Paper Info
Title
Log-Nets: Logarithmic Feature-Product Layers Yield More Compact Networks.
Abstract
We introduce Logarithm-Networks (Log-Nets), a novel bio-inspired type of network architecture based on logarithms of feature maps followed by convolutions. Log-Nets are capable of surpassing the performance of traditional convolutional neural networks (CNNs) while using fewer parameters. Performance is evaluated on the Cifar-10 and ImageNet benchmarks.
Year
DOI
Venue
2020
10.1007/978-3-030-61616-8_7
ICANN (2)
DocType
Citations 
PageRank 
Conference
0
0.34
References 
Authors
0
3
Name
Order
Citations
PageRank
Philipp Grüning100.68
Thomas Martinetz2656.13
Erhardt Barth365358.33