operation on pairs of filters and that such AND operations …
More from arxiv.org / cs.CV updates on arXiv.org
Jobs in AI, ML, Big Data
Senior ML Researcher - 3D Geometry Processing | 3D Shape Generation | 3D Mesh Data
@ Promaton | Europe
Principal Data Engineer
@ RS21 | Remote
SQL/Power BI Developer
@ ICF | Virginia Remote Office (VA99)
Senior Machine Learning Engineer (Canada Remote)
@ Fullscript | Ottawa, ON
Software Engineer - MLOps.
@ Renesas Electronics | Toyosu, Japan
Junior Data Scientist / Artificial Intelligence consultant
@ Deloitte | Luxembourg, LU