Frames Learned by Prime Convolution Layers in a Deep Learning Framework.
basic_science · Level V
Where this comes from
- Record sourced from PubMed, PMID 32721900.
- Also identified by DOI 10.1109/TNNLS.2020.3009059.
- No licence information is recorded for this record.
- Because redistribution is not established, this page shows the abstract only. Follow the links below for the full text.
Abstract
This brief addresses understandability of modern machine learning networks with respect to the statistical properties of their convolution layers. It proposes a set of tools for categorizing a convolution layer in terms of kernel property (meanlet, differencelet, or distrotlet) or kernel sequence property (frame spectra and intralayer correlation matrix). These tools are expected to be relevant for determining the generalization capabilities of a convolutional neural network. In particular, this brief highlights that the less frequency penalizing network among AlexNet, GoogleNet, RESNET101, and VGG19 is the more relevant one in terms of solutions for low-level ice-sheet feature enhancement.